Energy-Aware Informative Path Planning for Heterogeneous Multi-Robot Systems
Aiman Munir, Ayan Dutta, Ramviyas Parasuraman
AI summary
Problem
Existing multi-robot path planning methods typically assume unlimited energy and uniform robot capabilities, making them inefficient and prone to premature mission failure in long-term, large-scale deployments with heterogeneous teams.
Approach
The authors introduce EA-MIPP, a distributed controller that continuously adjusts each robot's sampling targets and navigation goals by weighing its current energy level against spatial prediction uncertainty, enabling smooth role transitions.
Key results
- Dynamically adapts exploration-exploitation tradeoffs using real-time energy and uncertainty thresholds
- Achieves up to 32% energy savings while maintaining high Gaussian Process reconstruction accuracy
- Enables persistent operations through optimized recharging station assignment and smooth state transitions
- Hardware experiments closely match simulation results, validating real-world deployment readiness
Why it matters
Enables longer-lasting, energy-efficient multi-robot missions for critical large-scale applications like environmental monitoring and precision agriculture where robot capabilities and power constraints vary.
Abstract
Effective energy management is essential for max- imizing information gathering tasks with networked mobile robots, particularly for large-scale, energy-intensive tasks such as agricultural monitoring and wildfire mapping. This paper presents a novel framework that integrates robots’ energy profiles with confidence bounds of their assigned regions to optimize sampling targets. Designed for persistent, long-term deployments, the framework employs Gaussian Process Re- gression (GPR) to maximize data acquisition and accurately reconstruct unknown spatial distributions (e.g., algae outbreaks or humidity maps). The method enables seamless transitions among exploration (mapping uncertain regions at high energy), exploitation (refining maps at moderate energy levels), and recharging (navigating to charging stations at low energy), thereby achieving energy-balanced informative path planning. Experiments demonstrate the effectiveness of the approach against state-of-the-art methods in generating energy-efficient and distinct paths for heterogeneous robots, delivering up to 32% energy savings while maintaining high reconstruction accuracy. Hardware experiments closely matched the perfor- mance in simulation.