Search papers, labs, and topics across Lattice.
This paper introduces Kernel-SDF, an open-source library for real-time signed distance function (SDF) estimation that uses kernel regression to learn a continuous occupancy field and GP regression for accurate SDF estimation with calibrated uncertainty. By combining kernel regression for the front-end and GP regression for the back-end, Kernel-SDF overcomes limitations of voxel-based, neural network, and traditional GP methods in terms of accuracy, scalability, and uncertainty quantification. Experiments demonstrate that Kernel-SDF achieves superior accuracy and real-time performance, making it suitable for robotics applications requiring reliable geometric information.
Real-time, uncertainty-aware signed distance functions are now possible without sacrificing accuracy, thanks to a novel kernel regression and GP regression hybrid.
Accurate and efficient environment representation is crucial for robotic applications such as motion planning, manipulation, and navigation. Signed distance functions (SDFs) have emerged as a powerful representation for encoding distance to obstacle boundaries, enabling efficient collision-checking and trajectory optimization techniques. However, existing SDF reconstruction methods have limitations when it comes to large-scale uncertainty-aware SDF estimation from streaming sensor data. Voxel-based approaches are limited by fixed resolution and lack uncertainty quantification, neural network methods require significant training time, while Gaussian process (GP) methods struggle with scalability, sign estimation, and uncertainty calibration. In this letter, we develop an open-source library, Kernel-SDF, which uses kernel regression to learn SDF with calibrated uncertainty quantification in real-time. Our approach consists of a front-end that learns a continuous occupancy field via kernel regression, and a back-end that estimates accurate SDF via GP regression using samples from the front-end surface boundaries. Kernel-SDF provides accurate SDF, SDF gradient, SDF uncertainty, and mesh construction in real-time. Evaluation results show that Kernel-SDF achieves superior accuracy compared to existing methods, while maintaining real-time performance, making it suitable for various robotics applications requiring reliable uncertainty-aware geometric information.
