Autonomous Animated Characters

James Kuffner, Jr., (  )

Project Description

Click image to download movie Quicktime (1.1MB)

This research investigates the problem of designing a software framework for creating autonomous agents for interactive character animation. The ultimate goal is to create animated characters able to respond intelligently to task-level commands such as "walk over to the table and pick up the book". User commands or high-level scripts provide task commands, and the software automatically generates the underlying motion to complete the task. Potential applications include virtual reality, video games, web avatars, desktop movie studios, and other real-time virtual human simulations (urban / industrial / military).

Research Overview

Our research efforts have been divided into several key areas, including goal-directed navigation, object grasping and manipulation, and synthetic vision. Links to these specific topics are provided below.

General Animation Framework	Goal-Directed Navigation

Simulated Visual Perception	Object Grasping and Manipulation

High-Level Behaviors

References

• J.J. Kuffner and J.C. Latombe. Interactive manipulation planning for animated characters. In Pacific Graphics '00, Hong Kong, October 2000. (poster paper). [Abstract] [MoreInfo]
   
• J.J. Kuffner and S.M. LaValle. RRT-Connect: An efficient approach to single-query path planning. In Proc. IEEE Int'l Conf. on Robotics and Automation (ICRA'2000), San Francisco, CA, April 2000. [Abstract] [MoreInfo]

• J.J. Kuffner Jr. Autonomous Agents for Real-time Animation. PhD thesis, Stanford University, Stanford, CA, December 1999. [Abstract] [MoreInfo]

• J.J. Kuffner and J.C. Latombe. Fast synthetic vision, memory, and learning models for virtual humans. In Proc. CA '99 : IEEE Int'l Conf. on Computer Animation., pages 118-127, Geneva, Switzerland, May 1999. [Abstract] [MoreInfo]

• J.J. Kuffner Jr. Goal-directed navigation for animated characters using real-time path planning and control. In Proc. CAPTECH '98 : Workshop on Modelling and Motion Capture Techniques for Virtual Environments, Geneva, Switzerland, November 1998. Springer-Verlag. [Abstract] [MoreInfo]

• Y. Koga, K. Kondo, J.J. Kuffner, and J.C. Latombe. Planning motions with intentions. In Proc. SIGGRAPH '94, pages 395-408, 1994. (Color plates not included). [Abstract] [MoreInfo]

• J. Kuffner, K. Kondo, Y. Koga, and J.C. Latombe. ENDGAME. Video transactions of the Electronic Theater of SIGGRAPH '94, July 1994. [MoreInfo]