Search papers, labs, and topics across Lattice.
CooperDrive is a cooperative perception framework for autonomous vehicles that shares object-level Bird's-Eye View (BEV) features between vehicles to improve situational awareness in occluded and non-line-of-sight scenarios. By reusing detector BEV features for pose estimation and BEV reconstruction, CooperDrive achieves low-latency perception fusion without requiring heavy encoders. Real-world tests demonstrate that CooperDrive increases reaction lead time and safety margins while maintaining low bandwidth usage and end-to-end latency.
Sharing lightweight Bird's-Eye View features between autonomous vehicles slashes reaction times in occluded scenarios, turning reactive maneuvers into proactive safety.
Autonomous vehicles equipped with robust onboard perception, localization, and planning still face limitations in occlusion and non-line-of-sight (NLOS) scenarios, where delayed reactions can increase collision risk. We propose CooperDrive, a cooperative perception framework that augments situational awareness and enables earlier, safer driving decisions. CooperDrive offers two key advantages: (i) each vehicle retains its native perception, localization, and planning stack, and (ii) a lightweight object-level sharing and fusion strategy bridges perception and planning. Specifically, CooperDrive reuses detector Bird's-Eye View (BEV) features to estimate accurate vehicle poses without additional heavy encoders, thereby reconstructing BEV representations and feeding the planner with low latency. On the planning side, CooperDrive leverages the expanded object set to anticipate potential conflicts earlier and adjust speed and trajectory proactively, thereby transforming reactive behaviors into predictive and safer driving decisions. Real-world closed-loop tests at occlusion-heavy NLOS intersections demonstrate that CooperDrive increases reaction lead time, minimum time-to-collision (TTC), and stopping margin, while requiring only 90 kbps bandwidth and maintaining an average end-to-end latency of 89 ms.
