Exciting Action: Investigating Efficient Exploration for Learning Musculoskeletal Humanoid Locomotion
Authors:
- 22 November 2024
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 205-212
Abstract
Learning a locomotion controller for a musculoskeletal system is challenging due to over-actuation and high-dimensional action space. While many reinforcement learning methods attempt to address this issue, they often struggle to learn human-like gaits because of the complexity involved in engineering an effective reward function. In this paper, we demonstrate that adversarial imitation learning can address this issue by analyzing key problems and providing solutions using both current literature and novel techniques. We validate our methodology by learning walking and running gaits on a simulated humanoid model with 16 degrees of freedom and 92 Muscle-Tendon Units, achieving natural-looking gaits with only a few demonstrations. Code is available at https://github.com/henriTUD/musculoco_learning.Keywords
This publication has 18 references indexed in Scilit:
- Muscle‐driven virtual human motion generation approach based on deep reinforcement learningComputer Animation and Virtual Worlds, 2022
- Muscle Activation Analysis from Gait Kinematics and Reinforcement Learning2022
- Deep reinforcement learning for modeling human locomotion control in neuromechanical simulationbioRxiv, 2020
- Artificial Intelligence for Prosthetics: Challenge Solutions2019
- A deep reinforcement learning based approach towards generating human walking behavior with a neuromuscular model2019
- Learning to Run Challenge Solutions: Adapting Reinforcement Learning Methods for Neuromusculoskeletal Environments2018
- MuJoCo: A physics engine for model-based control2012
- Muscle contributions to propulsion and support during runningJournal of Biomechanics, 2010
- OpenSim: Open-Source Software to Create and Analyze Dynamic Simulations of MovementIEEE Transactions on Biomedical Engineering, 2007
- On the Theory of the Brownian MotionPhysical Review B, 1930