Expressive Gesture Animation Based on Non Parametric Learning of Sensory-Motor Models

Authors:
Sylvie Gibet;Pierre-François Marteau
Affiliations:
-;-
Venue:
CASA '03 Proceedings of the 16th International Conference on Computer Animation and Social Agents (CASA 2003)
Year:
2003

Citing 0
Cited 4

Analysis of Human Motion, Based on the Reduction of Multidimensional Captured Data --- Application to Hand Gesture Compression, Segmentation and Synthesis

AMDO '08 Proceedings of the 5th international conference on Articulated Motion and Deformable Objects
Adaptive sampling of motion trajectories for discrete task-based analysis and synthesis of gesture

GW'05 Proceedings of the 6th international conference on Gesture in Human-Computer Interaction and Simulation
Modeling joint synergies to synthesize realistic movements

GW'09 Proceedings of the 8th international conference on Gesture in Embodied Communication and Human-Computer Interaction
Toward a motor theory of sign language perception

GW'11 Proceedings of the 9th international conference on Gesture and Sign Language in Human-Computer Interaction and Embodied Communication

Quantified Score

Hi-index	0.00

Visualization

Abstract

This paper presents an efficient method of learningmotion control for autonomous animated characters.The method uses a non parametric learning approachwhich identifies non linear mappings between sensorysignals and motor control. The learning phase ishandled through a General Regression Neural Networkmodel simulated by using near neighbors searchalgorithms (kd-tree). The resulting adaptive model(ASMM) is suitable for the expressive animation of ananthropomorphic hand-arm system involved in reachingor tracking tasks.