Uncertainty-Aware Multi-Robot Task Allocation With Strongly Coupled Inter-Robot Rewards

2025-09-26

AI Summary

This paper addresses task allocation for heterogeneous robot teams operating under uncertain task requirements. We propose a decentralized collaborative allocation method that explicitly models inter-robot coupling rewards based on capability complementarity within a distributed framework, integrated with an uncertainty-aware mechanism to guide robots toward high-uncertainty tasks. Task requirements are represented as capability probability distributions, and allocation is optimized via a market-based algorithm enabling polynomial-time computation—suitable for communication-constrained environments. Our approach advances state-of-the-art by unifying capability-aware coupling, uncertainty-driven exploration, and computational efficiency in a decentralized setting. Experiments demonstrate significant improvements over baseline algorithms: +18.3% in task completion rate and +22.7% in resource utilization, while maintaining robust collaboration and resource efficiency under dynamic conditions.

Technology Category

Humans and AI: Planning and Decision Support for Human-Machine TeamsIntelligent Robots: Learning & Optimization for ROBConstraint Satisfaction and Optimization: Distributed CSP/Optimization

Application Category

Economics, Online Markets and Human Computation: Incentives in network design for Web infrastructures and ecosystemsResponsible Web: Human-perceived consequences of algorithmic deployment on the webGraph Algorithms and Modeling for the Web: Algorithms and analysis for incomplete, noisy, or partially observed Web-related graphs

Abstract

This paper proposes a task allocation algorithm for teams of heterogeneous robots in environments with uncertain task requirements. We model these requirements as probability distributions over capabilities and use this model to allocate tasks such that robots with complementary skills naturally position near uncertain tasks, proactively mitigating task failures without wasting resources. We introduce a market-based approach that optimizes the joint team objective while explicitly capturing coupled rewards between robots, offering a polynomial-time solution in decentralized settings with strict communication assumptions. Comparative experiments against benchmark algorithms demonstrate the effectiveness of our approach and highlight the challenges of incorporating coupled rewards in a decentralized formulation.

Problem

• Allocating tasks to heterogeneous robots with uncertain requirements
• Optimizing coupled rewards between robots in decentralized settings
• Proactively mitigating task failures while conserving robot resources

Innovation

• Uses probability distributions to model uncertain task requirements
• Employs market-based approach for optimizing team objectives
• Provides polynomial-time solution for decentralized robot allocation