LeggedRobots

Miniprojects for the MICRO-507 : Legged Robots course

Table of Contents

• About the Project 1
• About the Project 2
• Folder Structure
• Videos
• Contact

About The Project 1

Project 1 is about planning the Center of Mass (CoM) trajectory for a (simulated) biped Atlas robot. The technique used is the Divergent Component of Motion (DCM). The resulting gaits are analyzed and discussed, and the conclusion is reached that this method requires quite a few simplifications, some of which are not valid in the real world.

About The Project 2

Project 2 adresses quadruped locomotion. Gaits are generated for (simulated) A1 quadruped, first using Central Pattern Generators (CPG), and the using Deep Reinforcement Learning (DRL) The resulting gaits are analyzed and discussed, and the conclusion is reached that CPG methods are relatively simple and quick to implement, however, they require a lot of parameter tuning to get them to work nicely. DRL techniques require no (manual) parameter tuning, but instead require the setting an appropriate reward function, which can be difficult to guesstimate.

Folder Structure

Folder Name	Comment
Project_1	folder containing the project 1
- code	python code for the project
Project_2	folder containing the project 2
- code	python code for the project

Videos

Project 1

Fast Locomotion

fast_locomotion.mp4

Normal Locomotion

normal_locomotion.mp4

Project 2

CPG

Pace

PACE.mov

Walk

WALK.mov

Bound

BOUND.mov

Trot

TROT.mov

DRL

PPO with Cartesian PD

RL_PPO_WITH_CARTESIAN_PD.mov

PPO without Cartesian PD

RL_PPO_WITHOUT_CARTESIAN_PD.mov

Contacts

Biselx Michael - [email protected]
Bumann Samuel - [email protected]
lvuilleu

Project Link: https://github.com/mbiselx/LeggedRobots