Bootstrapped Neuro-Simulation for Damage Recovery in Complex Robots

• Published in: 2022 IEEE Congress on Evolutionary Computation (CEC) pp. 1 - 8
• Main Authors: Leonard, Brydon A., Du Plessis, Mathys C.
• Format: Conference Proceeding
• Language: English
• Published: IEEE 18.07.2022
• Subjects: Adaptation models; damage recovery; Evolutionary robotics; Legged locomotion; Neural networks; neuro-simulation; Process control; Training; Training data
• DOI: 10.1109/CEC55065.2022.9870204

Bootstrapped Neuro-Simulation is a technique in which a Neural Network Simulator, used for the evaluation of controllers during the Evolutionary Robotics process, is trained concurrently with the evolution of the controllers themselves. This removes the need for creating a simulator before commencing controller evolution and results in a simulator that is not only tailored specifically to the robot being used, but also to the task that the robot is expected to perform. This paper demonstrates that Bootstrapped Neuro-Simulation can also be used for damage recovery since the Neural Network Simulator adapts to physical changes to the robot and enables the evolution of controllers that utilize the undamaged components of the robot. Limbs of a hexapod robot are disabled to simulate damage in the experiments described in this paper. Various adaptations to the Bootstrapped Neuro-Simulation algorithm are investigated in simulation. A real-world robot is used to demonstrate the successful recovery from damage and to illustrate situations where the adaptations were found to be beneficial.