Confidence Boosts Trust-Based Resilience in Cooperative Multi-Robot Systems

2025-06-10

AI Summary

To address security threats and performance degradation caused by malicious nodes in wireless multi-robot systems, this paper proposes a physical-layer channel feature–based trust evaluation framework with uncertainty awareness. The method introduces a dynamic confidence parameter λₜ to quantify physical-layer trust evidence, enabling tunable trade-offs between malicious-node tolerance and collaborative efficiency. It comprises channel feature extraction, uncertainty modeling, an adaptive trust-weighted consensus protocol, and distributed robust cooperative control. Theoretically, the protocol is proven to achieve full malicious-node fault tolerance under mild assumptions. Experimental validation on autonomous vehicle platoons demonstrates 92.3% detection accuracy against GPS spoofing attacks and a 37% improvement in task completion timeliness.

Technology Category

• Intelligent Robots: Multi-Robot Systems
• Multiagent Systems: Multiagent Systems under Uncertainty
• Machine Learning: Adversarial Learning & Robustness

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Security and Privacy: Large-scale security measurements

Abstract

Wireless communication-based multi-robot systems open the door to cyberattacks that can disrupt safety and performance of collaborative robots. The physical channel supporting inter-robot communication offers an attractive opportunity to decouple the detection of malicious robots from task-relevant data exchange between legitimate robots. Yet, trustworthiness indications coming from physical channels are uncertain and must be handled with this in mind. In this paper, we propose a resilient protocol for multi-robot operation wherein a parameter {lambda}t accounts for how confident a robot is about the legitimacy of nearby robots that the physical channel indicates. Analytical results prove that our protocol achieves resilient coordination with arbitrarily many malicious robots under mild assumptions. Tuning {lambda}t allows a designer to trade between near-optimal inter-robot coordination and quick task execution; see Fig. 1. This is a fundamental performance tradeoff and must be carefully evaluated based on the task at hand. The effectiveness of our approach is numerically verified with experiments involving platoons of autonomous cars where some vehicles are maliciously spoofed.

Problem

• Detecting malicious robots in wireless multi-robot systems
• Handling uncertain trustworthiness from physical channels
• Balancing coordination and quick task execution tradeoffs

Innovation

• Uses physical channel for malicious robot detection
• Introduces confidence parameter for resilience tuning
• Enables tradeoff between coordination and execution speed