Planning, Execution, and Adaptation for Multi-Robot Systems using Probabilistic and Temporal Planning

Yaniel Carreno, Jun Hao Alvin Ng, Yvan Petillot, Ronald P. A. Petrick

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Planning for multi-robot coordination during long horizon missions in complex environments need to consider resources, temporal constraints, and uncertainty. This could be computationally expensive and impractical for online planning and execution. We propose a decoupled framework to address this. At the high-level, we plan for multi-robot missions that require coordination amongst robots considering temporal and numeric constraints. The temporal plan is decomposed into low-level plans for individual robots. At the low-level, we perform online learning and adaptation due to unexpected probabilistic outcomes to achieve mission goals. Our framework learns over time to improve the performance by (1) updating the learned domain model to reduce model prediction errors and (2) constraining the robot's capabilities which in turn improves goal allocation. The approach provides a solution to planning problems that require long-term robot operability. We demonstrate the performance of our approach via experiments involving a fleet of heterogeneous robots.
Original languageEnglish
Title of host publicationAAMAS '22: Proceedings of the 21st International Conference on Autonomous Agents and Multiagent Systems
EditorsP. Faliszewski, V. Mascardi, C. Pelachaud, M. E. Taylor
PublisherInternational Foundation for Autonomous Agents and Multiagent Systems
Pages217-225
Number of pages9
ISBN (Print)9781450392136
Publication statusPublished - 9 May 2022
Event21st International Conference on Autonomous Agents and Multiagent Systems 2022 - Auckland, New Zealand
Duration: 9 May 202213 May 2022

Conference

Conference21st International Conference on Autonomous Agents and Multiagent Systems 2022
Abbreviated titleAAMAS 2022
Country/TerritoryNew Zealand
CityAuckland
Period9/05/2213/05/22

Keywords

  • Model-Based Reinforcement Learning
  • Multi-Agent Planning
  • Multi-Robot Systems
  • Temporal Planning

ASJC Scopus subject areas

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering

Fingerprint

Dive into the research topics of 'Planning, Execution, and Adaptation for Multi-Robot Systems using Probabilistic and Temporal Planning'. Together they form a unique fingerprint.

Cite this