Introduction

WalkNet is a neural network-based agent contoller with navigation capabilities, as well as modulating the agent's expression of affect and personal signature through its movements. WalkNet can be used for autonomous agent movement, or by direct control of the user or a video games AI.

WalkNet is part of my PhD research and is the second iteration of my agent system, proceeding the AffectNet project.

Outputs

Sample output of WalkNet
Generating walking movements while transitioning from a high valence, high arousal state to a low valence, low arousal state.
Sample output of WalkNet
Generating walking movements while transitioning from a low valence, high arousal state to a high valence, low arousal state.
Real-time control and movement generation.

Publication

Omid Alemi and Philippe Pasquier. "WalkNet: A Neural-Network-Based Interactive Walking Controller". In Proceedings of the 17th International Conference on Intelligent Virtual Agents. IVA 2017. Lecture Notes in Computer Science, vol 10498. Springer, Cham. PDF. DOI.