Abstract
Obstacle detection is one of the essential capabilities for autonomous robots operated on unstructured terrain. In this paper, a novel laser-based approach is proposed for obstacle detection by autonomous robots, in which the Sobel operator is deployed in the edge-detection process of 3D laser point clouds. The point clouds of unstructured terrain are filtered by VoxelGrid, and then processed by the Gaussian kernel function to obtain the edge features of obstacles. The Euclidean clustering algorithm is optimized by super-voxel in order to cluster the point clouds of each obstacle. The characteristics of the obstacles are recognized by the Levenberg–Marquardt back-propagation (LM-BP) neural network. The algorithm proposed in this paper is a post-processing algorithm based on the reconstructed point cloud. Experiments are conducted by using both the existing datasets and real unstructured terrain point cloud reconstructed by an all-terrain robot to demonstrate the feasibility and performance of the proposed approach.
Highlights
With the advancement of technology, wheeled mobile robots have gradually moved towards automation and intelligence in recent years [1,2]
Optimization of obstacle extraction based on non-maximum suppression (26011 points)
To further verify performanceofofthe theproposed proposed algorithm, used an an all-terrain robotrobot and and thethe performance algorithm,wewe used all-terrain reconstructed the real unstructured terrain point cloud as the original point cloud based on a tworeconstructed the real unstructured terrain point cloud as the original point cloud based on a two-step step registration algorithm [36]
Summary
With the advancement of technology, wheeled mobile robots have gradually moved towards automation and intelligence in recent years [1,2]. Bazazian et al proposed a fast and precise method to detect sharp edge features, which analyses the eigenvalues of the covariance matrix defined by k-nearest neighbors of each point [21]. Inwas this paper,based a LiDAR the pointtime-consuming cloud into clusters and identify regions with sharp features proposed on the system is deployed foranalysis an autonomous to understand theallunstructured environment. As extracting sharp edge features from a 3D point cloud requires accurate normal estimation, characteristics of the 3D point cloud and realizes the edge detection of unstructured terrain.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
