Extended Visibility of Autonomous Vehicles via Optimized Cooperative Perception under Imperfect Communication

2025-03-23

AI Summary

To address degraded individual perception performance of autonomous vehicles under adverse weather, complex road geometries, and dense traffic, this paper proposes a collaborative perception optimization framework under communication constraints. The method jointly models vehicle spatial positioning, visual field-of-view coverage, motion blur effects, and communication resource limitations—achieving, for the first time, multi-dimensional coupled optimization for collaborative perception networking. We design a power-channel joint adaptive allocation mechanism tailored for LTE/5G NR-V2X, enabling dynamic auxiliary vehicle selection and real-time resource scheduling. Evaluated on the CARLA platform via multi-vehicle collaborative perception simulations, the framework improves pedestrian detection accuracy by approximately 10% over baseline individual perception, significantly enhancing perceptual robustness and driving safety in challenging scenarios.

Technology Category

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

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Web performance, measurement, and characterization
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Responsible Web: Human-perceived consequences of algorithmic deployment on the web

Abstract

Autonomous Vehicles (AVs) rely on individual perception systems to navigate safely. However, these systems face significant challenges in adverse weather conditions, complex road geometries, and dense traffic scenarios. Cooperative Perception (CP) has emerged as a promising approach to extending the perception quality of AVs by jointly processing shared camera feeds and sensor readings across multiple vehicles. This work presents a novel CP framework designed to optimize vehicle selection and networking resource utilization under imperfect communications. Our optimized CP formation considers critical factors such as the helper vehicles' spatial position, visual range, motion blur, and available communication budgets. Furthermore, our resource optimization module allocates communication channels while adjusting power levels to maximize data flow efficiency between the ego and helper vehicles, considering realistic models of modern vehicular communication systems, such as LTE and 5G NR-V2X. We validate our approach through extensive experiments on pedestrian detection in challenging scenarios, using synthetic data generated by the CARLA simulator. The results demonstrate that our method significantly improves upon the perception quality of individual AVs with about 10% gain in detection accuracy. This substantial gain uncovers the unleashed potential of CP to enhance AV safety and performance in complex situations.

Problem

• Enhance AV perception via optimized cooperative systems
• Optimize vehicle selection and resource use in imperfect networks
• Improve detection accuracy in adverse conditions via CP

Innovation

• Optimized cooperative perception for AVs
• Dynamic vehicle selection and resource allocation
• Enhanced detection accuracy via CP