A Model for Optimal Resilient Planning Subject to Fallible Actuators

TL;DR

This paper develops a planning model within the Markov Decision Processes framework that enables robots to adapt their strategies proactively to actuator failures, ensuring goal attainment despite component malfunctions.

Contribution

It introduces a novel MDP-based model that accounts for actuator failure probabilities and enables resilient planning with computational reuse strategies.

Findings

Strategic planning improves robot resilience to actuator failures.

Reusing computations reduces planning complexity.

Robots can schedule actuator use to preserve critical components.

Abstract

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.