Robotic Online Path Planning on Point Cloud

• Published in: IEEE transactions on cybernetics Vol. 46; no. 5; pp. 1217 - 1228
• Main Author: Liu, Ming
• Format: Journal Article
• Language: English
• Published: United States IEEE 01-05-2016; The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
• Subjects: Computation; Graphics processing units; Mathematical analysis; Measurement; Mobile robots; Navigation; Path planning; Raw; Robots; Tensile stress; Tensors; Three dimensional; Three dimensional models; Three-dimensional displays; Voting; Mobile robots; navigation; path planning
• ISSN: 2168-2267; 2168-2275
• DOI: 10.1109/TCYB.2015.2430526

This paper deals with the path-planning problem for mobile wheeled- or tracked-robot which drive in 2.5-D environments, where the traversable surface is usually considered as a 2-D-manifold embedded in a 3-D ambient space. Specially, we aim at solving the 2.5-D navigation problem using raw point cloud as input. The proposed method is independent of traditional surface parametrization or reconstruction methods, such as a meshing process, which generally has high-computational complexity. Instead, we utilize the output of 3-D tensor voting framework on the raw point clouds. The computation of tensor voting is accelerated by optimized implementation on graphics computation unit. Based on the tensor voting results, a novel local Riemannian metric is defined using the saliency components, which helps the modeling of the latent traversable surface. Using the proposed metric, we prove that the geodesic in the 3-D tensor space leads to rational path-planning results by experiments. Compared to traditional methods, the results reveal the advantages of the proposed method in terms of smoothing the robot maneuver while considering the minimum travel distance.