Robust task-based control policies for physics-based characters

Stelian Coros, Philippe Beaudoin, Michiel van de Panne
2009 ACM Transactions on Graphics  
a) Go-to-line (b) Heading (c) Go-to-point (d) Point-with-heading (e) Heading-and-speed (f) Very Robust Walk Figure 1 : We precompute task-specific control policies for real-time physics-based characters. The character moves efficiently towards the current goal, responds interactively to changes of the goal, and can respond to significant physical interaction with the environment. Abstract We present a method for precomputing robust task-based control policies for physically simulated
more » ... 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.
doi:10.1145/1618452.1618516 fatcat:hmqdlyfyjzhhrhvdpoxoah6ypu