Time-Bounded Mission Planning in Time-Varying Domains with Semi-MDPs and Gaussian Processes

Paul Duckworth, Bruno Lacerda, Nick Hawes
Proceedings of the 2020 Conference on Robot Learning, PMLR 155:1654-1668, 2021.

Abstract

Uncertain, time-varying dynamic environments are ubiquitous in real world robotics. We propose an online planning framework to address time-bounded missions under time-varying dynamics, where those dynamics affect the duration and outcome of actions. We pose such problems as semi-Markov decision processes, where actions have a duration distributed according to an a priori unknown time-varying function. Our approach maintains a belief over this function, and time is propagated through a discrete search tree that efficiently maintains a subset of reachable states. We show improved mission performance on a marine vehicle simulator acting under real-world spatio-temporal ocean currents, and demonstrate the ability to solve co-safe linear temporal logic problems, which are more complex than the reachability problems tackled in previous approaches.

Cite this Paper


BibTeX
@InProceedings{pmlr-v155-duckworth21a, title = {Time-Bounded Mission Planning in Time-Varying Domains with Semi-MDPs and Gaussian Processes}, author = {Duckworth, Paul and Lacerda, Bruno and Hawes, Nick}, booktitle = {Proceedings of the 2020 Conference on Robot Learning}, pages = {1654--1668}, year = {2021}, editor = {Kober, Jens and Ramos, Fabio and Tomlin, Claire}, volume = {155}, series = {Proceedings of Machine Learning Research}, month = {16--18 Nov}, publisher = {PMLR}, pdf = {https://proceedings.mlr.press/v155/duckworth21a/duckworth21a.pdf}, url = {https://proceedings.mlr.press/v155/duckworth21a.html}, abstract = {Uncertain, time-varying dynamic environments are ubiquitous in real world robotics. We propose an online planning framework to address time-bounded missions under time-varying dynamics, where those dynamics affect the duration and outcome of actions. We pose such problems as semi-Markov decision processes, where actions have a duration distributed according to an a priori unknown time-varying function. Our approach maintains a belief over this function, and time is propagated through a discrete search tree that efficiently maintains a subset of reachable states. We show improved mission performance on a marine vehicle simulator acting under real-world spatio-temporal ocean currents, and demonstrate the ability to solve co-safe linear temporal logic problems, which are more complex than the reachability problems tackled in previous approaches.} }
Endnote
%0 Conference Paper %T Time-Bounded Mission Planning in Time-Varying Domains with Semi-MDPs and Gaussian Processes %A Paul Duckworth %A Bruno Lacerda %A Nick Hawes %B Proceedings of the 2020 Conference on Robot Learning %C Proceedings of Machine Learning Research %D 2021 %E Jens Kober %E Fabio Ramos %E Claire Tomlin %F pmlr-v155-duckworth21a %I PMLR %P 1654--1668 %U https://proceedings.mlr.press/v155/duckworth21a.html %V 155 %X Uncertain, time-varying dynamic environments are ubiquitous in real world robotics. We propose an online planning framework to address time-bounded missions under time-varying dynamics, where those dynamics affect the duration and outcome of actions. We pose such problems as semi-Markov decision processes, where actions have a duration distributed according to an a priori unknown time-varying function. Our approach maintains a belief over this function, and time is propagated through a discrete search tree that efficiently maintains a subset of reachable states. We show improved mission performance on a marine vehicle simulator acting under real-world spatio-temporal ocean currents, and demonstrate the ability to solve co-safe linear temporal logic problems, which are more complex than the reachability problems tackled in previous approaches.
APA
Duckworth, P., Lacerda, B. & Hawes, N.. (2021). Time-Bounded Mission Planning in Time-Varying Domains with Semi-MDPs and Gaussian Processes. Proceedings of the 2020 Conference on Robot Learning, in Proceedings of Machine Learning Research 155:1654-1668 Available from https://proceedings.mlr.press/v155/duckworth21a.html.

Related Material