Plug-and-Play Reweighting for Resilient Collaborative Decision-Making in Connected Autonomous Driving

2026-07-10

AI Summary

This work addresses the degradation in decision reliability caused by perceptual noise and adversarial attacks on cooperative agents in connected autonomous driving. To this end, the authors propose an attention-based encoder-decoder framework for collaborative perception and decision-making, augmented with a plug-and-play dynamic reweighting module. This module adaptively suppresses the influence of anomalous inputs by analyzing the consistency between neighboring points and local geometric structures via local median consensus, and can be seamlessly integrated into existing attention architectures without requiring retraining. In high-fidelity simulations involving five types of adversarial attacks and perceptual noise, the proposed method achieves up to a 26% performance improvement over the state-of-the-art in accident-prone scenarios, significantly enhancing system robustness and resilience.

Abstract

Collaborative decision-making is a fundamental capability in multi-robot systems, such as connected autonomous vehicles. However, perceptual noise and adversarial attacks in collaborators can severely affect decision reliability. Overall, existing methods typically rely on retraining with attack-specific defenses or on restrictive perturbation assumptions to improve resilience, which limits their practicality. In this paper, we propose a novel Resilient Collaborative Decision-Making (RCDM) framework that consists of an attention-based encoder for extracting individual robot perceptual embeddings and an attention-based decoder for fusing collaborator perceptions and making decisions. To improve resilience to corrupted observations, we design a novel plug-and-play reweighting module that down-weights the influence of corrupted inputs by analyzing the consistency of neighborhood points relative to the local structure and assigning smaller weights to points that deviate strongly from the local median. This module can be seamlessly integrated into attention-based collaborative decision-making without requiring additional training. We evaluate our method in high-fidelity simulations, considering perceptual noise and five types of attacks across diverse accident-prone scenarios. Experimental results demonstrate that our approach consistently outperforms existing methods by up to 26% and achieves state-of-the-art resilient performance.

Problem

• collaborative decision-making
• perceptual noise
• adversarial attacks
• resilience
• connected autonomous driving

Innovation

• plug-and-play reweighting
• resilient collaborative decision-making
• attention-based fusion
• adversarial robustness
• connected autonomous driving