Agentic LinkDreamer improves vehicle perception during V2X outages
Agentic LinkDreamer: Adaptive Neuro-Fuzzy World-Model Decision Making for Intermittent V2X Cooperative Perception
Networking and Internet Architecture
Summary
Vehicles share information to better detect objects around them, but communication can sometimes break, causing gaps in the shared data. The authors propose Agentic LinkDreamer, a smart system that predicts and decides how to handle missing information during these communication breaks. It uses memory of past data and a flexible decision process to balance safety, communication needs, and delays, improving detection accuracy even when data links are unreliable. This approach helps vehicles maintain good awareness with less constant data exchange.
What this means in practice
- •For automotive development teams: Enhance autonomous vehicle perception systems to maintain accuracy despite intermittent V2X communication outages using adaptive prediction and decision strategies.
- •For smart city infrastructure planners: Design V2X communication protocols that integrate adaptive feature prediction to improve road safety when vehicle communications degrade unpredictably.
Authors
Zhaoyu Liu, Dongmin Wang, Liu Cao, Jijing Cai, Kai Fang, Syed Ishtiaque Ahmed, Almetwally M. Mostafa
Abstract
Intermittent vehicle-to-everything (V2X) communication can remove collaborator information needed for cooperative perception, degrading object detection during link outages. Existing recovery methods reconstruct missing features but rarely determine when to trust predictions, reuse historical observations, or request fresh information. This paper proposes Agentic LinkDreamer, a soft-computing framework integrating a latent world model with an interpretable neuro-fuzzy decision agent. It maintains causal collaborator memory and uses a relative-motion-conditioned recurrent world model to predict unavailable bird's-eye-view (BEV) features. Prediction uncertainty, perceptual complementarity, memory freshness, communication quality, and residual communication budget form a compact decision state. A differentiable Takagi-Sugeno controller selects among five modes: ego-only perception, motion-compensated historical feature reuse, latent imagination, low-rate temporal-summary refresh, and high-rate collaborator-feature refresh. The policy balances detection risk, communication overhead, latency, predictive uncertainty, and action switching. After link recovery, reflection compares predicted and received features to update uncertainty calibration and causal memory. For reproducible evaluation without assuming unavailable physical-layer traces, we construct a geometry-derived V2X degradation protocol using recorded trajectories and LiDAR-derived scene geometry from V2X-Real. On the real-world V2X-Real V2V split, Agentic LinkDreamer achieves 90.95 AP@0.5 on outage frames and recovers 92.9% of the cooperative-perception performance gap. At a high-performance operating point, it remains only 0.65 AP below the cooperative upper reference while reducing communication volume by approximately 31% relative to continuous high-rate cooperation. This improves resilience under V2X outages.