Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty

TL;DR

This paper introduces A2MAML, a novel multi-agent multimodal learning framework that models modality-specific uncertainty, actively selects reliable sensor data, and improves robustness in autonomous driving accident detection.

Contribution

A2MAML is the first approach to perform fine-grained, modality-level fusion with uncertainty modeling and active selection in multi-agent systems under uncertainty.

Findings

Achieves up to 18.7% higher accident detection rate.

Outperforms single-agent and collaborative baselines.

Supports asymmetric modality availability.

Abstract

Multi-agent systems are increasingly equipped with heterogeneous multimodal sensors, enabling richer perception but introducing modality-specific and agent-dependent uncertainty. Existing multi-agent collaboration frameworks typically reason at the agent level, assume homogeneous sensing, and handle uncertainty implicitly, limiting robustness under sensor corruption. We propose Active Asymmetric Multi-Agent Multimodal Learning under Uncertainty (A2MAML), a principled approach for uncertainty-aware, modality-level collaboration. A2MAML models each modality-specific feature as a stochastic estimate with uncertainty prediction, actively selects reliable agent-modality pairs, and aggregates information via Bayesian inverse-variance weighting. This formulation enables fine-grained, modality-level fusion, supports asymmetric modality availability, and provides a principled mechanism to suppress corrupted or noisy modalities. Extensive experiments on connected autonomous driving scenarios for collaborative accident detection demonstrate that A2MAML consistently outperforms both single-agent and collaborative baselines, achieving up to 18.7% higher accident detection rate.