📄 中文摘要
协作感知使自主智能体能够通过无线通信共享编码表示，从而增强彼此的实时情境感知。然而，有限的通信带宽与丰富的传感器信息之间的矛盾阻碍了其实际应用。近期研究探索了选择策略，仅共享每帧的一部分特征，同时努力保持性能水平。然而，带宽需求仍然对当前无线技术造成压力。为根本缓解这一矛盾，研究采用主动方法，利用时间连续性识别捕捉环境动态的特征，避免重复和冗余地传输静态信息。
COOPERTRIM: 适应性数据选择用于不确定性感知的协作感知
📄 English Summary
COOPERTRIM: Adaptive Data Selection for Uncertainty-Aware Cooperative Perception
Cooperative perception enables autonomous agents to share encoded representations over wireless communication, enhancing each other's real-time situational awareness. However, the conflict between limited communication bandwidth and rich sensor information hinders practical deployment. Recent studies have explored selection strategies that share only a subset of features per frame while striving to maintain performance levels. Nevertheless, the bandwidth requirements continue to stress current wireless technologies. To fundamentally alleviate this tension, a proactive approach is taken, leveraging temporal continuity to identify features that capture environmental dynamics while avoiding repetitive and redundant transmission of static information.