Near-Optimal Multi-Agent Learning for Safe Coverage Control

by   Manish Prajapat, et al.

In multi-agent coverage control problems, agents navigate their environment to reach locations that maximize the coverage of some density. In practice, the density is rarely known a priori, further complicating the original NP-hard problem. Moreover, in many applications, agents cannot visit arbitrary locations due to a priori unknown safety constraints. In this paper, we aim to efficiently learn the density to approximately solve the coverage problem while preserving the agents' safety. We first propose a conditionally linear submodular coverage function that facilitates theoretical analysis. Utilizing this structure, we develop MacOpt, a novel algorithm that efficiently trades off the exploration-exploitation dilemma due to partial observability, and show that it achieves sublinear regret. Next, we extend results on single-agent safe exploration to our multi-agent setting and propose SafeMac for safe coverage and exploration. We analyze SafeMac and give first of its kind results: near optimal coverage in finite time while provably guaranteeing safety. We extensively evaluate our algorithms on synthetic and real problems, including a bio-diversity monitoring task under safety constraints, where SafeMac outperforms competing methods.


page 2

page 5

page 8


Multi-Agent Coverage in Urban Environments

We study multi-agent coverage algorithms for autonomous monitoring and p...

MACE: Multi-Agent Autonomous Collaborative Exploration of Unknown Environments

In this paper, we propose a new framework for multi-agent collaborative ...

Time-Efficient Mars Exploration of Simultaneous Coverage and Charging with Multiple Drones

This paper presents a time-efficient scheme for Mars exploration by the ...

Decentralized Multi-Agent Linear Bandits with Safety Constraints

We study decentralized stochastic linear bandits, where a network of N a...

Provably Learning Nash Policies in Constrained Markov Potential Games

Multi-agent reinforcement learning (MARL) addresses sequential decision-...

Near-optimal irrevocable sample selection for periodic data streams with applications to marine robotics

We consider the task of monitoring spatiotemporal phenomena in real-time...

Please sign up or login with your details

Forgot password? Click here to reset