Engineered Self-Organization for Resilient Robot Self-Assembly with Minimal Surprise

  title={Engineered Self-Organization for Resilient Robot Self-Assembly with Minimal Surprise},
  author={Tanja Katharina Kaiser and H. Hamann},
  journal={Robotics Auton. Syst.},
  • Tanja Katharina Kaiser, H. Hamann
  • Published 2019
  • Computer Science
  • Robotics Auton. Syst.
  • In collective robotic systems, the automatic generation of controllers for complex tasks is still a challenging problem. Open-ended evolution of complex robot behaviors can be a possible solution whereby an intrinsic driver for pattern formation and self-organization may prove to be important. We implement such a driver in collective robot systems by evolving prediction networks as world models in pair with action-selection networks. Fitness is given for good predictions which causes a bias… CONTINUE READING
    1 Citations
    Diversity in swarm robotics with task-independent behavior characterization


    Self-assembly in Patterns with Minimal Surprise: Engineered Self-organization and Adaptation to the Environment
    • 5
    Programmable self-assembly in a thousand-robot swarm
    • 659
    • PDF
    Taming the Beast: Guided Self-organization of Behavior in Autonomous Robots
    • 17
    • PDF
    Evolution of Collective Behaviors by Minimizing Surprise
    • 15
    • PDF
    Emergent Structures Assembled by Large Swarms of Simple Robots
    • 9
    • PDF
    Symbiotic Multi-Robot Organisms - Reliability, Adaptability, Evolution
    • 131
    Evolving robot swarm behaviors by minimizing surprise: results of simulations in 2-d on a Torus
    • 3
    Swarm-Bot: A New Distributed Robotic Concept
    • 355
    • PDF