RCVLA is proposed, a radar-camera VLA framework consisting of a radar-grounded semantic reasoning stage (RCVLA-Sem) and a trajectory arbitration stage (RCVLA-Phys), which performs gated bidirectional interaction between camera and radar tokens for driving question answering and reference trajectory generation.
Lian-Qing Zheng, Xiao-Kai Bai, Yi-Xuan Luo et al.· arXiv.org· 0 citations
Fixed roadside cameras repeatedly observe a stable scene overlaid by sparse moving traffic. Temporal memory can recover weak observations, but reusing moving evidence at stale locations can corrupt occupancy predictions. Motion compensation addresses displacement, while reliance on the resulting history remains a separ...
Xiao-Kai Bai, Lei Yang, Song Wang et al.· arXiv.org· 0 citations
4D radar complements dense image semantics with long-range geometry and radial motion, but existing radar--camera detectors largely solve \emph{where} to align the modalities while leaving \emph{whether} a piece of evidence supports an evolving object hypothesis implicit. An image token may describe an occluder, a near...
Xiao-Kai Bai, Zhen-Yu Fan, Lian-Qing Zheng et al.· 0 citations
A 4D radar-camera framework for 360 full-scene perception, which models semantic occupancy as a persistent scene state rather than a terminal output, and follows a cross-modal state reasoning paradigm.