SIGGRAPH 2010 By Focus
Learning Behavior Styles With Inverse Reinforcement Learning
A method for inferring the behavior styles of character controllers from examples. This paper shows that a rich set of behavior variations can be captured by determining the appropriate reward function in the reinforcement-learning framework and that the discovered-reward function can be applied to different tasks.
A Synthetic-Vision-Based Steering Approach for Crowd Simulation
Humans control their locomotion from their optic flow. This paper simulates crowds of individual walkers steered from their synthetic vision. The avoidance model is inspired by cognitive science work on human locomotion. The simulations display emerging self-organized patterns at a global scale from the local interactions between walkers.
Comprehensive Biomechanical Modeling and Simulation of the Upper Body
This comprehensive biomechanical model of the human upper body confronts the combined challenge of modeling and controlling more or less all of the relevant articular bones and muscles as well as simulating the physics-based deformations of the soft tissues.
A method for generating body-language animations from live speech using optimal policy controllers. The method is modular and versatile, admitting a variety of applications and additional input channels.