[go: up one dir, main page]
More Web Proxy on the site http://driver.im/
Skip to content
View DMackRus's full-sized avatar

Highlights

  • Pro

Block or report DMackRus

Block user

Prevent this user from interacting with your repositories and sending you notifications. Learn more about blocking users.

You must be logged in to block users.

Please don't include any personal information such as legal names or email addresses. Maximum 100 characters, markdown supported. This note will be visible to only you.
Report abuse

Contact GitHub support about this user’s behavior. Learn more about reporting abuse.

Report abuse
DMackRus/README.md

Hi, I'm Dave👋

I am a PhD student at the University of Leeds working on robotic manipulation!

The general work of my PhD has been focused on methods of using approximations / simplifications to speed up trajectory optimisation, especially for manipulation in clutter. The two main pieces of work of my PhD so far have been on the following:

  • Speeding up gradient-based trajectory optimisation via approximating dynamics derivatives over a trajectory. We only compute dynamics derivatives at certain timesteps (keypoints) over the trajectory and then interpolate the rest! This work was presented at ICRA2023, and the project source code is here. This work is currently being extended to a journal paper, my new repository takes this first ideas significantly further on a wide variety of tasks!
  • Speeding up gradient-based trajectory optimisation via operating on a reduced state vector. This reduced state vector changes dynamically during online MPC! This work was presented at WAFR2024, and the project source code is here.

Both of these works are focused on speeding up trajectory optimisation times whilst trying to minimse any degradation in performance. This is especially useful in MPC where it is usually more important to optimise a trajectory as fast as possible, and not get too hung up on optimality.

To finish my PhD I am interested in combining learning methods with trajectory optimisation, again in the same vein as my previous two works.

📫 If you want to reach out about anything here is my email! el16dmcr@leeds.ac.uk

Pinned Loading

  1. Dynamic_Interpolation_iLQR Dynamic_Interpolation_iLQR Public

    Russell et al. ~ ICRA 2023 Paper: Adaptive approximation of dynamics gradients via interpolation to speed up trajectory optimisation

    Makefile 4

  2. TrajOptKP TrajOptKP Public

    Gradient-based trajectory optimisation toolbox that speeds up trajectory optimisation by only computing dynamics derivatives at key-points with finite-differencing. Remainder of derivatives are app…

    C++ 4 3

  3. iLQR-SVR iLQR-SVR Public

    Russell et al. ~WAFR 2024 Paper: Online state vector reduction during model predictive control with gradient-based trajectory optimisation

    C++

  4. cobot_pump_ros cobot_pump_ros Public

    Forked from roboticsleeds/cobot_pump_ros

    ROS package for the cobot pump using the libfranka middleware

    CMake

  5. OSRS-Flipping-Assistant OSRS-Flipping-Assistant Public

    OSRS (Old School RuneScape) Flipping assistant GUI. Free tool to download that can keep track of item price changes and enable users to receive alerts when items hit certain price thresholds.

    Python 1