Evolving Error Tolerance in Biologically-Inspired iAnt Robots

摘要

Evolutionary algorithms can adapt the behavior of individu-als to maximize the fitness of cooperative multi-agent teams. We use a genetic algorithm (GA) to optimize behavior in a team of simulated robots that mimic foraging ants, then trans-fer the evolved behaviors into physical iAnt robots. We in-troduce positional and resource detection error models into our simulation to characterize the empirically-measured sen-sor error in our physical robots. Physical and simulated robots that live in a world with error and use parameters adapted specifically for an error-prone world perform better than robots in the same error-prone world using parameters adapted for an error-free world. Additionally, teams of robots in error-adapted simulations collect resources at the same rate as the physical robots. Our approach extends state-of-the-art biologically-inspired robotics, evolving high-level behav-iors that are robust to sensor error and meaningful for phe-notypic analysis. This work demonstrates the utility of em-ploying evolutionary methods to optimize the performance of distributed robot teams in unknown environments.