Intent-based Deep Reinforcement Learning for Multi-agent Informative Path Planning
Authors:
- 4 December 2023
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 71-77
Abstract
In multi-agent informative path planning (MAIPP), agents must collectively construct a global belief map of an underlying distribution of interest (e.g., gas concentration, light intensity, or pollution levels) over a given domain, based on measurements taken along their trajectory. They must frequently replan their path to balance the exploration of new areas with the exploitation of known high-interest areas, to maximize information gain within a predefined budget. Traditional approaches rely on reactive path planning conditioned on other agents’ predicted future actions. However, as the belief is continuously updated, the predicted actions may not match the executed actions, introducing noise and reducing performance. We propose a decentralized, deep reinforcement learning (DRL) approach using an attention-based neural network, where agents optimize long-term individual and cooperative objectives by sharing their intent, represented as a distribution of medium-/long-term future positions obtained from their own policy. Intent sharing enables agents to learn to claim or avoid broader areas, while the use of attention mechanisms allows them to identify useful portions of imperfect predictions, maximizing cooperation even based on imperfect information. Our experiments compare the performance of our approach, its variants, and high-quality baselines across various MAIPP scenarios. We finally demonstrate the effectiveness of our approach under limited communication ranges, towards deployments under realistic communication constraints.Keywords
All Related Versions
This publication has 19 references indexed in Scilit:
- Adaptive continuous‐space informative path planning for online environmental monitoringJournal of Field Robotics, 2017
- Decentralized multi-agent exploration with online-learning of Gaussian processes2016
- Adaptive informative path planning in metric spacesThe International Journal of Robotics Research, 2015
- Path planning for surface inspection on a robot-based scanning system2015
- Sampling-based robotic information gathering algorithmsThe International Journal of Robotics Research, 2014
- Bayesian Optimisation for informative continuous path planning2014
- Branch and bound for informative path planning2012
- Robots for Environmental Monitoring: Significant Advancements and ApplicationsIEEE Robotics & Automation Magazine, 2012
- Multi-Robot Search and Rescue: A Potential Field Based Approach2007
- Long Short-Term MemoryNeural Computation, 1997