Adaptive Tracking of a Single-Rigid-Body Character in Various Environments

by   Taesoo Kwon, et al.

Since the introduction of DeepMimic [Peng et al. 2018], subsequent research has focused on expanding the repertoire of simulated motions across various scenarios. In this study, we propose an alternative approach for this goal, a deep reinforcement learning method based on the simulation of a single-rigid-body character. Using the centroidal dynamics model (CDM) to express the full-body character as a single rigid body (SRB) and training a policy to track a reference motion, we can obtain a policy that is capable of adapting to various unobserved environmental changes and controller transitions without requiring any additional learning. Due to the reduced dimension of state and action space, the learning process is sample-efficient. The final full-body motion is kinematically generated in a physically plausible way, based on the state of the simulated SRB character. The SRB simulation is formulated as a quadratic programming (QP) problem, and the policy outputs an action that allows the SRB character to follow the reference motion. We demonstrate that our policy, efficiently trained within 30 minutes on an ultraportable laptop, has the ability to cope with environments that have not been experienced during learning, such as running on uneven terrain or pushing a box, and transitions between learned policies, without any additional learning.


page 1

page 3

page 6

page 9

page 10


QuestSim: Human Motion Tracking from Sparse Sensors with Simulated Avatars

Real-time tracking of human body motion is crucial for interactive and i...

Generating Upper-Body Motion for Real-Time Characters Making their Way through Dynamic Environments

Real-time character animation in dynamic environments requires the gener...

Real-Time Character Rise Motions

This paper presents an uncomplicated dynamic controller for generating p...

Composite Motion Learning with Task Control

We present a deep learning method for composite and task-driven motion c...

PMP: Learning to Physically Interact with Environments using Part-wise Motion Priors

We present a method to animate a character incorporating multiple part-w...

Brax – A Differentiable Physics Engine for Large Scale Rigid Body Simulation

We present Brax, an open source library for rigid body simulation with a...

ORBIT: A Unified Simulation Framework for Interactive Robot Learning Environments

We present ORBIT, a unified and modular framework for robot learning pow...

Please sign up or login with your details

Forgot password? Click here to reset