Multi-Objective Policy Generation for Mobile Robots under Probabilistic Time-Bounded Guarantees

Authors

  • Bruno Lacerda School of Computer Science University of Birmingham
  • David Parker School of Computer Science University of Birmingham
  • Nick Hawes School of Computer Science University of Birmingham

Abstract

We present a methodology for the generation of mobile robot controllers which offer probabilistic time-bounded guarantees on successful task completion, whilst also trying to satisfy soft goals. The approach is based on a stochastic model of the robot’s environment and action execution times, a set of soft goals, and a formal task specification in co-safe linear temporal logic, which are analysed using multi-objective model checking techniques for Markov decision processes. For efficiency, we propose a novel two-step approach. First, we explore policies on the Pareto front for minimising expected task execution time whilst optimising the achievement of soft goals. Then, we use this to prune a model with more detailed timing information, yielding a time-dependent policy for which more fine-grained probabilistic guarantees can be provided. We illustrate and evaluate the generation of policies on a delivery task in a care home scenario, where the robot also tries to engage in entertainment activities with the patients.

Downloads

Published

2017-06-05

How to Cite

Lacerda, B., Parker, D., & Hawes, N. (2017). Multi-Objective Policy Generation for Mobile Robots under Probabilistic Time-Bounded Guarantees. Proceedings of the International Conference on Automated Planning and Scheduling, 27(1), 504-512. Retrieved from https://ojs.aaai.org/index.php/ICAPS/article/view/13865