Action generation from natural language

Authors:
Satoshi Funatsu;Tomofumi Koyama;Suguru Saito;Takenobu Tokunaga;Masayuki Nakajima
Affiliations:
Department of Computer Science, Tokyo Institute of Technology, Japan;Department of Computer Science, Tokyo Institute of Technology, Japan;Department of Computer Science, Tokyo Institute of Technology, Japan;Department of Computer Science, Tokyo Institute of Technology, Japan;Department of Computer Science, Tokyo Institute of Technology, Japan
Venue:
PCM'04 Proceedings of the 5th Pacific Rim conference on Advances in Multimedia Information Processing - Volume Part III
Year:
2004

Citing 3
Cited 0

Animation control for real-time virtual humans

Communications of the ACM
Dynamically altering agent behaviors using natural language instructions

AGENTS '00 Proceedings of the fourth international conference on Autonomous agents
Motion graphs

Proceedings of the 29th annual conference on Computer graphics and interactive techniques

Quantified Score

Hi-index	0.00

Visualization

Abstract

When building a virtual agent system equipped with a natural language command interface, the interpretation of sentences into action commands that will drive the animation is crucial. In our system, these action commands are transformed a series of spatial and action constraint symbols. Using these symbols, the system can decide on the most plausible motion for the agent.