[go: up one dir, main page]
More Web Proxy on the site http://driver.im/

WO2018210059A1 - 机器人充电方法及装置 - Google Patents

机器人充电方法及装置 Download PDF

Info

Publication number
WO2018210059A1
WO2018210059A1 PCT/CN2018/080273 CN2018080273W WO2018210059A1 WO 2018210059 A1 WO2018210059 A1 WO 2018210059A1 CN 2018080273 W CN2018080273 W CN 2018080273W WO 2018210059 A1 WO2018210059 A1 WO 2018210059A1
Authority
WO
WIPO (PCT)
Prior art keywords
robot
potential
charging
charging pile
data
Prior art date
Application number
PCT/CN2018/080273
Other languages
English (en)
French (fr)
Other versions
WO2018210059A9 (zh
Inventor
白静
李宇翔
陈士凯
Original Assignee
上海思岚科技有限公司
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by 上海思岚科技有限公司 filed Critical 上海思岚科技有限公司
Priority to US16/613,421 priority Critical patent/US11351681B2/en
Priority to EP18801429.4A priority patent/EP3627267B1/en
Publication of WO2018210059A1 publication Critical patent/WO2018210059A1/zh
Publication of WO2018210059A9 publication Critical patent/WO2018210059A9/zh

Links

Images

Classifications

    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B25J19/02Sensing devices
    • B25J19/021Optical sensing devices
    • B25J19/022Optical sensing devices using lasers
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B60VEHICLES IN GENERAL
    • B60LPROPULSION OF ELECTRICALLY-PROPELLED VEHICLES; SUPPLYING ELECTRIC POWER FOR AUXILIARY EQUIPMENT OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRODYNAMIC BRAKE SYSTEMS FOR VEHICLES IN GENERAL; MAGNETIC SUSPENSION OR LEVITATION FOR VEHICLES; MONITORING OPERATING VARIABLES OF ELECTRICALLY-PROPELLED VEHICLES; ELECTRIC SAFETY DEVICES FOR ELECTRICALLY-PROPELLED VEHICLES
    • B60L53/00Methods of charging batteries, specially adapted for electric vehicles; Charging stations or on-board charging equipment therefor; Exchange of energy storage elements in electric vehicles
    • B60L53/30Constructional details of charging stations
    • B60L53/35Means for automatic or assisted adjustment of the relative position of charging devices and vehicles
    • B60L53/36Means for automatic or assisted adjustment of the relative position of charging devices and vehicles by positioning the vehicle
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J19/00Accessories fitted to manipulators, e.g. for monitoring, for viewing; Safety devices combined with or specially adapted for use in connection with manipulators
    • B25J19/02Sensing devices
    • B25J19/021Optical sensing devices
    • B25J19/023Optical sensing devices including video camera means
    • BPERFORMING OPERATIONS; TRANSPORTING
    • B25HAND TOOLS; PORTABLE POWER-DRIVEN TOOLS; MANIPULATORS
    • B25JMANIPULATORS; CHAMBERS PROVIDED WITH MANIPULATION DEVICES
    • B25J9/00Programme-controlled manipulators
    • B25J9/16Programme controls
    • B25J9/1656Programme controls characterised by programming, planning systems for manipulators
    • B25J9/1664Programme controls characterised by programming, planning systems for manipulators characterised by motion, path, trajectory planning
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0212Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory
    • G05D1/0225Control of position or course in two dimensions specially adapted to land vehicles with means for defining a desired trajectory involving docking at a fixed facility, e.g. base station or loading bay
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0234Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using optical markers or beacons
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0231Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means
    • G05D1/0246Control of position or course in two dimensions specially adapted to land vehicles using optical position detecting means using a video camera in combination with image processing means
    • GPHYSICS
    • G05CONTROLLING; REGULATING
    • G05DSYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
    • G05D1/00Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
    • G05D1/02Control of position or course in two dimensions
    • G05D1/021Control of position or course in two dimensions specially adapted to land vehicles
    • G05D1/0268Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means
    • G05D1/0274Control of position or course in two dimensions specially adapted to land vehicles using internal positioning means using mapping information stored in a memory device
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/00032Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by data exchange
    • H02J7/00038Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by data exchange using passive battery identification means, e.g. resistors or capacitors
    • HELECTRICITY
    • H02GENERATION; CONVERSION OR DISTRIBUTION OF ELECTRIC POWER
    • H02JCIRCUIT ARRANGEMENTS OR SYSTEMS FOR SUPPLYING OR DISTRIBUTING ELECTRIC POWER; SYSTEMS FOR STORING ELECTRIC ENERGY
    • H02J7/00Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries
    • H02J7/0042Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by the mechanical construction
    • H02J7/0045Circuit arrangements for charging or depolarising batteries or for supplying loads from batteries characterised by the mechanical construction concerning the insertion or the connection of the batteries

Definitions

  • the invention relates to a robot charging method and device.
  • the robot remotely returns to the charging pile for a long time and has low blind efficiency. Even before the battery capacity is exhausted, the robot cannot find the charging pile to cause the battery to be over-discharged, causing damage to the battery or shutdown.
  • the existing charging pile identification method also has problems of sensitive hardware characteristics, vulnerability to environmental interference, and inaccurate identification.
  • An object of the present invention is to provide a robot charging method and apparatus, which can solve the problem that the robot remotely returns to the charging pile for a long time and has low blind efficiency.
  • a robot charging method comprising:
  • Collecting current surrounding environment data of the robot in motion generating an environment map of the environment in which the robot is located and a pose of the robot in the environment map according to the surrounding environment data, the environment map including the recorded Potential or registered charging station location;
  • the structure according to the collected identifier is The data determines the pose of the charging pile
  • the method further includes:
  • the structure data of the identifier on the charging pile is collected. If the matching degree between the structure data of the collected identifier and the pre-stored identifier template structure data is greater than a preset matching degree threshold, determining the charging pile according to the structural data of the collected identifier Pose
  • the voltage of the mobile machine after the charging pile is docked with the robot is collected.
  • the identifier comprises a reflective material of at least one protruding structure and a reflective material of at least one concave structure, wherein a depth value between the convex structure and the concave structure is greater than a preset Depth threshold.
  • the method before collecting the current surrounding environment data of the robot, the method further includes:
  • the path is The object is recorded as a potential charging post location.
  • the structural data of the identifier on the potential or registered charging pile is collected, and if the matching degree between the structural data of the collected identifier and the pre-stored identification template structure data is greater than a preset matching degree threshold, The structural data of the collected identifier determines the pose of the charging pile, including:
  • the robot moves the short-term plucking area to the preset data, and collects one potential after each movement or Structural data of the identification on the registered charging post;
  • the structural data of the identifier on the potential or registered charging pile is collected, and if the matching degree between the structural data of the collected identifier and the pre-stored identification template structure data is greater than a preset matching degree threshold, The structural data of the collected identifier determines the pose of the charging pile, including:
  • the robot will move the preset data in the short-range pile-picking area, and collect each potential after each movement. Or structural data of the identification on the registered charging post;
  • the pile determines the posture of the charging pile according to the structural data of the collected identification of the charging pile to be docked.
  • the current surrounding environment data of the robot during the movement is collected, including:
  • the current ambient data of the robot on the move is acquired by one or any combination of infrared, camera, ultrasound, and laser acquisition devices.
  • the structural data of the identification on the potential or registered charging post is acquired by one or any combination of infrared, depth camera, ultrasound, and laser acquisition devices.
  • the posture of the robot in the environment map is adjusted according to the posture of the charging pile, and the charging pile is docked with the robot for charging, including:
  • the robot is moved to a short-range ploughing docking area near a potential or registered charging pile position, including:
  • the robot continues to move into a short-range plunging docking area near a potential or registered charging pile location.
  • a robot charging apparatus comprising:
  • An acquisition positioning module configured to collect current surrounding environment data of the robot in motion, generate an environment map of the environment in which the robot is located according to the surrounding environment data, and a posture of the robot in the environment map,
  • the environmental map includes the recorded potential or registered charge pile locations;
  • a remote regression module configured to move the robot to a short-range plucking docking area near a potential or registered charging pile position according to the environment map and the pose in the environment map;
  • the self-seeking pile module is configured to collect structural data of the identifier on the potential or registered charging pile. If the matching degree of the collected structure data and the pre-stored identification template structure data is greater than a preset matching degree threshold, The structural data of the collected identifier determines the posture of the charging pile;
  • a docking module configured to adjust a posture of the robot in the environment map according to a posture of the charging pile, and connect the charging pile to a robot for charging.
  • the docking module is further configured to collect a voltage of the mobile device after the charging pile is docked with the robot, and if the collected voltage does not exceed a preset voltage threshold, the short-range searching After the docking area moves the position, the independent homing module and the docking module are repeatedly executed until the voltage collected by the docking module exceeds a preset voltage threshold.
  • the identifier comprises a reflective material of at least one protruding structure and a reflective material of at least one concave structure, wherein a depth value between the convex structure and the concave structure is greater than a preset Depth threshold.
  • the acquiring and positioning module is further configured to collect structural data of the passing object during the moving process of the robot performing the task before collecting the current surrounding environment data of the robot in the moving, if If the matching degree of the collected structural data of the collected object and the pre-stored identification template structure data is greater than a preset matching degree threshold, the passing object is recorded as a potential charging pile position.
  • the autonomous locating module is configured to: if the number of the identifiers on the potential or registered charging piles in the current short-range plucking area is one, the robot is in the short-range plucking area Presetting the movement of the secondary data, collecting the structural data of the identification on the potential or registered charging post after each movement; calculating the structural data and pre-existing of the identification on the one potential or registered charging post for each acquisition Whether the matching degree of the identifier template structure data is greater than a preset matching degree threshold, and determining that the calculated matching degree of the one potential or registered charging pile is greater than a preset matching degree threshold is greater than a preset number of times, and if so, according to The structural data of the collected identification determines the pose of the charging post.
  • the autonomous homing module is configured to: if the number of the identifiers on the potential or registered charging piles in the current short-range plucking area is multiple, the robot is in the short-range plucking area As a preset data movement, collecting structural data of the identification on each potential or registered charging post after each movement; calculating the structural data of the identification on each potential or registered charging pile for each acquisition and Whether the matching degree of the pre-stored identification template structure data is greater than a preset matching degree threshold, and calculating whether the matching degree of each potential or registered charging post is greater than a preset matching degree threshold is greater than a preset number, and the matching is performed.
  • the potential pile that is greater than the preset matching degree threshold and is greater than the preset number of potential or registered charging piles is selected as the charging pile to be docked, and the charging pile is determined according to the structural data of the collected identification of the charging pile to be docked. Position.
  • the acquisition and positioning module is configured to collect current ambient data of the robot while moving by one or any combination of infrared, camera, ultrasound, and laser collection devices.
  • the autonomous homing module is configured to collect structural data of an identifier on a potential or registered charging post by one or any combination of an infrared, a depth camera, an ultrasound, and a laser collection device.
  • the docking module is configured to collect a moving distance and a direction of the robot; and adjust the moving distance and direction of the robot according to the posture of the charging pile, and adjust the robot in the environment map. In the pose, the charging pile is docked with the robot for charging.
  • the remote regression module is configured to determine a global path of the robot movement according to a current environment map, a current pose in the environment map, and a potential or registered charging post position;
  • the global path controls the robot to move to a short-range ploughing docking area near a potential or registered charging pile location; collecting a current moving speed of the robot, according to a current environmental map, a current pose in the environmental map, and
  • the current moving speed of the robot adjusts the local trajectory of the global path and the running speed in the local trajectory to obtain an adjusted smooth collision-free global path; according to the adjusted global path, the robot continues to move Near the potential or registered charge pile location in the short-range piling area.
  • a computing based device comprising:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to:
  • Collecting current surrounding environment data of the robot in motion generating an environment map of the environment in which the robot is located and a pose of the robot in the environment map according to the surrounding environment data, the environment map including the recorded Potential or registered charging station location;
  • the structure according to the collected identifier is The data determines the pose of the charging pile
  • the present invention moves the robot to the vicinity of the potential or registered charging pile position according to the environment map and the robot self-positioning information, that is, the posture of the robot in the environment map, to avoid blindly following the wall.
  • Random walking to find the charging pile to avoid the long return time of the complex indoor environment, and does not need to have certain ability to distinguish the wall and island obstacles, and accelerate the recharge efficiency; when the robot moves to the near-pile docking area, the laser can be used.
  • the collecting device performs straight line extraction of the identified structural data, and combines the set identification template structure data to perform charging pile identification. After the collected structural data of the identification and the identification template structure data meet the preset matching degree, the collection device can be implemented.
  • the charging pile is docked and charged by the robot; the physical connection is confirmed according to the voltage condition of the connection between the robot and the charging pile to ensure correct charging behavior; the invention can realize accurate identification of the charging pile, is efficient and reliable, and effectively overcomes the sensitivity of hardware characteristics in the prior art. a series of pile jitter, interference, and misidentification caused by environmental interference for.
  • FIG. 1 is a flow chart showing a method of charging a robot according to an embodiment of the present invention
  • FIG. 2 is a schematic view showing a charging post identification according to an embodiment of the present invention.
  • FIG. 3 is a block diagram showing a robot charging apparatus according to an embodiment of the present invention.
  • Figure 4 shows a schematic diagram of an embodiment of the invention.
  • the terminal, the device of the service network, and the trusted party each include one or more processors (CPUs), input/output interfaces, network interfaces, and memory.
  • processors CPUs
  • input/output interfaces network interfaces
  • memory volatile and non-volatile memory
  • the memory may include non-persistent memory, random access memory (RAM), and/or non-volatile memory in a computer readable medium, such as read only memory (ROM) or flash memory.
  • RAM random access memory
  • ROM read only memory
  • Memory is an example of a computer readable medium.
  • Computer readable media including both permanent and non-persistent, removable and non-removable media, can be stored by any method or technology.
  • the information can be computer readable instructions, data structures, modules of programs, or other data.
  • Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read only memory. (ROM), electrically erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disk read only memory (CD-ROM), digital versatile disk (DVD) or other optical storage,
  • computer readable media does not include non-transitory computer readable media, such as modulated data signals and carrier waves.
  • the present invention provides a robot charging method, the method comprising:
  • Step S1 collecting current surrounding environment data of the robot in motion, and generating an environment map of the environment in which the robot is located and a pose of the robot in the environment map according to the surrounding environment data, where the environment map includes The potential or registered charging pile position has been recorded; here, this step is repeated continuously throughout the entire process of moving the machine from the beginning to the docking with the charging pile, the environment map and the robot are in the The pose in the environment map is constantly changing as the robot moves, the recorded potential charging post position may be the location of the actual charging post, or may not be the location of the real charging post, the registered The charging pile position is the position of the real charging pile;
  • Step S2 moving the robot to a short-range plucking docking area near a potential or registered charging pile position according to the environment map and the pose in the environment map;
  • Step S3 collecting structural data of the identifier on the potential or registered charging post. If the matching degree between the structural data of the collected identifier and the pre-stored identification template structure data is greater than a preset matching degree threshold, according to the collected The structural data of the identification determines the position of the charging pile;
  • Step S4 adjusting the posture of the robot in the environment map according to the posture of the charging pile, and docking the charging pile with the robot for charging.
  • the present invention is divided into three processes: remote regression, proximity charging pile identification, and docking charging.
  • the remote regression mainly moves the robot to the vicinity of the potential or registered charging pile position according to the environment map and the robot self-positioning information, that is, the posture of the robot in the environment map, avoiding blindly following the wall and randomly walking to find the charging. Piles, to avoid the complex indoor environment return time is long, and do not need to have a certain ability to distinguish between wall and island obstacles, speed up the efficiency of recharge.
  • the short-distance charging pile identification and the docking charging are mainly after the robot moves to the short-range plucking docking area, and the laser and other collecting devices can be used to perform straight line extraction of the identified structural data, and combined with the set identification template structure data to perform charging.
  • Pile identification when the structure data of the collected identification and the identification template structure data meet the preset matching degree, the charging pile and the robot can be connected and charged.
  • the method further includes:
  • the structure data of the identifier on the charging pile is collected. If the matching degree between the structure data of the collected identifier and the pre-stored identifier template structure data is greater than a preset matching degree threshold, determining the charging pile according to the structural data of the collected identifier Pose
  • the voltage of the mobile machine after the charging pile is docked with the robot is collected.
  • the physical connection is confirmed according to the voltage situation after the robot is connected to the charging post. If the robot and the charging pile are not properly connected, the robot is reconnected with the charging post to ensure correct charging behavior.
  • the identifier comprises a reflective material of at least one raised structure and a reflective material of at least one recessed structure, wherein a depth value between the raised structure and the recessed structure Greater than the preset depth threshold.
  • the convex structure and the concave structure are combined to generate a mark, and the depth value between the convex structure and the concave structure is greater than a preset depth threshold, which can effectively distinguish the mark from other objects in the environment, and avoid mistakes.
  • Identification For example, the logo as shown in FIG. 2 includes three raised structures a, b, a and two recessed structures c, c, a, c, b, c, a which are sequentially connected to form an identification.
  • step S1 before collecting the current surrounding environment data of the robot, the method further includes:
  • the path is The object is recorded as a potential charging post location.
  • the execution task refers to a local work task performed by the robot, for example, the sweeping robot performs a sweeping task, the tour guide robot performs a tour guide task, and the like.
  • the potential charging pile position can be continuously supplemented and updated by collecting structural data of the passing object during the movement of the robot to perform the task.
  • step S3 the structural data of the identifier on the potential or registered charging pile is collected, and if the matching structure data of the collected identifier and the pre-stored identification template structure data are greater than the pre-preparation
  • the matching threshold is determined, and the posture of the charging pile is determined according to the structural data of the collected identifier, including:
  • the robot moves the short-term plucking area to the preset data, and collects one potential after each movement or Structural data of the identification on the registered charging post;
  • the robot performs each in the short-range plucking area.
  • the matching degree of the one potential or registered charging pile is greater than the preset matching degree threshold is greater than the preset number of times, the potential or registered charging pile is used as the charging pile to be docked, thereby Ensure reliable confirmation of the charging pile and accurate determination of the charging pile position.
  • the number of times that the calculated structural data of the identifier on the current potential or registered charging stub and the pre-stored identification template structure data is greater than the preset matching degree threshold is 6 times, and the preset number of times is 5 times. If the number of times is greater than 5 times, the potential or registered charging pile is used as the charging pile to be docked. Otherwise, other charging piles to be docked can be found again.
  • step S3 the structural data of the identifier on the potential or registered charging pile is collected, and if the matching structure data of the collected identifier and the pre-stored identification template structure data are greater than the pre-preparation
  • the matching threshold is determined, and the posture of the charging pile is determined according to the structural data of the collected identifier, including:
  • the robot will move the preset data in the short-range pile-picking area, and collect each potential after each movement. Or structural data of the identification on the registered charging post;
  • the pile determines the posture of the charging pile according to the structural data of the collected identification of the charging pile to be docked.
  • the robot is in the short-range plucking area according to the preset locating movement strategy.
  • the potential or the registered charging pile with the matching degree greater than the preset matching degree threshold is selected as the charging pile to be docked, thereby ensuring reliable confirmation and charging of the charging pile.
  • Accurate determination of pile pose For example, the number of identifiers on the current potential or registered charging post is three, and the matching of the structural data of the identifier on the first potential or registered charging post with the pre-stored identification template structure data is greater than the preset.
  • the number of times of the matching degree threshold is 6 times, and the number of times the matching degree of the structure data of the identifier on the second potential or registered charging pile and the pre-stored identification template structure data is greater than the preset matching degree threshold is 7 times, and the calculation is performed.
  • the number of times that the matching structure data of the identifier on the third potential or registered charging post and the pre-stored identification template structure data is greater than the preset matching degree threshold is 8 times, the preset number of times is 5 times, 6 times , 7 times and 8 times are greater than the preset number of times. If the matching degree of the third potential or registered charging pile is greater than the preset matching degree threshold, the third potential or registered charging pile is taken as Charging pile to be docked.
  • step S1 the current surrounding environment data of the robot during the movement is collected, including:
  • the current ambient data of the robot on the move is acquired by one or any combination of infrared, camera, ultrasound, and laser acquisition devices.
  • step S3 the structural data of the identifier on the potential or registered charging pile is collected, including:
  • the structural data of the identification on the potential or registered charging post is acquired by one or any combination of infrared, depth camera, ultrasound, and laser acquisition devices.
  • step S1 current environmental data of the robot in motion is collected, an environmental map of the environment in which the robot is located is generated according to the surrounding environment data, and the robot is in the environment.
  • the pose in the map including:
  • An environment map of the environment in which the robot is located and a pose of the robot in the environment map are generated according to the current surrounding environment data and the moving distance and direction of the robot.
  • the current surrounding environment data of the robot combined with the collection of the moving distance and the direction, can more accurately generate an environment map of the environment in which the robot is located and a pose of the robot in the environment map.
  • step S4 the posture of the robot in the environment map is adjusted according to the posture of the charging pile, and the charging pile is docked with the robot for charging, including:
  • the posture of the robot in the environment map can be more accurately adjusted to accurately accurately charge the charging pile. Dock with the robot to charge.
  • step S2 the robot is moved to a near-end pile docking near a potential or registered charging pile position according to the environmental map and the pose in the environment map.
  • the region including:
  • the robot continues to move into a short-range plunging docking area near a potential or registered charging pile location.
  • the local trajectory of the global path can be continuously adjusted to generate smooth collision-free control. Decision-making, to ensure that the robot in the regression process, due to changes in the environment, such as the addition of new obstacles in the global path, to achieve obstacle avoidance capabilities, complete the regression.
  • a robot charging apparatus comprising:
  • the acquisition positioning module 1 is configured to collect current surrounding environment data of the robot during the movement, and generate an environment map of the environment in which the robot is located according to the surrounding environment data and a posture of the robot in the environment map.
  • the environmental map includes recorded potential or registered charging post locations;
  • a remote regression module 2 configured to move the robot to a short-range plucking docking area near a potential or registered charging pile position according to the environment map and the pose in the environment map;
  • the self-seeking pile module 3 is configured to collect structural data of the identifier on the potential or registered charging pile. If the matching degree of the collected structure data and the pre-stored identification template structure data is greater than a preset matching degree threshold, Determining a posture of the charging pile according to the structural data of the collected identifier;
  • the docking module 4 is configured to adjust a posture of the robot in the environment map according to the posture of the charging pile, and connect the charging pile to the robot for charging.
  • the docking module is further configured to collect a voltage of the mobile machine after the charging pile is docked with the robot, and if the collected voltage does not exceed a preset voltage threshold, the After the short-range locating area is moved, the independent homing module and the docking module are repeatedly executed until the voltage collected by the docking module exceeds a preset voltage threshold.
  • the identifier comprises a reflective material of at least one raised structure and a reflective material of at least one recessed structure, wherein a depth value between the raised structure and the recessed structure Greater than the preset depth threshold.
  • the acquisition and positioning module 1 is further configured to collect the transit object during the movement of the robot to perform the task before the current surrounding environment data of the robot is being collected.
  • the structural data is recorded as a potential charging pile position if the matching degree of the collected structural data of the collected object and the pre-stored identification template structure data is greater than a preset matching degree threshold.
  • the autonomous homing module 3 is configured to: if the number of the identifiers on the potential or registered charging piles in the current short-range plucking area is one, the robot is in the short range The pile-picked area is moved by preset data, and the structural data of the identifier on the potential or registered charging pile after each movement is collected; and the identifier on the one potential or registered charging pile is collected for each collection.
  • the matching degree of the structure data and the pre-stored identifier template structure data is greater than a preset matching degree threshold, and determining that the calculated matching degree of the one potential or registered charging pile is greater than the preset matching degree threshold is greater than a preset number of times And if yes, determining the pose of the charging post based on the structural data of the collected identification.
  • the autonomous locating module 3 is configured to: if the number of the identifiers on the potential or registered charging piles in the current short-range plucking area is multiple, the robot is near The path of the docking area is preset to move the data, and the structural data of the identification on each potential or registered charging post after each movement is collected; each potential or registered charging pile is collected for each acquisition.
  • the matching degree of the identified structural data and the pre-stored identification template structure data is greater than a preset matching degree threshold, and calculating whether the matching degree of each potential or registered charging post is greater than a preset matching degree threshold is greater than a preset number of times And selecting, as the charging pile to be docked, the potential or the registered charging pile with the matching degree greater than the preset matching degree threshold and the preset number of times, according to the structure of the collected identification of the charging pile to be docked
  • the data determines the pose of the charging post.
  • the acquisition positioning module 1 is configured to collect current ambient data of the robot during movement by one or any combination of infrared, camera, ultrasound, and laser acquisition devices.
  • the autonomous homing module 3 is configured to collect an identifier on a potential or registered charging pile by one or any combination of an infrared, a depth camera, an ultrasonic, and a laser collecting device. Structural data.
  • the docking module is configured to collect a moving distance and a direction of the robot; and adjust the moving distance and direction of the robot according to the posture of the charging pile and adjust the robot.
  • the pose in the environment map connects the charging post to the robot for charging.
  • the remote regression module 2 is configured to determine the robot movement according to a current environment map, a current pose in the environment map, and a potential or registered charging pile position. a global path; controlling, according to the global path, the robot to move to a short-range ploughing docking area near a potential or registered charging pile position; collecting a current moving speed of the robot according to the current environment map, the environmental map. The current pose and the current moving speed of the robot adjust the local trajectory of the global path and the running speed in the local trajectory to obtain an adjusted smooth, collision-free global path; according to the adjusted global path, The robot continues to move into the near-pile docking area near the potential or registered charging pile location.
  • the present invention mainly comprises four parts: an SLAM autonomous positioning part, a data acquisition part, a remote recharge, a short-range independent homing (charging pile identification), and a docking charging.
  • the SLAM autonomous positioning part mainly used to construct an environmental map, and obtain the current pose of the robot in real time according to the map and observation information. It is mainly composed of autonomous positioning module and map module:
  • Map module The environment map is constructed mainly by using SLAM related algorithms.
  • the map can be used for global path planning and autonomous positioning module, and is a core module in the intelligent mobile algorithm, wherein SLAM (simultaneous localization and mapping), also known as CML (Concurrent Mapping and Localization), instant positioning and map construction, or concurrent Construction and positioning;
  • SLAM simultaneous localization and mapping
  • CML Concurrent Mapping and Localization
  • Autonomous positioning module Based on the current sensor information, the storage module is constructed in combination with the environment map, and the current pose information is obtained by using the relevant matching algorithm, so that the robot knows its posture in the environment in real time.
  • the data acquisition part mainly used for the current ambient data of the robot in the movement, the odometer data (the current moving distance of the robot, the direction), to provide data support for the operation of other modules. It is mainly composed of sensor data acquisition and filtering module and odometer acquisition module:
  • Sensor data acquisition and filtering module collecting intelligent device configuration sensor data, using relevant filtering algorithm to remove excess noise of excess measurement data in the current surrounding environment data in motion;
  • Odometer module Obtain the intelligent device mileage data (the current moving distance and direction of the robot), provide a priori knowledge for the self-positioning module, and judge the docking, the pile-to-point and the rotation angle of the robot and the charging pile. .
  • remote recharge The main purpose is to move the robot to the vicinity of the potential or registered charging pile position according to the environmental map and the posture information of the robot, avoid blindly following the wall, randomly walk to find the charging pile, and solve the complex indoor environment regression. Long time problem, speed up the efficiency of recharge. It is mainly realized by the components of the recharge navigation task setting, the global path planning module, the partial path planning module, the motion control module and the intelligent mobile module. The functions are as follows:
  • Recharge navigation task setting set remote regression task according to the potential or registered charging post position and the current pose of the robot;
  • Global path planning module according to the recharge navigation task setting delivery task and autonomous positioning module information, combined with the heuristic search algorithm, using the environment map, the search starting point (the current pose of the robot) to the end point (potential charging pile position) globally Collision optimal path, guiding the smart device to complete the set regression task;
  • a local planning module In the regression process, due to changes in the environment, a local planning module is required to make the system have certain obstacle avoidance capabilities, and the regression task is completed.
  • the module utilizes multi-sensor fusion data and the current global path. And self-positioning information, combined with the current speed information of the robot, using dynamic window algorithm to generate smooth collision-free control decisions;
  • Motion control module using the global path planning module and the local trajectory planning module to generate collision-free control decisions, combined with the smart device motion model to generate motion control decisions;
  • Intelligent mobile module Receive motion control decision of motion control module, control device without collision movement.
  • Proximity self-seeking pile (charging pile identification) and docking charging After the robot moves to the short-range pile-picking area, it collects the structural data of the identification on the potential or registered charging pile, and combines the set charging.
  • the identification template structure of the pile is used to identify the charging pile.
  • the candidate charging pile can be identified, and the pile-seeking movement strategy is designed, and the highest probability is selected according to the multi-frame statistical data.
  • the potential charging pile is used as the final charging pile position, and the posture of the robot relative to the charging pile is adjusted, and the docking charging is performed.
  • Mainly consists of independent pile-seeking strategy, identification structure based near-charging pile identification module, posture adjustment and docking charging pile module, charging pile physical connection confirmation module:
  • Independent pile-seeking module design independent pile-seeking strategy. In the short-range plucking area, set the robot's motion strategy (moving, rotating or other means) to speed up the pile-seeking probability;
  • Identification module short-range charging pile identification module According to the charging pile identification structure, when the structural data of the identification on the potential or registered charging pile and the identification template structure satisfy a certain matching degree, the candidate charging can be identified as candidate charging. Pile, and determine the current observation candidate charging pile set and its position information, combined with multi-frame detection information, and according to the charge pile posture information of the candidate set, do statistics, each time a certain candidate charging pile is observed, the probability is corresponding Increasing, when the probability of observing a candidate charging pile is greater than the set probability, the target charging pile is found, and the relative position of the target charging pile is obtained;
  • Charging pile physical connection confirmation module monitor the connection voltage of the robot to determine whether the electrical connection is successful, so as to determine the physical connection between the robot and the charging pile.
  • a computing based device comprising:
  • a memory arranged to store computer executable instructions that, when executed, cause the processor to:
  • Collecting current surrounding environment data of the robot in motion generating an environment map of the environment in which the robot is located and a pose of the robot in the environment map according to the surrounding environment data, the environment map including the recorded Potential or registered charging station location;
  • the structure according to the collected identifier is The data determines the pose of the charging pile
  • the present invention moves the robot to the vicinity of the potential or registered charging pile position according to the environment map and the robot self-positioning information, that is, the posture of the robot in the environment map, thereby avoiding blind wall and random.
  • performing straight line extraction of the identified structural data, and combining the set identification template structure data to perform charging pile identification, and when the collected structural data of the identification and the identification template structure data satisfy the preset matching degree, the charging pile can be implemented.
  • the battery is docked and charged; the physical connection is confirmed according to the voltage situation of the robot and the charging pile to ensure correct charging behavior; the invention can realize accurate identification of the charging pile, is efficient and reliable, and effectively overcomes the hardware characteristic sensitivity and environment in the prior art. Interference caused by a series of pile jitter, interference, misidentification behavior.
  • the present invention can be implemented in software and/or a combination of software and hardware, for example, using an application specific integrated circuit (ASIC), a general purpose computer, or any other similar hardware device.
  • the software program of the present invention may be executed by a processor to implement the steps or functions described above.
  • the software program (including related data structures) of the present invention can be stored in a computer readable recording medium such as a RAM memory, a magnetic or optical drive or a floppy disk and the like.
  • some of the steps or functions of the present invention may be implemented in hardware, for example, as a circuit that cooperates with a processor to perform various steps or functions.
  • a portion of the invention can be applied as a computer program product, such as computer program instructions, which, when executed by a computer, can invoke or provide a method and/or solution in accordance with the present invention.
  • the program instructions for invoking the method of the present invention may be stored in a fixed or removable recording medium and/or transmitted by a data stream in a broadcast or other signal bearing medium, and/or stored in a The working memory of the computer device in which the program instructions are run.
  • an embodiment in accordance with the present invention includes a device including a memory for storing computer program instructions and a processor for executing program instructions, wherein when the computer program instructions are executed by the processor, triggering
  • the apparatus operates based on the aforementioned methods and/or technical solutions in accordance with various embodiments of the present invention.

Landscapes

  • Engineering & Computer Science (AREA)
  • Physics & Mathematics (AREA)
  • Radar, Positioning & Navigation (AREA)
  • Remote Sensing (AREA)
  • Automation & Control Theory (AREA)
  • General Physics & Mathematics (AREA)
  • Aviation & Aerospace Engineering (AREA)
  • Mechanical Engineering (AREA)
  • Robotics (AREA)
  • Power Engineering (AREA)
  • Multimedia (AREA)
  • Electromagnetism (AREA)
  • Optics & Photonics (AREA)
  • Computer Vision & Pattern Recognition (AREA)
  • Transportation (AREA)
  • Manipulator (AREA)
  • Control Of Position, Course, Altitude, Or Attitude Of Moving Bodies (AREA)

Abstract

一种机器人充电方法及装置,根据环境地图及机器人自定位信息即所述机器人在所述环境地图中的位姿,将机器人移动至潜在或者已注册的充电桩位置附近;当机器人移动到近程寻桩对接区域后,利用激光等采集装置,进行标识的结构数据的直线提取,并结合设定的标识模板结构数据,做充电桩识别,当采集的标识的结构数据与标识模板结构数据满足预设的匹配程度后,即可实施充电桩与机器人对接充电;根据机器人与充电桩连接后的电压情况做物理连接确认,确保充电正确行为;可实现充电桩的精确识别,高效可靠,克服现有技术中硬件特性敏感、环境干扰带来的一系列对桩抖动、干扰、误识别行为。

Description

机器人充电方法及装置 技术领域
本发明涉及一种机器人充电方法及装置。
背景技术
随着智能机器人发展,各种服务类机器人纷纷涌现,譬如扫地机、导游、导购类机器人、咨询机器人等,人们对机器人长期值守、增加活动范围、延长自治时间等功能要求越来越高,因此补充动力能源成为一个亟待解决的问题。常见机器人动力能源为无缆化主要依赖高品质的机载蓄电池组,因此,自主回充技术应运而生,即在机器人电量不足且无无人工干预前提下,通过某种方式,引导机器人远程回归至充电对接区域,自动实现对接,进行充电技术。
但是,现有方案中,机器人远程回归充电桩的时间长且盲目效率低,甚至存在电池能力耗尽前,机器人无法寻找到充电桩导致电池过度放电,造成损坏电池或者停机等问题。另外,现有的充电桩识别方法中还存在硬件特性敏感、易受环境干扰,识别不准确等问题。
发明内容
本发明的一个目的是提供一种机器人充电方法及装置,能够解决机器人远程回归充电桩的时间长且盲目效率低的问题。
根据本发明的一个方面,提供了一种机器人充电方法,该方法包括:
采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜 在或者已注册的充电桩位置附近的近程寻桩对接区域内;
采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
进一步的,上述方法中,将所述充电桩与机器人对接进行充电之后,还包括:
采集所述采集潜在或者已注册的充电桩与机器人对接后移动机器的电压,若所述采集的电压未超过预设电压阈值,则将所述近程寻桩对接区域移动位置后,重复如下步骤,直至所述采集的电压超过预设电压阈值:
采集充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电;
采集所述充电桩与机器人对接后移动机器的电压。
进一步的,上述方法中,所述标识包括相连接的至少一个凸起结构的反光材质和至少一个凹陷结构的反光材质,其中,所述凸起结构和凹陷结构之间的深度值大于预设的深度阈值。
进一步的,上述方法中,采集机器人在移动中的当前的周围环境数据之前,还包括:
在所述机器人执行任务的移动过程中,采集途经物体的结构数据,若所述采集的途经物体的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则将所述途经物体记录为潜在的充电桩位置。
进一步的,上述方法中,采集潜在或者已注册的充电桩上的标识的结 构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿,包括:
若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后该一个潜在或者已注册的充电桩上的标识的结构数据;
计算每一次采集的该一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,判断该一个潜在或者已注册的充电桩的所述计算的匹配度大于预设匹配度阈值的次数大于预设次数,若是,则根据所述采集的标识的结构数据确定充电桩的位姿。
进一步的,上述方法中,采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿,包括:
若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为多个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后每一个潜在或者已注册的充电桩上的标识的结构数据;
计算每一次采集的每一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,计算每一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数是否大于预设次数,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,根据所述待对接的充电桩的采集的标识的结构数据确定充电桩的位姿。
进一步的,上述方法中,采集机器人在移动中的当前的周围环境数据,包括:
通过红外、摄像头、超声和激光采集装置中的一种或任意组合,采集机器人在移动中的当前的周围环境数据。
进一步的,上述方法中,采集潜在或者已注册的充电桩上的标识的结构数据,包括:
通过红外、深度摄像头、超声和激光采集装置中的一种或任意组合采集潜在或者已注册的充电桩上的标识的结构数据。
进一步的,上述方法中,根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电,包括:
采集机器人的移动距离、方向;
根据所述充电桩的位姿调整和采集的机器人的移动距离、方向,调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
进一步的,上述方法中,根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内,包括:
根据当前的环境地图、所述环境地图中的当前位姿和潜在或者已注册的充电桩位置,确定所述机器人移动的全局路径;
根据所述全局路径控制所述机器人向潜在或者已注册的充电桩位置附近的近程寻桩对接区域移动;
采集机器人的当前移动速度,根据当前的环境地图、所述环境地图中的当前位姿和机器人的当前移动速度对所述全局路径的局部轨迹和局部轨迹中的运行速度进行调整,得到调整后的平滑的无碰撞的全局路径;
根据所述调整后的全局路径,将所述机器人继续移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内。
根据本发明的另一方面,还提供了一种机器人充电装置,该装置包括:
采集定位模块,用于采集机器人在移动中的当前的周围环境数据,根 据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
远程回归模块,用于根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
自主寻桩模块,用于采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
对接模块,用于根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
进一步的,上述装置中,所述对接模块,还用于采集所述充电桩与机器人对接后移动机器的电压,若所述采集的电压未超过预设电压阈值,则将所述近程寻桩对接区域移动位置后,重复执行自主寻桩模块和对接模块,直至所述对接模块采集的电压超过预设电压阈值。
进一步的,上述装置中,所述标识包括相连接的至少一个凸起结构的反光材质和至少一个凹陷结构的反光材质,其中,所述凸起结构和凹陷结构之间的深度值大于预设的深度阈值。
进一步的,上述装置中,所述采集定位模块,还用于在采集机器人在移动中的当前的周围环境数据之前,在所述机器人执行任务的移动过程中,采集途经物体的结构数据,若所述采集的途经物体的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则将所述途经物体记录为潜在的充电桩位置。
进一步的,上述装置中,所述自主寻桩模块,用于若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,将机器人在近 程寻桩对接区域作预设次数据的移动,采集每一次移动后该一个潜在或者已注册的充电桩上的标识的结构数据;计算每一次采集的该一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,判断该一个潜在或者已注册的充电桩的所述计算的匹配度大于预设匹配度阈值的次数大于预设次数,若是,则根据所述采集的标识的结构数据确定充电桩的位姿。
进一步的,上述装置中,所述自主寻桩模块,用于若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为多个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后每一个潜在或者已注册的充电桩上的标识的结构数据;计算每一次采集的每一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,计算每一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数是否大于预设次数,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,根据所述待对接的充电桩的采集的标识的结构数据确定充电桩的位姿。
进一步的,上述装置中,所述采集定位模块,用于通过红外、摄像头、超声和激光采集装置中的一种或任意组合,采集机器人在移动中的当前的周围环境数据。
进一步的,上述装置中,所述自主寻桩模块,用于通过红外、深度摄像头、超声和激光采集装置中的一种或任意组合采集潜在或者已注册的充电桩上的标识的结构数据。
进一步的,上述装置中,所述对接模块,用于采集机器人的移动距离、方向;根据所述充电桩的位姿调整和采集的机器人的移动距离、方向,调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
进一步的,上述装置中,所述远程回归模块,用于根据当前的环境地图、所述环境地图中的当前位姿和潜在或者已注册的充电桩位置,确定所述机器人移动的全局路径;根据所述全局路径控制所述机器人向潜在或者已注册的充电桩位置附近的近程寻桩对接区域移动;采集机器人的当前移动速度,根据当前的环境地图、所述环境地图中的当前位姿和机器人的当前移动速度对所述全局路径的局部轨迹和局部轨迹中的运行速度进行调整,得到调整后的平滑的无碰撞的全局路径;根据所述调整后的全局路径,将所述机器人继续移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内。
根据本发明的另一面,还提供一种基于计算的设备,包括:
处理器;以及
被安排成存储计算机可执行指令的存储器,所述可执行指令在被执行时使所述处理器:
采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
与现有技术相比,本发明根据环境地图及机器人自定位信息即所述机器人在所述环境地图中的位姿,将机器人移动至潜在或者已注册的充电桩位置附近,避免盲目的循墙、随机行走寻找充电桩,避免复杂室内环境回 归时间长,且不需具备一定的分辨墙壁和孤岛障碍物能力,加快回充效率;当机器人移动到近程寻桩对接区域后,可以利用激光等采集装置,进行标识的结构数据的直线提取,并结合设定的标识模板结构数据,做充电桩识别,当采集的标识的结构数据与标识模板结构数据满足预设的匹配程度后,即可实施充电桩与机器人对接充电;根据机器人与充电桩连接后的电压情况做物理连接确认,确保充电正确行为;本发明可实现充电桩的精确识别,高效可靠,有效的克服现有技术中硬件特性敏感、环境干扰带来的一系列对桩抖动、干扰、误识别行为。
附图说明
通过阅读参照以下附图所作的对非限制性实施例所作的详细描述,本发明的其它特征、目的和优点将会变得更明显:
图1示出本发明一实施例的机器人充电方法的流程图;
图2示出本发明一实施例的充电桩标识的示意图;
图3示出本发明一实施例的机器人充电装置的模块图;
图4示出本发明一实施例的原理图。
附图中相同或相似的附图标记代表相同或相似的部件。
具体实施方式
下面结合附图对本发明作进一步详细描述。
在本申请一个典型的配置中,终端、服务网络的设备和可信方均包括一个或多个处理器(CPU)、输入/输出接口、网络接口和内存。
内存可能包括计算机可读介质中的非永久性存储器,随机存取存储器(RAM)和/或非易失性内存等形式,如只读存储器(ROM)或闪存(flash RAM)。内存是计算机可读介质的示例。
计算机可读介质包括永久性和非永久性、可移动和非可移动媒体可以 由任何方法或技术来实现信息存储。信息可以是计算机可读指令、数据结构、程序的模块或其他数据。计算机的存储介质的例子包括,但不限于相变内存(PRAM)、静态随机存取存储器(SRAM)、动态随机存取存储器(DRAM)、其他类型的随机存取存储器(RAM)、只读存储器(ROM)、电可擦除可编程只读存储器(EEPROM)、快闪记忆体或其他内存技术、只读光盘只读存储器(CD-ROM)、数字多功能光盘(DVD)或其他光学存储、磁盒式磁带,磁带磁盘存储或其他磁性存储设备或任何其他非传输介质,可用于存储可以被计算设备访问的信息。按照本文中的界定,计算机可读介质不包括非暂存电脑可读媒体(transitory media),如调制的数据信号和载波。
如图1所示,本发明提供一种机器人充电方法,所述方法包括:
步骤S1,采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;在此,本步骤在移动机器从开始移动到与充电桩对接成功停止移动的全程中,不断重复进行,所述环境地图和所述机器人在所述环境地图中的位姿随着机器人的移动,不断变化更新,所述已记录的潜在充电桩位置是可能是真正的充电桩的位置,也可能不是真正的充电桩的位置,所述已注册的充电桩位置是真正的充电桩的位置;
步骤S2,根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
步骤S3,采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
步骤S4,根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
具体的,本发明分为三个过程:远程回归、近程充电桩识别及对接充电。
远程回归主要是根据环境地图及机器人自定位信息即所述机器人在所述环境地图中的位姿,将机器人移动至潜在或者已注册的充电桩位置附近,避免盲目的循墙、随机行走寻找充电桩,避免复杂室内环境回归时间长,且不需具备一定的分辨墙壁和孤岛障碍物能力,加快回充效率。
近程充电桩识别及对接充电主要是当机器人移动到近程寻桩对接区域后,可以利用激光等采集装置,进行标识的结构数据的直线提取,并结合设定的标识模板结构数据,做充电桩识别,当采集的标识的结构数据与标识模板结构数据满足预设的匹配程度后,即可实施充电桩与机器人对接充电。
本发明的机器人充电方法一实施例中,步骤S4中的,将所述充电桩与机器人对接进行充电之后,还包括:
采集所述采集潜在或者已注册的充电桩与机器人对接后移动机器的电压,若所述采集的电压未超过预设电压阈值,则将所述近程寻桩对接区域移动位置后,重复如下步骤,直至所述采集的电压超过预设电压阈值:
采集充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电;
采集所述充电桩与机器人对接后移动机器的电压。
本实施例中,根据机器人与充电桩连接后的电压情况做物理连接确认,如果机器人与充电桩未正确连接,则重新将机器人与充电桩进行连接,确保充电正确行为。
本发明的机器人充电方法一实施例中,所述标识包括相连接的至少一 个凸起结构的反光材质和至少一个凹陷结构的反光材质,其中,所述凸起结构和凹陷结构之间的深度值大于预设的深度阈值。
在此,将凸起结构和凹陷结构组合生成标识,且所述凸起结构和凹陷结构之间的深度值大于预设的深度阈值,可有效将标识与环境中的其它物体相区别,避免误识别。例如,如图2所示的标识包括3个凸起结构a、b、a和2个凹陷结构c、c,a、c、b、c、a依次连接成标识。
本发明的机器人充电方法一实施例中,步骤S1,采集机器人在移动中的当前的周围环境数据之前,还包括:
在所述机器人执行任务的移动过程中,采集途经物体的结构数据,若所述采集的途经物体的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则将所述途经物体记录为潜在的充电桩位置。
在此,所述执行任务是指所述机器人执行的本职工作任务,例如,扫地机器人执行扫地任务,导游机器人执行导游任务等等。本实施例中,通过在所述机器人执行任务的移动过程中,采集途经物体的结构数据,可以不断地补充和更新潜在的充电桩位置。
本发明的机器人充电方法一实施例中,步骤S3,采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿,包括:
若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后该一个潜在或者已注册的充电桩上的标识的结构数据;
计算每一次采集的该一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,判断该一个潜在或者已注册的充电桩的所述计算的匹配度大于预设匹配度阈值的次数大于预设次数,若是,则根据所述采集的标识的结构数据确定充 电桩的位姿。
本实施例中,若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,按照预定的寻桩移动策略,所述机器人在近程寻桩对接区域内进行各次移动后,该一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数大于预设次数,则将该一个潜在或者已注册的充电桩作为待对接的充电桩,从而保证充电桩的可靠确认和充电桩位姿的精确确定。例如,计算的当前一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值的次数为6次,所述预设次数为5次,6次大于5次,则将该一个潜在或者已注册的充电桩作为待对接的充电桩,否则可以重新查找其它待对接的充电桩。
本发明的机器人充电方法一实施例中,步骤S3,采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿,包括:
若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为多个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后每一个潜在或者已注册的充电桩上的标识的结构数据;
计算每一次采集的每一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,计算每一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数是否大于预设次数,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,根据所述待对接的充电桩的采集的标识的结构数据确定充电桩的位姿。
本实施例中,若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为多个,按照预设的寻桩移动策略,所述机器人在近程寻桩 对接区域内进行各次移动后,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,从而保证充电桩的可靠确认和充电桩位姿的精确确定。例如,当前一个潜在或者已注册的充电桩上的标识数为3个,计算的第1个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值的次数为6次,计算的第2个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值的次数为7次,计算的第3个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值的次数为8次,所述预设次数为5次,6次、7次和8次都大于预设次数,第3个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数最多,则将第3个潜在或者已注册的充电桩作为待对接的充电桩。
本发明的机器人充电方法一实施例中,步骤S1,采集机器人在移动中的当前的周围环境数据,包括:
通过红外、摄像头、超声和激光采集装置中的一种或任意组合,采集机器人在移动中的当前的周围环境数据。
本发明的机器人充电方法一实施例中,步骤S3,采集潜在或者已注册的充电桩上的标识的结构数据,包括:
通过红外、深度摄像头、超声和激光采集装置中的一种或任意组合采集潜在或者已注册的充电桩上的标识的结构数据。
本发明的机器人充电方法一实施例中,步骤S1,采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,包括:
采集机器人在移动中的当前的周围环境数据,采集机器人的当前移动距离、方向;
根据所述机器人的当前周围环境数据和移动距离、方向,生成所述机 器人所处环境的环境地图和所述机器人在所述环境地图中的位姿。
本实施例中,通过所述机器人的当前周围环境数据结合移动距离、方向的采集,可以更精确地生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿。
本发明的机器人充电方法一实施例中,步骤S4,根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电,包括:
采集机器人的移动距离、方向;
根据所述充电桩的位姿调整和采集的机器人的移动距离、方向,调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
本实施例中,通过所述充电桩的位姿调整结合采集的机器人的移动距离、方向,可以更精确地调整所述机器人在所述环境地图中的位姿,以准确地将所述充电桩与机器人对接进行充电。
本发明的机器人充电方法一实施例中,步骤S2,根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内,包括:
根据当前的环境地图、所述环境地图中的当前位姿和潜在或者已注册的充电桩位置,确定所述机器人移动的全局路径;
根据所述全局路径控制所述机器人向潜在或者已注册的充电桩位置附近的近程寻桩对接区域移动;
采集机器人的当前移动速度,根据当前的环境地图、所述环境地图中的当前位姿和机器人的当前移动速度对所述全局路径的局部轨迹和局部轨迹中的运行速度进行调整,得到调整后的平滑的无碰撞的全局路径;
根据所述调整后的全局路径,将所述机器人继续移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内。
在此,根据不断更新的当前的环境地图、所述环境地图中的当前位姿,结合机器人的当前速度信息,可以对所述全局路径的的局部轨迹进行不断的调整,产生平滑的无碰撞控制决策,保证机器人在回归过程中,由于环境发生变化,例如在全局路径增加了新的障碍物,实现避障能力,完成回归。
如图3所示,根据本发明的另一面,还提供一种机器人充电装置,所述装置包括:
采集定位模块1,用于采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
远程回归模块2,用于根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
自主寻桩模块3,用于采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
对接模块4,用于根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
本发明的机器人充电装置一实施例中,所述对接模块,还用于采集所述充电桩与机器人对接后移动机器的电压,若所述采集的电压未超过预设电压阈值,则将所述近程寻桩对接区域移动位置后,重复执行自主寻桩模块和对接模块,直至所述对接模块采集的电压超过预设电压阈值。
本发明的机器人充电装置一实施例中,所述标识包括相连接的至少一个凸起结构的反光材质和至少一个凹陷结构的反光材质,其中,所述凸起 结构和凹陷结构之间的深度值大于预设的深度阈值。
本发明的机器人充电装置一实施例中,所述采集定位模块1,还用于在采集机器人在移动中的当前的周围环境数据之前,在所述机器人执行任务的移动过程中,采集途经物体的结构数据,若所述采集的途经物体的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则将所述途经物体记录为潜在的充电桩位置。
本发明的机器人充电装置一实施例中,所述自主寻桩模块3,用于若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后该一个潜在或者已注册的充电桩上的标识的结构数据;计算每一次采集的该一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,判断该一个潜在或者已注册的充电桩的所述计算的匹配度大于预设匹配度阈值的次数大于预设次数,若是,则根据所述采集的标识的结构数据确定充电桩的位姿。
本发明的机器人充电装置一实施例中,所述自主寻桩模块3,用于若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为多个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后每一个潜在或者已注册的充电桩上的标识的结构数据;计算每一次采集的每一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,计算每一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数是否大于预设次数,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,根据所述待对接的充电桩的采集的标识的结构数据确定充电桩的位姿。
本发明的机器人充电装置一实施例中,所述采集定位模块1,用于通过红外、摄像头、超声和激光采集装置中的一种或任意组合,采集机器人 在移动中的当前的周围环境数据。
本发明的机器人充电装置一实施例中,所述自主寻桩模块3,用于通过红外、深度摄像头、超声和激光采集装置中的一种或任意组合采集潜在或者已注册的充电桩上的标识的结构数据。
本发明的机器人充电装置一实施例中,所述对接模块,用于采集机器人的移动距离、方向;根据所述充电桩的位姿调整和采集的机器人的移动距离、方向,调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
本发明的机器人充电装置一实施例中,所述远程回归模块2,用于根据当前的环境地图、所述环境地图中的当前位姿和潜在或者已注册的充电桩位置,确定所述机器人移动的全局路径;根据所述全局路径控制所述机器人向潜在或者已注册的充电桩位置附近的近程寻桩对接区域移动;采集机器人的当前移动速度,根据当前的环境地图、所述环境地图中的当前位姿和机器人的当前移动速度对所述全局路径的局部轨迹和局部轨迹中的运行速度进行调整,得到调整后的平滑的无碰撞的全局路径;根据所述调整后的全局路径,将所述机器人继续移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内。
如图4所示,本发明的一具体应用实施例中,本发明主要包括四部分:SLAM自主定位部分、数据采集部分、远程回充、近程自主寻桩(充电桩识别)及对接充电。
一、SLAM自主定位部分:主要用于构建环境地图,并根据地图和观测信息实时获得机器人的当前位姿。主要由自主定位模块、地图模块组成:
1)地图模块:主要利用SLAM相关算法,构建环境地图。该地图可用于全局路径规划以及自主定位模块,是智能移动算法中的核心模块,其中,SLAM(simultaneous localization and mapping),也称为CML(Concurrent Mapping and Localization),即时定位与地图构建,或并发建图与定位;
2)自主定位模块:基于当前传感器信息,结合环境地图构建存储模块,利用相关匹配算法,获得当前位姿信息,使得机器人实时知道自己在环境中的位姿。
二、数据采集部分:主要用于机器人在移动中的当前的周围环境数据、里程计数据(机器人的当前移动距离、方向)获取,为其他模块运行提供数据支撑。主要由传感器数据采集滤波模块、里程计采集模块组成:
1)传感器数据采集滤波模块:采集智能设备配置传感器数据,采用相关滤波算法,出去在移动中的当前的周围环境数据中多余测量数据多余噪点;
2)里程计模块:获取智能设备里程数据(机器人的当前移动距离、方向),为自定位模块提供先验知识,及用于机器人与充电桩的对接时、下桩到点及旋转角度的判断。
三、远程回充:主要目的是根据环境地图及机器人的位姿信息,将机器人移动至潜在或者已注册的充电桩位置附近,避免盲目的循墙、随机行走寻找充电桩,解决复杂室内环境回归时间长问题,加快回充效率。其主要由回充导航任务设置、全局路径规划模块、局部路径规划模块、运动控制模块、智能移动模块各部分组成模块实现及作用如下:
1)回充导航任务设置:根据潜在或者已注册的充电桩位置及机器人的当前位姿,设置远程回归任务;
2)全局路径规划模块:根据回充导航任务设置下发任务和自主定位模块信息,结合启发式搜索算法,利用环境地图,搜索起点(机器人当前位姿)到终点(潜在充电桩位置)全局无碰撞最优路径,指引智能设备完成设定的回归任务;
3)局部轨迹规划模块:在回归过程中,由于环境发生变化,需有局部规划模块,使系统具备一定的避障能力,完成回归任务,该模块利用多传感器融合后数据,以及当前全局路径,和自定位信息,结合机器人的当 前速度信息,利用动态窗口算法产生平滑的无碰撞控制决策;
4)运动控制模块:利用全局路径规划模块和局部轨迹规划模块产生的无碰撞控制决策,结合智能设备运动模型,产生运动控制决策;
5)智能移动模块:接收运动控制模块的运动控制决策,控制设备无碰撞移动。
四、近程自主寻桩(充电桩识别)及对接充电:机器人移动到近程寻桩对接区域后,针对当前采集潜在或者已注册的充电桩上的标识的结构数据,并结合设定的充电桩的标识模板结构,做充电桩识别。当采集潜在或者已注册的充电桩上的标识的结构数据与标识模板结构满足一定的匹配程度后,即可标识为候选充电桩,并设计寻桩移动策略,根据多帧统计数据,选择最高概率的潜在充电桩作为最终充电桩位置,同时调整机器人相对充电桩的位姿,实施对接充电。主要由自主寻桩策略、基于标识结构近程充电桩识别模块、位姿调整及对接充电桩模块、充电桩物理连接确认模块组成:
1)自主寻桩模块:设计自主寻桩策略。在近程寻桩对接区域,设定机器人的运动策略(移动、旋转或者其他方式),加快寻桩概率;
2)基于标识结构近程充电桩识别模块:根据充电桩标识结构,当采集潜在或者已注册的充电桩上的标识的结构数据与标识模板结构满足一定的匹配程度后,即可标识为候选充电桩,并确定当前观测候选充电桩集及其位置信息,结合多帧检测信息,并根据候选集中的充电桩位姿信息,做统计,每多观测到某一候选充电桩,则其概率做相应增加,当某一候选充电桩观测到的概率大于设定概率,即找到目标充电桩,并获得目标充电桩相对位姿;
3)对接充电桩模块:根据机器人位姿,及目标充电桩相对位姿,调整机器人位姿,进行充电桩对接;
4)充电桩物理连接确认模块:监测机器人连接段电压,确定电器连 接是否成功,从而确定机器人与充电桩存在物理连接。
根据本发明的另一面,还提供一种基于计算的设备,包括:
处理器;以及
被安排成存储计算机可执行指令的存储器,所述可执行指令在被执行时使所述处理器:
采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
本发明的机器人充电装置和基于计算的设备的各实施例的具体内容可参见机器人充电方法各实施例的对应内容,在此不再赘述。
综上所述,本发明根据环境地图及机器人自定位信息即所述机器人在所述环境地图中的位姿,将机器人移动至潜在或者已注册的充电桩位置附近,避免盲目的循墙、随机行走寻找充电桩,避免复杂室内环境回归时间长,且不需具备一定的分辨墙壁和孤岛障碍物能力,加快回充效率;当机器人移动到近程寻桩对接区域后,可以利用激光等采集装置,进行标识的结构数据的直线提取,并结合设定的标识模板结构数据,做充电桩识别,当采集的标识的结构数据与标识模板结构数据满足预设的匹配程度后,即可实施充电桩与机器人对接充电;根据机器人与充电桩连接后的电压情况做物理连接确认,确保充电正确行为;本发明可实现充电桩的精确识别, 高效可靠,有效的克服现有技术中硬件特性敏感、环境干扰带来的一系列对桩抖动、干扰、误识别行为。
显然,本领域的技术人员可以对本申请进行各种改动和变型而不脱离本申请的精神和范围。这样,倘若本申请的这些修改和变型属于本申请权利要求及其等同技术的范围之内,则本申请也意图包含这些改动和变型在内。
需要注意的是,本发明可在软件和/或软件与硬件的组合体中被实施,例如,可采用专用集成电路(ASIC)、通用目的计算机或任何其他类似硬件设备来实现。在一个实施例中,本发明的软件程序可以通过处理器执行以实现上文所述步骤或功能。同样地,本发明的软件程序(包括相关的数据结构)可以被存储到计算机可读记录介质中,例如,RAM存储器,磁或光驱动器或软磁盘及类似设备。另外,本发明的一些步骤或功能可采用硬件来实现,例如,作为与处理器配合从而执行各个步骤或功能的电路。
另外,本发明的一部分可被应用为计算机程序产品,例如计算机程序指令,当其被计算机执行时,通过该计算机的操作,可以调用或提供根据本发明的方法和/或技术方案。而调用本发明的方法的程序指令,可能被存储在固定的或可移动的记录介质中,和/或通过广播或其他信号承载媒体中的数据流而被传输,和/或被存储在根据所述程序指令运行的计算机设备的工作存储器中。在此,根据本发明的一个实施例包括一个装置,该装置包括用于存储计算机程序指令的存储器和用于执行程序指令的处理器,其中,当该计算机程序指令被该处理器执行时,触发该装置运行基于前述根据本发明的多个实施例的方法和/或技术方案。
对于本领域技术人员而言,显然本发明不限于上述示范性实施例的细节,而且在不背离本发明的精神或基本特征的情况下,能够以其他的具体形式实现本发明。因此,无论从哪一点来看,均应将实施例看作是示范性的,而且是非限制性的,本发明的范围由所附权利要求而不是上述说明限 定,因此旨在将落在权利要求的等同要件的含义和范围内的所有变化涵括在本发明内。不应将权利要求中的任何附图标记视为限制所涉及的权利要求。此外,显然“包括”一词不排除其他单元或步骤,单数不排除复数。装置权利要求中陈述的多个单元或装置也可以由一个单元或装置通过软件或者硬件来实现。第一,第二等词语用来表示名称,而并不表示任何特定的顺序。

Claims (21)

  1. 一种机器人充电方法,其中,该方法包括:
    采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
    根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
    采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
    根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
  2. 根据权利要求1所述的方法,其中,将所述充电桩与机器人对接进行充电之后,还包括:
    采集所述采集潜在或者已注册的充电桩与机器人对接后移动机器的电压,若所述采集的电压未超过预设电压阈值,则将所述近程寻桩对接区域移动位置后,重复如下步骤,直至所述采集的电压超过预设电压阈值:
    采集充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
    根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电;
    采集所述充电桩与机器人对接后移动机器的电压。
  3. 根据权利要求1所述的方法,其中,所述标识包括相连接的至少 一个凸起结构的反光材质和至少一个凹陷结构的反光材质,其中,所述凸起结构和凹陷结构之间的深度值大于预设的深度阈值。
  4. 根据权利要求1所述的方法,其中,采集机器人在移动中的当前的周围环境数据之前,还包括:
    在所述机器人执行任务的移动过程中,采集途经物体的结构数据,若所述采集的途经物体的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则将所述途经物体记录为潜在的充电桩位置。
  5. 根据权利要求1至4任一项所述的方法,其中,采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿,包括:
    若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后该一个潜在或者已注册的充电桩上的标识的结构数据;
    计算每一次采集的该一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,判断该一个潜在或者已注册的充电桩的所述计算的匹配度大于预设匹配度阈值的次数大于预设次数,若是,则根据所述采集的标识的结构数据确定充电桩的位姿。
  6. 根据权利要求1至4任一项所述的方法,其中,采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿,包括:
    若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数 量为多个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后每一个潜在或者已注册的充电桩上的标识的结构数据;
    计算每一次采集的每一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,计算每一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数是否大于预设次数,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,根据所述待对接的充电桩的采集的标识的结构数据确定充电桩的位姿。
  7. 根据权利要求1至4任一项所述的方法,其中,采集机器人在移动中的当前的周围环境数据,包括:
    通过红外、摄像头、超声和激光采集装置中的一种或任意组合,采集机器人在移动中的当前的周围环境数据。
  8. 根据权利要求1至4任一项所述的方法,其中,采集潜在或者已注册的充电桩上的标识的结构数据,包括:
    通过红外、深度摄像头、超声和激光采集装置中的一种或任意组合采集潜在或者已注册的充电桩上的标识的结构数据。
  9. 根据权利要求1至4任一项所述的方法,其中,根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电,包括:
    采集机器人的移动距离、方向;
    根据所述充电桩的位姿调整和采集的机器人的移动距离、方向,调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
  10. 根据权利要求1至4任一项所述的方法,其中,根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内,包括:
    根据当前的环境地图、所述环境地图中的当前位姿和潜在或者已注册的充电桩位置,确定所述机器人移动的全局路径;
    根据所述全局路径控制所述机器人向潜在或者已注册的充电桩位置附近的近程寻桩对接区域移动;
    采集机器人的当前移动速度,根据当前的环境地图、所述环境地图中的当前位姿和机器人的当前移动速度对所述全局路径的局部轨迹和局部轨迹中的运行速度进行调整,得到调整后的平滑的无碰撞的全局路径;
    根据所述调整后的全局路径,将所述机器人继续移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内。
  11. 一种机器人充电装置,其中,该装置包括:
    采集定位模块,用于采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
    远程回归模块,用于根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
    自主寻桩模块,用于采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大 于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
    对接模块,用于根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
  12. 根据权利要求11所述的装置,其中,所述对接模块,还用于采集所述充电桩与机器人对接后移动机器的电压,若所述采集的电压未超过预设电压阈值,则将所述近程寻桩对接区域移动位置后,重复执行自主寻桩模块和对接模块,直至所述对接模块采集的电压超过预设电压阈值。
  13. 根据权利要求11所述的装置,其中,所述标识包括相连接的至少一个凸起结构的反光材质和至少一个凹陷结构的反光材质,其中,所述凸起结构和凹陷结构之间的深度值大于预设的深度阈值。
  14. 根据权利要求11所述的装置,其中,所述采集定位模块,还用于在采集机器人在移动中的当前的周围环境数据之前,在所述机器人执行任务的移动过程中,采集途经物体的结构数据,若所述采集的途经物体的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则将所述途经物体记录为潜在的充电桩位置。
  15. 根据权利要求11至14任一项所述的装置,其中,所述自主寻桩模块,用于若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为一个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后该一个潜在或者已注册的充电桩上的标识的结构数据;计算每一次采集的该一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,判断该一个潜在或者已注册的充电桩的所述计算的匹配度大于预设匹配度阈值的次数大于预设次数,若是,则根据所述采集的标识的结构数据确定充电桩的位姿。
  16. 根据权利要求11至14任一项所述的装置,其中,所述自主寻桩模块,用于若当前近程寻桩对接区域内潜在或者已注册的充电桩上的标识的数量为多个,将机器人在近程寻桩对接区域作预设次数据的移动,采集每一次移动后每一个潜在或者已注册的充电桩上的标识的结构数据;计算每一次采集的每一个潜在或者已注册的充电桩上的标识的结构数据与预存的标识模板结构数据的匹配度是否大于预设匹配度阈值,计算每一个潜在或者已注册的充电桩的所述匹配度大于预设匹配度阈值的次数是否大于预设次数,将所述匹配度大于预设匹配度阈值的次数最多且大于预设次数的潜在或者已注册的充电桩选择为待对接的充电桩,根据所述待对接的充电桩的采集的标识的结构数据确定充电桩的位姿。
  17. 根据权利要求11至14任一项所述的装置,其中,所述采集定位模块,用于通过红外、摄像头、超声和激光采集装置中的一种或任意组合,采集机器人在移动中的当前的周围环境数据。
  18. 根据权利要求11至14任一项所述的装置,其中,所述自主寻桩模块,用于通过红外、深度摄像头、超声和激光采集装置中的一种或任意组合采集潜在或者已注册的充电桩上的标识的结构数据。
  19. 根据权利要求11至14任一项所述的装置,其中,所述对接模块,用于采集机器人的移动距离、方向;根据所述充电桩的位姿调整和采集的机器人的移动距离、方向,调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
  20. 根据权利要求11至14任一项所述的装置,其中,所述远程回归模块,用于根据当前的环境地图、所述环境地图中的当前位姿和潜在或者已注册的充电桩位置,确定所述机器人移动的全局路径;根据所述全局路径控制所述机器人向潜在或者已注册的充电桩位置附近的近程寻桩对接区域移动;采集机器人的当前移动速度,根据当前的环境地图、所述环境 地图中的当前位姿和机器人的当前移动速度对所述全局路径的局部轨迹和局部轨迹中的运行速度进行调整,得到调整后的平滑的无碰撞的全局路径;根据所述调整后的全局路径,将所述机器人继续移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内。
  21. 一种基于计算的设备,其中,包括:
    处理器;以及
    被安排成存储计算机可执行指令的存储器,所述可执行指令在被执行时使所述处理器:
    采集机器人在移动中的当前的周围环境数据,根据所述周围环境数据生成所述机器人所处环境的环境地图和所述机器人在所述环境地图中的位姿,所述环境地图包括已记录的潜在或者已注册的充电桩位置;
    根据所述环境地图和所述环境地图中的位姿,将所述机器人移动至潜在或者已注册的充电桩位置附近的近程寻桩对接区域内;
    采集潜在或者已注册的充电桩上的标识的结构数据,若所述采集的标识的结构数据与预存的标识模板结构数据的匹配度大于预设匹配度阈值,则根据所述采集的标识的结构数据确定充电桩的位姿;
    根据所述充电桩的位姿调整所述机器人在所述环境地图中的位姿,将所述充电桩与机器人对接进行充电。
PCT/CN2018/080273 2017-05-18 2018-03-23 机器人充电方法及装置 WO2018210059A1 (zh)

Priority Applications (2)

Application Number Priority Date Filing Date Title
US16/613,421 US11351681B2 (en) 2017-05-18 2018-03-23 Method and apparatus for charging robot
EP18801429.4A EP3627267B1 (en) 2017-05-18 2018-03-23 Method and apparatus for charging robot

Applications Claiming Priority (2)

Application Number Priority Date Filing Date Title
CN201710350724.2A CN106980320B (zh) 2017-05-18 2017-05-18 机器人充电方法及装置
CN201710350724.2 2017-05-18

Publications (2)

Publication Number Publication Date
WO2018210059A1 true WO2018210059A1 (zh) 2018-11-22
WO2018210059A9 WO2018210059A9 (zh) 2021-02-18

Family

ID=59343064

Family Applications (1)

Application Number Title Priority Date Filing Date
PCT/CN2018/080273 WO2018210059A1 (zh) 2017-05-18 2018-03-23 机器人充电方法及装置

Country Status (4)

Country Link
US (1) US11351681B2 (zh)
EP (1) EP3627267B1 (zh)
CN (1) CN106980320B (zh)
WO (1) WO2018210059A1 (zh)

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114256925A (zh) * 2021-12-22 2022-03-29 香港中文大学深港创新研究院(福田) 一种机器人自动充电系统及其充电方法
CN114625115A (zh) * 2021-03-09 2022-06-14 北京石头世纪科技股份有限公司 机器人的充电方法、装置及机器人

Families Citing this family (45)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
EP3508049B1 (en) 2016-06-30 2022-08-24 Techtronic Outdoor Products Technology Limited An autonomous lawn mower
CN106980320B (zh) 2017-05-18 2020-06-19 上海思岚科技有限公司 机器人充电方法及装置
CN107544248B (zh) * 2017-09-13 2019-12-13 上海思岚科技有限公司 一种移动机器人中的任务优化方法及设备
CN108873879B (zh) * 2017-09-25 2022-03-04 北京石头创新科技有限公司 自主移动机器人及其寻桩方法、控制装置和智能清洁系统
CN107577236A (zh) * 2017-09-27 2018-01-12 上海有个机器人有限公司 机器人自动归位充电方法、机器人、系统以及存储介质
CN108002154A (zh) * 2017-11-22 2018-05-08 上海思岚科技有限公司 控制机器人跨楼层移动的方法
CN107945233B (zh) * 2017-12-04 2020-11-24 深圳市无限动力发展有限公司 视觉扫地机器人及其回充方法
CN109974727B (zh) * 2017-12-28 2021-01-08 深圳市优必选科技有限公司 一种机器人充电方法、装置及机器人
CN108279667A (zh) * 2018-01-08 2018-07-13 浙江立石机器人技术有限公司 机器人充电路径规划方法、装置及系统
CN108303984A (zh) * 2018-02-27 2018-07-20 弗徕威智能机器人科技(上海)有限公司 一种移动机器人的自主回充方法
CN108444482B (zh) * 2018-06-15 2021-10-22 东北大学 一种无人机自主寻路避障方法及系统
CN108983603B (zh) * 2018-06-27 2021-07-16 广州视源电子科技股份有限公司 一种机器人与物体的对接方法及其机器人
CN108767933A (zh) * 2018-07-30 2018-11-06 杭州迦智科技有限公司 一种用于充电的控制方法及其装置、存储介质和充电设备
CN109211237A (zh) * 2018-08-07 2019-01-15 北京云迹科技有限公司 基于多充电桩的机器人位置校正方法和装置
CN110838144B (zh) * 2018-08-15 2022-09-30 杭州萤石软件有限公司 一种充电设备识别方法、移动机器人和充电设备识别系统
CN109358058B (zh) * 2018-10-10 2021-11-19 中石化(洛阳)科技有限公司 管道状态检测系统和方法
CN109586360B (zh) 2018-11-09 2020-09-22 深圳市银星智能科技股份有限公司 一种机器人自动充电的方法、装置、充电桩和机器人
CN111766852A (zh) * 2019-03-12 2020-10-13 北京奇虎科技有限公司 一种扫地机器人的清扫控制方法和装置
CN109993794A (zh) * 2019-03-29 2019-07-09 北京猎户星空科技有限公司 一种机器人重定位方法、装置、控制设备和存储介质
CN110162063A (zh) * 2019-06-12 2019-08-23 北京洛必德科技有限公司 一种用于机器人自动充电的路径规划方法和装置
CN110378960A (zh) * 2019-07-26 2019-10-25 青岛特锐德电气股份有限公司 一种充电接口的定位识别方法和装置
CN110477825B (zh) * 2019-08-30 2021-10-26 深圳飞科机器人有限公司 清洁机器人、自主充电方法、系统及可读存储介质
CN112748727B (zh) * 2019-10-31 2024-07-12 珠海一微半导体股份有限公司 一种利用目标点的导航控制方法、芯片及机器人
CN111142513B (zh) * 2019-12-02 2024-01-26 深圳优地科技有限公司 初始化坐标的获取方法、调度方法、电子设备及存储介质
CN111166248A (zh) * 2020-01-16 2020-05-19 深圳飞科机器人有限公司 清洁机器人、自主充电方法及自主充电系统
CN111679671A (zh) * 2020-06-08 2020-09-18 南京聚特机器人技术有限公司 一种机器人与充电桩自动对接的方法及其系统
CN111753695B (zh) * 2020-06-17 2023-10-13 上海宜硕网络科技有限公司 一种模拟机器人充电返回路线的方法、装置和电子设备
CN112033391B (zh) * 2020-08-20 2024-02-13 常州市贝叶斯智能科技有限公司 一种基于充电桩的机器人重定位方法及装置
CN111923771B (zh) * 2020-08-24 2021-09-17 东营科技职业学院 一种新能源电动汽车用可移动式电动汽车充电桩
CN112000100A (zh) * 2020-08-26 2020-11-27 德鲁动力科技(海南)有限公司 机器人的充电系统及方法
CN112180989B (zh) * 2020-09-30 2021-12-07 苏州盈科电子有限公司 一种机器人充电方法及装置
CN112327842B (zh) * 2020-10-29 2022-06-03 深圳市普渡科技有限公司 机器人定位充电桩的方法及系统
CN112636410A (zh) * 2020-12-10 2021-04-09 广州高新兴机器人有限公司 一种充电方法、移动机器人和充电桩
CN112987743B (zh) * 2021-03-02 2024-02-23 珠海一微半导体股份有限公司 一种机器人快速找座方法、芯片和机器人
CN112792820B (zh) * 2021-03-16 2021-09-14 千里眼(广州)人工智能科技有限公司 机器人自动回充方法、装置及机器人系统
CN113189981A (zh) * 2021-04-08 2021-07-30 深圳拓邦股份有限公司 充电机器人中转点识别方法、装置及充电机器人
CN113741447B (zh) * 2021-08-27 2024-02-20 优必康(青岛)科技有限公司 机器人充电对桩方法、装置、终端设备及存储介质
CN114967668A (zh) * 2021-11-19 2022-08-30 丰疆智能(深圳)有限公司 一种机器人自动充电方法及系统
CN114301110A (zh) * 2021-11-26 2022-04-08 苏州光格科技股份有限公司 机器人电池电量校准方法、装置、电子设备和存储介质
CN114355911B (zh) * 2021-12-24 2024-03-29 深圳甲壳虫智能有限公司 机器人的充电方法、装置、机器人和存储介质
CN114047771B (zh) * 2022-01-17 2022-04-08 广州里工实业有限公司 移动机器人的对接方法、系统、计算机设备及存储介质
CN114527755A (zh) * 2022-02-21 2022-05-24 山东新一代信息产业技术研究院有限公司 一种机器人自动回桩充电的方法、设备、存储介质
CN114744721A (zh) * 2022-04-28 2022-07-12 深圳市优必选科技股份有限公司 一种机器人的充电控制方法、终端设备及存储介质
CN115933706B (zh) * 2023-02-07 2023-07-25 科大讯飞股份有限公司 机器人充电方法、装置、机器人及机器人系统
CN116429145B (zh) * 2023-06-07 2023-08-25 福龙马城服机器人科技有限公司 一种复杂场景下无人车与垃圾桶自动对接导航方法及系统

Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE2226880B2 (de) * 1971-06-04 1976-02-05 KX. Tokyo Keiki, Tokio Unstetiger regler
CN102545275A (zh) * 2010-12-07 2012-07-04 上海新世纪机器人有限公司 机器人自动充电装置及其自动充电方法
CN103645733A (zh) * 2013-12-02 2014-03-19 江苏建威电子科技有限公司 自寻充电机器人及其自寻充电系统和方法
CN103901895A (zh) * 2014-04-18 2014-07-02 江苏久祥汽车电器集团有限公司 一种基于无极FastSLAM算法和匹配优化目标定位方法及机器人
CN103926925A (zh) * 2014-04-22 2014-07-16 江苏久祥汽车电器集团有限公司 一种基于改进的vfh算法的定位与避障方法及机器人
CN106980320A (zh) * 2017-05-18 2017-07-25 上海思岚科技有限公司 机器人充电方法及装置

Family Cites Families (20)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
JP4265076B2 (ja) * 2000-03-31 2009-05-20 沖電気工業株式会社 多画角カメラ、及び自動撮影装置
CA2373337A1 (en) * 2001-02-26 2002-08-26 Bombardier Inc. Snowmobile slide rail system
JP2004237075A (ja) * 2003-02-06 2004-08-26 Samsung Kwangju Electronics Co Ltd 外部充電装置を有するロボット掃除機システム及びロボット掃除機の外部充電装置の接続方法。
CN101431241B (zh) * 2007-11-06 2013-05-15 希姆通信息技术(上海)有限公司 双核手机关机状态下充电及充电导致开机处理方法及装置
KR101553654B1 (ko) * 2009-02-13 2015-10-01 삼성전자 주식회사 이동 로봇 및 이동 로봇의 이동 방법
KR101672787B1 (ko) * 2009-06-19 2016-11-17 삼성전자주식회사 로봇청소기와 도킹스테이션 및 이를 가지는 로봇청소기 시스템 및 그 제어방법
CN102202117B (zh) * 2011-04-22 2015-01-28 中兴通讯股份有限公司 一种具有usb接口的电子设备及其usb通信启动方法
US8515580B2 (en) * 2011-06-17 2013-08-20 Microsoft Corporation Docking process for recharging an autonomous mobile device
US9538892B2 (en) * 2012-10-05 2017-01-10 Irobot Corporation Robot management systems for determining docking station pose including mobile robots and methods using same
CN104063040A (zh) * 2013-03-18 2014-09-24 维沃移动通信有限公司 移动手持设备中前置摄像头在进行对象检测识别时的智能控制方法及系统
CN105527961A (zh) * 2014-09-30 2016-04-27 科沃斯机器人有限公司 一种自移动表面行走机器人系统及回归主充电座的方法
CN104348238B (zh) * 2014-11-13 2017-05-10 惠州Tcl移动通信有限公司 一种充电电压控制装置、移动终端、及控制方法
CN104578251A (zh) * 2014-12-01 2015-04-29 嘉兴市德宝威微电子有限公司 机器人充电方法和系统
DE102015114883A1 (de) * 2015-09-04 2017-03-09 RobArt GmbH Identifizierung und Lokalisierung einer Basisstation eines autonomen mobilen Roboters
CN105990876B (zh) * 2015-12-21 2019-03-01 小米科技有限责任公司 充电桩及其识别方法、装置和自动清洁设备
CN205681138U (zh) * 2015-12-21 2016-11-09 小米科技有限责任公司 充电桩和自动清洁系统
CN105739501B (zh) * 2016-04-01 2017-09-26 北京云迹科技有限公司 一种智能机器人自动充电的方法
CN105743197A (zh) * 2016-05-12 2016-07-06 上海思岚科技有限公司 一种移动机器人系统及其自主充电方法
CN106125724A (zh) * 2016-06-13 2016-11-16 华讯方舟科技有限公司 一种机器人自主充电的方法及系统
CN106451635A (zh) * 2016-11-02 2017-02-22 深圳乐行天下科技有限公司 一种智能回充方法及装置

Patent Citations (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
DE2226880B2 (de) * 1971-06-04 1976-02-05 KX. Tokyo Keiki, Tokio Unstetiger regler
CN102545275A (zh) * 2010-12-07 2012-07-04 上海新世纪机器人有限公司 机器人自动充电装置及其自动充电方法
CN103645733A (zh) * 2013-12-02 2014-03-19 江苏建威电子科技有限公司 自寻充电机器人及其自寻充电系统和方法
CN103901895A (zh) * 2014-04-18 2014-07-02 江苏久祥汽车电器集团有限公司 一种基于无极FastSLAM算法和匹配优化目标定位方法及机器人
CN103926925A (zh) * 2014-04-22 2014-07-16 江苏久祥汽车电器集团有限公司 一种基于改进的vfh算法的定位与避障方法及机器人
CN106980320A (zh) * 2017-05-18 2017-07-25 上海思岚科技有限公司 机器人充电方法及装置

Non-Patent Citations (1)

* Cited by examiner, † Cited by third party
Title
See also references of EP3627267A4 *

Cited By (2)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN114625115A (zh) * 2021-03-09 2022-06-14 北京石头世纪科技股份有限公司 机器人的充电方法、装置及机器人
CN114256925A (zh) * 2021-12-22 2022-03-29 香港中文大学深港创新研究院(福田) 一种机器人自动充电系统及其充电方法

Also Published As

Publication number Publication date
WO2018210059A9 (zh) 2021-02-18
CN106980320B (zh) 2020-06-19
EP3627267A1 (en) 2020-03-25
US11351681B2 (en) 2022-06-07
EP3627267A4 (en) 2020-07-01
EP3627267C0 (en) 2024-06-05
CN106980320A (zh) 2017-07-25
US20200164530A1 (en) 2020-05-28
EP3627267B1 (en) 2024-06-05

Similar Documents

Publication Publication Date Title
WO2018210059A1 (zh) 机器人充电方法及装置
US10823576B2 (en) Systems and methods for robotic mapping
CN113741438B (zh) 路径规划方法、装置、存储介质、芯片及机器人
CN110675307B (zh) 基于vslam的3d稀疏点云到2d栅格图的实现方法
CN109730590B (zh) 清洁机器人以及清洁机器人自动返回充电的方法
CN111743450B (zh) 可移动装置的回充方法及可移动装置
CN110632915B (zh) 机器人回充路径规划方法、机器人及充电系统
Thompson et al. A probabilistic model of human motion and navigation intent for mobile robot path planning
WO2020199589A1 (zh) 桌面机器人的回充控制方法
WO2019062650A1 (zh) 一种扫地机器人的控制方法及设备
CN109528089B (zh) 一种被困清洁机器人的继续行走方法、装置及芯片
CN108290294A (zh) 移动机器人及其控制方法
JP2006350776A (ja) 移動体の経路生成装置
CN108180901A (zh) 导盲机器人的室内导航方法、装置、机器人及存储介质
US20230195130A1 (en) Information collection method, device and storage medium
CN110861082B (zh) 辅助建图方法、装置、建图机器人及存储介质
CN114448114A (zh) 基于移动机器人的智能无线供电系统
WO2018228254A1 (zh) 一种移动电子设备以及该移动电子设备中的方法
WO2023000679A1 (zh) 机器人回充控制方法、装置和存储介质
WO2020008754A1 (ja) 情報処理装置、最適時間推定方法、自己位置推定方法及びプログラムを記録した記録媒体
CN101672916A (zh) 机械扫描式成像声呐的运动失真补偿方法
CN112447058B (zh) 泊车方法、装置、计算机设备及存储介质
CN111630346B (zh) 基于图像和无线电词语的移动设备的改进定位
CN113467451A (zh) 机器人的回充方法和装置、电子设备和可读存储介质
CN106204516B (zh) 一种机器人的自动充电方法及装置

Legal Events

Date Code Title Description
121 Ep: the epo has been informed by wipo that ep was designated in this application

Ref document number: 18801429

Country of ref document: EP

Kind code of ref document: A1

NENP Non-entry into the national phase

Ref country code: DE

ENP Entry into the national phase

Ref document number: 2018801429

Country of ref document: EP

Effective date: 20191218