Efficient Local-to-Global Collaborative Perception via Joint Communication and Computation Optimization

2026-01-19

AI Summary

This work addresses the high communication overhead and escalating computational latency in cooperative perception systems, which worsen as the number of connected vehicles increases. To mitigate these challenges, the authors propose a Local-to-Global Cooperative Perception (LGCP) framework that partitions roadways into non-overlapping regions, each assigned to a designated group of vehicles for localized sensing. A group leader fuses local observations and transmits the compact representation to a roadside unit, which then aggregates inputs from all regions and broadcasts a global perception update. LGCP uniquely integrates spatial region grouping with centralized scheduling, significantly reducing both communication and computational loads while maintaining or even enhancing perception accuracy. Experimental results demonstrate that LGCP achieves comparable or superior perception performance to existing methods while reducing data transmission by 97.7% on average—equivalent to a 44-fold decrease.

Technology Category

• Planning, Routing, and Scheduling: Optimization of Spatio-temporal Systems
• Computer Vision: Learning & Optimization for CV
• Intelligent Robots: Multimodal Perception & Sensor Fusion

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Federated Web and WoT systems, including distributed, federated and edge-based data processing
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web
• Security and Privacy: Large-scale security measurements

Abstract

Autonomous driving relies on accurate perception to ensure safe driving. Collaborative perception improves accuracy by mitigating the sensing limitations of individual vehicles, such as limited perception range and occlusion-induced blind spots. However, collaborative perception often suffers from high communication overhead due to redundant data transmission, as well as increasing computation latency caused by excessive load with growing connected and autonomous vehicles (CAVs) participation. To address these challenges, we propose a novel local-to-global collaborative perception framework (LGCP) to achieve collaboration in a communication- and computation-efficient manner. The road of interest is partitioned into non-overlapping areas, each of which is assigned a dedicated CAV group to perform localized perception. A designated leader in each group collects and fuses perception data from its members, and uploads the perception result to the roadside unit (RSU), establishing a link between local perception and global awareness. The RSU aggregates perception results from all groups and broadcasts a global view to all CAVs. LGCP employs a centralized scheduling strategy via the RSU, which assigns CAV groups to each area, schedules their transmissions, aggregates area-level local perception results, and propagates the global view to all CAVs. Experimental results demonstrate that the proposed LGCP framework achieves an average 44 times reduction in the amount of data transmission, while maintaining or even improving the overall collaborative performance.

Problem

• collaborative perception
• communication overhead
• computation latency
• autonomous driving
• connected vehicles

Innovation

• collaborative perception
• communication-computation co-optimization
• local-to-global framework
• connected autonomous vehicles
• roadside unit scheduling