Scout-Assisted Planning for Heterogeneous Robot Teams under Partially Known Environments

2026-05-21

AI Summary

This work addresses the high navigation cost incurred by ground robots in partially known environments due to frequent backtracking caused by path blockages. To mitigate this, the authors propose a reconnaissance-assisted planning framework that leverages an aerial drone for active environmental scouting to inform and optimize the ground robot’s path planning. The approach introduces three key innovations: a novel information-gain-based action pruning mechanism, an efficient belief-state prediction module powered by graph neural networks, and a heterogeneous multi-robot collaborative planning architecture. Experimental results demonstrate that the proposed method reduces the ground robot’s traversal cost by 31.9%–37.7% compared to the Canadian Traveler Problem baseline and achieves an additional performance gain of 8%–14% over a nearest-neighbor heuristic reconnaissance strategy.

Abstract

Autonomous robot teams navigating partially known environments face costly backtracking when ground robots encounter blocked roads that are only revealed upon physical traversal. We address this with Scout-Assisted Planning, a heterogeneous planning framework in which scouting Unmanned Aerial Vehicles proactively gather environmental information to improve Unmanned Ground Vehicle navigation. To focus scouting on the most consequential edges, we propose Information Gain-based Action Pruning, which scores candidate scouting actions by their expected impact on ground robot behavior. Since exact Information Gain-based Action Pruning computation is prohibitively expensive, we develop a Graph Neural Network based model that predicts information gain values directly from graph structure and belief state, reducing planning time to real-time levels without sacrificing solution quality. Experiments across three environment types show that SAP with Information Gain Action Pruning reduces ground robot travel cost by 31.9--37.7% over the Canadian Traveler Problem baseline, and outperforms proximity-based scouting guidance by an additional 8--14%, confirming that principled information-gain-guided scouting is both more effective and computationally feasible for real-world deployment

Problem

• heterogeneous robot teams
• partially known environments
• costly backtracking
• blocked roads
• autonomous navigation

Innovation

• Scout-Assisted Planning
• Information Gain-based Action Pruning
• Graph Neural Network
• Heterogeneous Robot Teams
• Partially Known Environments