Batch differentiable pose refinement for in-the-wild camera/LiDAR extrinsic calibration

Accurate camera to LiDAR (Light Detection and Ranging) extrinsic calibration is important for robotic tasks carrying out tight sensor fusion — such as target tracking and odometry. Calibration is typically performed before deployment in controlled conditions using calibration targets, however, this...

Mô tả đầy đủ

Chi tiết về thư mục
Những tác giả chính: Fu, LFT, Fallon, M
Định dạng: Conference item
Ngôn ngữ:English
Được phát hành: Journal of Machine Learning Research 2023
Miêu tả
Tóm tắt:Accurate camera to LiDAR (Light Detection and Ranging) extrinsic calibration is important for robotic tasks carrying out tight sensor fusion — such as target tracking and odometry. Calibration is typically performed before deployment in controlled conditions using calibration targets, however, this limits scalability and subsequent recalibration. We propose a novel approach for target-free camera-LiDAR calibration using end-to-end direct alignment which doesn’t need calibration targets. Our batched formulation enhances sample efficiency during training and robustness at inference time. We present experimental results, on publicly available real-world data, demonstrating 1.6cm/0.07∘median accuracy when transferred to unseen sensors from held-out data sequences. We also show state-of-the-art zero-shot transfer to unseen cameras, LiDARs, and environments.