Feedback Control For Cassie With Deep Reinforcement Learning

3 code implementations • 15 Mar 2018 • Zhaoming Xie, Glen Berseth, Patrick Clary, Jonathan Hurst, Michiel Van de Panne

By formulating a feedback control problem as finding the optimal policy for a Markov Decision Process, we are able to learn robust walking controllers that imitate a reference motion with DRL.

Robotics

Iterative Reinforcement Learning Based Design of Dynamic Locomotion Skills for Cassie

1 code implementation • 22 Mar 2019 • Zhaoming Xie, Patrick Clary, Jeremy Dao, Pedro Morais, Jonathan Hurst, Michiel Van de Panne

Deep reinforcement learning (DRL) is a promising approach for developing legged locomotion skills.

Robotics

On Learning Symmetric Locomotion

1 code implementation • Proceedings of ACM SIGGRAPH Motion, Interaction, and Games (MIG 2019) 2019 • Farzad Abdolhosseini, Hung Yu Ling, Zhaoming Xie, Xue Bin Peng, Michiel Van de Panne

We describe, compare, and evaluate four practical methods for encouraging motion symmetry.

Learning to Correspond Dynamical Systems

no code implementations • L4DC 2020 • Nam Hee Kim, Zhaoming Xie, Michiel Van de Panne

Many dynamical systems exhibit similar structure, as often captured by hand-designed simplified models that can be used for analysis and control.

ALLSTEPS: Curriculum-driven Learning of Stepping Stone Skills

1 code implementation • 9 May 2020 • Zhaoming Xie, Hung Yu Ling, Nam Hee Kim, Michiel Van de Panne

Humans are highly adept at walking in environments with foot placement constraints, including stepping-stone scenarios where the footstep locations are fully constrained.

reinforcement-learning Reinforcement Learning (RL)

Learning a Contact-Adaptive Controller for Robust, Efficient Legged Locomotion

no code implementations • 21 Sep 2020 • Xingye Da, Zhaoming Xie, David Hoeller, Byron Boots, Animashree Anandkumar, Yuke Zhu, Buck Babich, Animesh Garg

We present a hierarchical framework that combines model-based control and reinforcement learning (RL) to synthesize robust controllers for a quadruped (the Unitree Laikago).

reinforcement-learning Reinforcement Learning (RL)

GLiDE: Generalizable Quadrupedal Locomotion in Diverse Environments with a Centroidal Model

no code implementations • 20 Apr 2021 • Zhaoming Xie, Xingye Da, Buck Babich, Animesh Garg, Michiel Van de Panne

Model-free reinforcement learning (RL) for legged locomotion commonly relies on a physics simulator that can accurately predict the behaviors of every degree of freedom of the robot.

Model Predictive Control Reinforcement Learning (RL)

Learning Soccer Juggling Skills with Layer-wise Mixture-of-Experts

1 code implementation • SIGGRAPH 2022 • Zhaoming Xie, Sebastian Starke, Hung Yu Ling, Michiel Van de Panne

Learning physics-based character controllers that can successfully integrate diverse motor skills using a single policy remains a challenging problem.

Humanoid Control Imitation Learning +1

Learning Bipedal Walking for Humanoids with Current Feedback

1 code implementation • 7 Mar 2023 • Rohan Pratap Singh, Zhaoming Xie, Pierre Gergondet, Fumio Kanehiro

Recent advances in deep reinforcement learning (RL) based techniques combined with training in simulation have offered a new approach to developing robust controllers for legged robots.

Reinforcement Learning (RL)