Select2Drive: Pragmatic Communications for Real-Time Collaborative Autonomous Driving

TL;DR

Select2Drive introduces a resource-efficient, predictive, and importance-based communication framework for real-time collaborative autonomous driving, improving perception accuracy and driving performance under bandwidth constraints.

Contribution

The paper proposes Select2Drive, a novel framework that optimizes resource use in collaborative driving through distributed prediction and importance-based communication.

Findings

Achieves 2.60% and 1.99% improvements in perception accuracy under bandwidth constraints.

Enhances closed-loop driving scores by up to 8.35%.

Improves route completion rates in dense traffic scenarios.

Abstract

Vehicle-to-everything communications-assisted autonomous driving has witnessed remarkable advancements in recent years, with pragmatic communications (PragComm) emerging as a promising paradigm for real-time collaboration among vehicles and other agents. Simultaneously, extensive research has explored the interplay between collaborative perception and decision-making in end-to-end driving frameworks. In this work, we revisit the collaborative driving problem and propose the Select2Drive framework to optimize the utilization of limited computational and communication resources. Particularly, to mitigate cumulative latency in perception and decision-making, Select2Drive introduces distributed predictive perception by formulating an active prediction paradigm and simplifying high-dimensional semantic feature prediction into a computation cost-efficient, motion-aware reconstruction. Given the ``less is more" principle that an over-broadened perceptual horizon possibly confuses the decision module rather than contributing to it, Select2Drive utilizes area-of-importance-based PragComm to prioritize the communications of critical regions, thus boosting both communication efficiency and decision-making efficacy. Empirical evaluations on the V2Xverse and real-world DAIR-V2X demonstrate that Select2Drive achieves a $2.60$\% and $1.99$\% improvement in offline perception tasks under limited bandwidth (resp., pose error conditions). Moreover, it delivers at most $8.35$\% and $2.65$\% enhancement in closed-loop driving scores and route completion rates, particularly in scenarios characterized by dense traffic and high-speed dynamics.