A Model for Optimal Resilient Planning Subject to Fallible Actuators
This addresses the problem of resilient planning for robots in scenarios with fallible actuators, representing an incremental advance in domain-specific robotics.
The paper tackles the problem of planning for robots with actuators prone to failure by formulating it within the Markov Decision Processes framework, resulting in qualitatively different behaviors and strategic solutions such as scheduling utilization to reserve critical actuators.
Robots incurring component failures ought to adapt their behavior to best realize still-attainable goals under reduced capacity. We formulate the problem of planning with actuators known a priori to be susceptible to failure within the Markov Decision Processes (MDP) framework. The model captures utilization-driven malfunction and state-action dependent likelihoods of actuator failure in order to enable reasoning about potential impairment and the long-term implications of impoverished future control. This leads to behavior differing qualitatively from plans which ignore failure. As actuators malfunction, there are combinatorially many configurations which can arise. We identify opportunities to save computation through re-use, exploiting the observation that differing configurations yield closely related problems. Our results show how strategic solutions are obtained so robots can respond when failures do occur -- for instance, in prudently scheduling utilization in order to keep critical actuators in reserve.