Interruption-Aware Cooperative Perception for V2X Communication-Aided Autonomous Driving
Preprint
Abstract
Cooperative perception can significantly improve the perception performance of autonomous vehicles beyond the limited perception ability of individual vehicles by exchanging information with neighbor agents through V2X communication. However, most existing work assume ideal communication among agents, ignoring the significant and common \textit{interruption issues} caused by imperfect V2X communication, where cooperation agents can not receive cooperative messages successfully and thus fail to achieve cooperative perception, leading to safety risks. To fully reap the benefits of cooperative perception in practice, we propose V2X communication INterruption-aware COoperative Perception (V2X-INCOP), a cooperative perception system robust to communication interruption for V2X communication-aided autonomous driving, which leverages historical cooperation information to recover missing information due to the interruptions and alleviate the impact of the interruption issue. To achieve comprehensive recovery, we design a communication-adaptive multi-scale spatial-temporal prediction model to extract multi-scale spatial-temporal features based on V2X communication conditions and capture the most significant information for the prediction of the missing information. To further improve recovery performance, we adopt a knowledge distillation framework to give explicit and direct supervision to the prediction model and a curriculum learning strategy to stabilize the training of the model. Experiments on three public cooperative perception datasets demonstrate that the proposed method is effective in alleviating the impacts of communication interruption on cooperative perception.Keywords
All Related Versions
This publication has 28 references indexed in Scilit:
- MADE: Malicious Agent Detection for Robust Multi-Agent Collaborative Perception2024
- V2X-Sim: Multi-Agent Collaborative Perception Dataset and Benchmark for Autonomous DrivingIEEE Robotics and Automation Letters, 2022
- Keypoints-Based Deep Feature Fusion for Cooperative Vehicle Detection of Autonomous DrivingIEEE Robotics and Automation Letters, 2022
- Fast and Robust Registration of Partially Overlapping Point CloudsIEEE Robotics and Automation Letters, 2021
- Beam-Based Mobility Management in 5G Millimetre Wave V2X Communications: A Survey and OutlookIEEE Open Journal of Intelligent Transportation Systems, 2021
- DistributedH∞ Controller Design and Robustness Analysis for Vehicle Platooning Under Random Packet DropIEEE Transactions on Intelligent Transportation Systems, 2020
- 3D Point Cloud Processing and Learning for Autonomous Driving: Impacting Map Creation, Localization, and PerceptionIEEE Signal Processing Magazine, 2020
- Challenges and Solutions for Cellular Based V2X CommunicationsIEEE Communications Surveys & Tutorials, 2020
- A Survey on 3D Object Detection Methods for Autonomous Driving ApplicationsIEEE Transactions on Intelligent Transportation Systems, 2019
- Data-Driven Intelligent Transportation Systems: A SurveyIEEE Transactions on Intelligent Transportation Systems, 2011