Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees
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...
| Main Authors: | , , |
|---|---|
| Format: | Conference item |
| Published: |
AAAI Press
2017
|
| _version_ | 1797064686116536320 |
|---|---|
| author | Lacerda, B Parker, D Hawes, N |
| author_facet | Lacerda, B Parker, D Hawes, N |
| author_sort | Lacerda, B |
| collection | OXFORD |
| description | 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. |
| first_indexed | 2024-03-06T21:17:52Z |
| format | Conference item |
| id | oxford-uuid:40683525-e63e-46d9-a5bf-0b4d1a55d152 |
| institution | University of Oxford |
| last_indexed | 2024-03-06T21:17:52Z |
| publishDate | 2017 |
| publisher | AAAI Press |
| record_format | dspace |
| spelling | oxford-uuid:40683525-e63e-46d9-a5bf-0b4d1a55d1522022-03-26T14:37:45ZMulti-objective policy generation for mobile robots under probabilistic time-bounded guaranteesConference itemhttp://purl.org/coar/resource_type/c_5794uuid:40683525-e63e-46d9-a5bf-0b4d1a55d152Symplectic Elements at OxfordAAAI Press2017Lacerda, BParker, DHawes, NWe 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. |
| spellingShingle | Lacerda, B Parker, D Hawes, N Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees |
| title | Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees |
| title_full | Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees |
| title_fullStr | Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees |
| title_full_unstemmed | Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees |
| title_short | Multi-objective policy generation for mobile robots under probabilistic time-bounded guarantees |
| title_sort | multi objective policy generation for mobile robots under probabilistic time bounded guarantees |
| work_keys_str_mv | AT lacerdab multiobjectivepolicygenerationformobilerobotsunderprobabilistictimeboundedguarantees AT parkerd multiobjectivepolicygenerationformobilerobotsunderprobabilistictimeboundedguarantees AT hawesn multiobjectivepolicygenerationformobilerobotsunderprobabilistictimeboundedguarantees |