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

Bellegarda et al., 2022 - Google Patents

CPG-RL: Learning central pattern generators for quadruped locomotion

Bellegarda et al., 2022

View PDF
Document ID
9136200861582321519
Author
Bellegarda G
Ijspeert A
Publication year
Publication venue
IEEE Robotics and Automation Letters

External Links

Snippet

In this letter, we present a method for integrating central pattern generators (CPGs), ie systems of coupled oscillators, into the deep reinforcement learning (DRL) framework to produce robust and omnidirectional quadruped locomotion. The agent learns to directly …
Continue reading at arxiv.org (PDF) (other versions)

Classifications

    • G—PHYSICS
    • G05—CONTROLLING; REGULATING
    • G05B—CONTROL OR REGULATING SYSTEMS IN GENERAL; FUNCTIONAL ELEMENTS OF SUCH SYSTEMS; MONITORING OR TESTING ARRANGEMENTS FOR SUCH SYSTEMS OR ELEMENTS
    • G05B13/00—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion
    • G05B13/02—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric
    • G05B13/0265—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion
    • G05B13/027—Adaptive control systems, i.e. systems automatically adjusting themselves to have a performance which is optimum according to some preassigned criterion electric the criterion being a learning criterion using neural networks only
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/04—Architectures, e.g. interconnection topology
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING; COUNTING
    • G06N—COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS
    • G06N3/00—Computer systems based on biological models
    • G06N3/02—Computer systems based on biological models using neural network models
    • G06N3/08—Learning methods

Similar Documents

Publication Publication Date Title
Bellegarda et al. CPG-RL: Learning central pattern generators for quadruped locomotion
Shao et al. Learning free gait transition for quadruped robots via phase-guided controller
Thor et al. Generic neural locomotion control framework for legged robots
Buschmann et al. Controlling legs for locomotion—insights from robotics and neurobiology
Wu et al. Learning robust and agile legged locomotion using adversarial motion priors
Lewis et al. Genetic algorithms for gait synthesis in a hexapod robot
Bellegarda et al. Robust high-speed running for quadruped robots via deep reinforcement learning
Sharbafi et al. Bioinspired legged locomotion: models, concepts, control and applications
Yang et al. Cajun: Continuous adaptive jumping using a learned centroidal controller
Shafiee et al. Manyquadrupeds: Learning a single locomotion policy for diverse quadruped robots
Shafiee et al. Puppeteer and marionette: Learning anticipatory quadrupedal locomotion based on interactions of a central pattern generator and supraspinal drive
Bellegarda et al. Quadruped-Frog: Rapid Online Optimization of Continuous Quadruped Jumping
Shafiee et al. Deeptransition: Viability leads to the emergence of gait transitions in learning anticipatory quadrupedal locomotion skills
Yu et al. Dynamic bipedal maneuvers through sim-to-real reinforcement learning
Li et al. Learning agile bipedal motions on a quadrupedal robot
Bellegarda et al. Visual cpg-rl: Learning central pattern generators for visually-guided quadruped navigation
Yu et al. Dynamic bipedal turning through sim-to-real reinforcement learning
Li et al. AI-CPG: Adaptive Imitated Central Pattern Generators for Bipedal Locomotion Learned Through Reinforced Reflex Neural Networks
Ouannes et al. Gait evolution for humanoid robot in a physically simulated environment
von Twickel et al. Reflex-oscillations in evolved single leg neurocontrollers for walking machines
Wei et al. Learning Gait-conditioned Bipedal Locomotion with Motor Adaptation
Liu et al. Skill Latent Space Based Multigait Learning for a Legged Robot
Miller et al. Reinforcement learning for legged robots: Motion imitation from model-based optimal control
Tan et al. Perceptive locomotion with controllable pace and natural gait transitions over uneven terrains
Li et al. Agile and versatile bipedal robot tracking control through reinforcement learning