A Model for Optimal Resilient Planning Subject to Fallible Actuators
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866913356718276608 |
|---|---|
| author | Baldes, Kyle Chaudhuri, Diptanil O'Kane, Jason M. Shell, Dylan A. |
| author_facet | Baldes, Kyle Chaudhuri, Diptanil O'Kane, Jason M. Shell, Dylan A. |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2405_11402 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | A Model for Optimal Resilient Planning Subject to Fallible Actuators Baldes, Kyle Chaudhuri, Diptanil O'Kane, Jason M. Shell, Dylan A. Robotics Artificial Intelligence 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. |
| title | A Model for Optimal Resilient Planning Subject to Fallible Actuators |
| topic | Robotics Artificial Intelligence |
| url | https://arxiv.org/abs/2405.11402 |