Affiliation:
1. University of British Columbia
Abstract
We present a method for precomputing robust task-based control policies for physically simulated characters. This allows for characters that can demonstrate skill and purpose in completing a given task, such as walking to a target location, while physically interacting with the environment in significant ways. As input, the method assumes an abstract action vocabulary consisting of balance-aware, step-based controllers. A novel constrained state exploration phase is first used to define a character dynamics model as well as a finite volume of character states over which the control policy will be defined. An optimized control policy is then computed using reinforcement learning. The final policy spans the cross-product of the character state and task state, and is more robust than the conrollers it is constructed from. We demonstrate real-time results for six locomotion-based tasks and on three highly-varied bipedal characters. We further provide a game-scenario demonstration.
Publisher
Association for Computing Machinery (ACM)
Subject
Computer Graphics and Computer-Aided Design
Reference36 articles.
1. Nonparametric representation of policies and value functions: A trajectory-based approach;Atkeson C. G.;Advances in Neural Information Processing Systems,2003
Cited by
63 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Adaptive Tracking of a Single-Rigid-Body Character in Various Environments;SIGGRAPH Asia 2023 Conference Papers;2023-12-10
2. Computer Game Scenario Representation: A Systematic Mapping Study;e-Informatica Software Engineering Journal;2023
3. PADL: Language-Directed Physics-Based Character Control;SIGGRAPH Asia 2022 Conference Papers;2022-11-29
4. ASE;ACM Transactions on Graphics;2022-07
5. MatBuilder;ACM Transactions on Graphics;2022-07