Neural Gait Generator

Physiological Gait Controls with a Neural Pattern Generator

Abstract

This paper proposes a control methodology for human gait with a pattern generator. The pattern generator generates cyclic signals via a couple of mutually inhibited neurons, and drives a proportional derivative controller that supplies joint angles of a virtual human. The state of the pattern generator is entrained by the signal of the controller, and such mutual feedback stabilizes the generation of rhythmic signals for variable conditions. Legs and arms can automatically synchronize their periodical movements without using a central supervisor because the corresponding neural oscillators mutually feed their output signals. Our system generates various gaits in a common mechanism with a small number of parameters, which is well suited for real-time, interactive and on-the-fly controls. Moreover, the movements obtained from motion capture data can be controlled by introducing adjustable non-linear filters.

Publications

1. Shigeru Kuriyama, Yoshimi Kurihara, Yusuke Irino, and Toyohisa Kaneko, "Physiological Gaits Controls with a Neural Pattern Generator", The Journal of Visualization and Computer Animation, Vol.13, No.2, pp.107-119, 2002.
2. Shigeru Kuriyama, Yusuke Irino, and Toyohisa Kaneko, "Adaptive Controls of Personified Locomotive Agents", International Workshop on Lifelike Animated Agents (In PRICAI-02), pp.70-75, 2002.
3. Shigeru Kuriyama, Yusuke Irino, and Toyohisa Kaneko, "Real-time Manipulation of Cyclic Motion-capture Data with Pattern Generator", First International Workshop on Entertainment Computing, pp.167-174, 2002.
4. Shigeru Kuriyama, Yoshimi Kurihara, and Toyohisa Kaneko, "Adaptive Gait Generation via Physiological Controls", Computer Animation 2001, pp.42-51, 2001.

Results

Simple demonstration MPEG-1: 7.2 MB with Audio 320×240, 0:43 (with Japanese caption)