Robots
Copyright: Tanja Katharina Kaiser

Division of Labor in Robot Swarms with Minimize Surprise

A major challenge in swarm robotics is to scale with task complexity. Division of labour and task allocation are solid candidates to resolve it. In this project, we propose to use methods of evolutionary computation and our predictive coding approach of minimize surprise. Key is to let robots choose actions that make their world predictable. We want to use minimize surprise to provoke division of labour and task allocation. We want to study this system in simulations and robot experiments of different sizes, ranging from 5 robots to 15 robots on small and large areas. There is potential to compare to collective behaviour in social animals that show complex forms of division of labour and task allocation. This natural division of labour often relies on morphological or genetic specialization and communication (e.g., recruitment signals). Similarly, decentralized mobile multi-robot systems need to coordinate and collaborate to solve complex tasks using collective behaviours.

Sketch of experiment scenario
Copyright: AG Cyber-Physical Systems

External Page

To view this content (source: www.xyz.de ), please click on Accept. We would like to point out that by accepting this iframe, data could be transmitted to third parties or cookies may be stored.

You can find more information on our privacy policy .