Vehicle edge cooperation cuts sensor data for safer remote driving
Case for Vehicle-Edge Collaborative Multi-Sensor Data Fusion for Autonomous Vehicle Teleoperation
Networking and Internet Architecture
Summary
Remote drivers help control self-driving cars when the cars face tricky situations. These drivers usually watch compressed video, which misses important 3D details needed for safety. The authors designed a system named SHARDED that sends smarter summaries of camera and LiDAR data from cars to nearby computing centers, instead of full raw data. This reduces the amount of data sent by up to half while still keeping good 3D understanding and reducing delays caused by unstable networks.
What this means in practice
- •For autonomous vehicle operators: Improve remote driving safety by sending efficient combined sensor data with reduced delays over 5G networks.
- •For edge computing providers: Support collaborative processing of vehicle sensor features to cut uplink data use while maintaining 3D perception quality.
Authors
Qixin Zhang, Ajay Kumar Gurumadaiah, Wei Ye, Eman Ramadan, Zhi-Li Zhang
Abstract
Teleoperation provides a critical safety fallback when autonomous vehicles (AVs) encounter scenarios that are outside their operational design domain. In practice, however, remote operators rely primarily on compressed camera streams over 5G, which often lack depth and spatial geometric cues for safe operation in complex dynamic environments. While multi-sensor fusion can enhance situational awareness, directly transmitting raw camera and LiDAR data is impractical due to 5G uplink bandwidth and latency constraints. In this paper, we propose SHARDED, a collaborative camera-LiDAR perception framework that deploys a feature-level fusion pipeline across the vehicle and edge to reduce uplink traffic while preserving 3D detection and depth estimation accuracy. We further design two complementary mechanisms for SHARDED: (i) A network-aware adaptive feature transmission mechanism that reduces data traffic by 50% on average (peaking at over 95%) compared to raw sensor data, and (ii) a latency-aware positional drift compensation mechanism to mitigate cross-modal misalignment induced by unstable network conditions. Evaluations on the nuScenes dataset and real-world 5G measurement traces show that SHARDED achieves competitive perception quality while reducing uplink bandwidth consumption and end-to-end latency.