Generating diverse behaviors of evolutionary robots with speciation for theory of mind

  • Authors:
  • Si-Hyuk Yi;Sung-Bae Cho

  • Affiliations:
  • Dept. of Computer Science, Yonsei University, Seoul, Korea;Dept. of Computer Science, Yonsei University, Seoul, Korea

  • Venue:
  • SEAL'12 Proceedings of the 9th international conference on Simulated Evolution and Learning
  • Year:
  • 2012

Quantified Score

Hi-index 0.00

Visualization

Abstract

Theory of Mind (ToM) is the ability to read another person's mind. To apply ToM in robots, robot should read the intention from target. However, it is difficult to read target's intention directly. Robot uses the sensors to measure distance from target because distance is the feature to read target's intention. Neural network has been widely used to control the robot for generating a diverse speciation. It has been less explored in behavior-based robotics. Speciation usually relies on a distance measure that allows different from the robot to target to be compared. In this paper, we proposed novel measure to generate diverse behaviors of a robot with speciation for ToM. It includes some distance measure such as Euclidean distance, cosine distance, arctangent distance, and edit distance. It generates diverse behaviors of the robot by neural network for ToM. The proposed method has been experimented on a real e-puck robot platform.