Cooperative perception enabled by V2X Communication technologies can
significantly improve the perception performance of autonomous vehicles beyond
the limited perception ability of the individual vehicles, therefore, improving
the safety and efficiency of autonomous driving in intelligent transportation
systems. However, in order to fully reap the benefits of cooperative perception
in practice, the impacts of imperfect V2X communication, i.e., communication
errors and disruptions, need to be understood and effective remedies need to be
developed to alleviate their adverse impacts. Motivated by this need, we
propose a novel INterruption-aware robust COoperative Perception (V2X-INCOP)
solution for V2X communication-aided autonomous driving, which leverages
historical information to recover missing information due to interruption. 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
direct supervision to the prediction model and a curriculum learning strategy
to stabilize the training of the model. Our experiments on three public
cooperative perception datasets demonstrate that our proposed method is
effective in alleviating the impacts of communication interruption on
cooperative perception.

本研究提出了一种基于历史信息的 V2X-INCOP 方案，利用通信自适应多尺度时空预测模型来提取多尺度时空特征、捕捉最显著的信息以预测遗漏的信息，同时采用知识蒸馏框架和课程学习策略来稳定模型训练，实验表明该方法能够有效缓解通信中断对合作感知的影响。