2020/11/02 by Yousef Emam, Gennaro Notomista, Emam, Yousef +5 · 1 citation
Engineering · Computer Science · #Advanced Control Systems Optimization #Reinforcement Learning in Robotics #Gaussian Processes and Bayesian Inference
paper · pdf · doi:10.48550/arxiv.2011.01164
Multi-robot task allocation is a ubiquitous problem in robotics due to its\napplicability in a variety of scenarios. Adaptive task-allocation algorithms\naccount for unknown disturbances and unpredicted phenomena in the environment\nwhere robots are deployed to execute tasks. However, this adaptivity typically\ncomes at the cost of requiring precise knowledge of robot models in order to\nevaluate the allocation effectiveness and to adjust the task assignment online.\nAs such, environmental disturbances can significantly degrade the accuracy of\nthe models which in turn negatively affects the quality of the task allocation.\nIn this paper, we leverage Gaussian processes, differential inclusions, and\nrobust control barrier functions to learn environmental disturbances in order\nto guarantee robust task execution. We show the implementation and the\neffectiveness of the proposed framework on a real multi-robot system.\n