Autonomous driving paper index
A Multi-Modal Fisheye, GPS, and CAN-Bus Dataset for Autonomous Valet Parking
One-line summary
A synchronized multi-modal driving dataset collected from a real autonomous valet parking (AVP) platform in a parking lot (Beijing, 116.235E, 40.139N) on January 8, 2026.
Engineering notes
Key topics: autonomous driving, control. See the paper for implementation details and experimental results.
Chinese explanation / 中文解读
中文解读待补充：本站会优先为端到端自动驾驶、BEV感知、3D目标检测、轨迹预测、路径规划、LiDAR感知等高价值论文补充中文说明。
Original abstract
A synchronized multi-modal driving dataset collected from a real autonomous valet parking (AVP) platform in a parking lot (Beijing, 116.235E, 40.139N) on January 8, 2026. The dataset contains 4 driving segments (438.9 s total, 8785 synchronized frames, 597.8 m) with three sensor modalities: - Front fisheye camera: 240x320 BGR8 images at 20 Hz (~180 deg field of view) - GPS: 10 Hz, 21 fields (lat/lon, local xg/yg, heading, velocity, satellite count) - Vehicle CAN bus: 20 Hz, 14 fields (steering angle, target speed, gear, turn signals, lights) Each segment folder contains images/, gps.csv, can.csv, images.csv, meta.json. Average vehicle speed 1.4 m/s (peak 3.1 m/s). 242 significant steering events (>5 deg change). NOTE: CAN target_speed and target_accel are constantly zero on this platform (longitudinal control handled by a separate low-level controller).
Links and sources
Need this topic turned into a technical roadmap?
Full Self Driving can prepare a custom autonomous driving literature review, code map, dataset map, and B2B technology assessment.
Request B2B research
Comments