Adaptive Obstacle Detection for Mobile Robots in Urban Environments Using Downward-Looking 2D LiDAR

Self Cite

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.

Section: Introductionmentioning

confidence: 99%

Novel Laser-Based Obstacle Detection for Autonomous Robots on Unstructured Terrain

Chen

Liu

et al. 2020

Self Cite

“…The safe and efficient navigation of an unmanned ground vehicle requires the terrain information, which can be exploited to predict the future pose of the vehicle and assess the traversability. The sensors used to obtain the terrain information include visual sensors [1,2,3,4,5], LiDARs [6,7,8,9,10,11,12,13], and so on. Visual sensors can provide various kinds of terrain information, but processing visual data often requires a long computation time.…”

Section: Introductionmentioning

confidence: 99%

Traversability Assessment and Trajectory Planning of Unmanned Ground Vehicles with Suspension Systems on Rough Terrain

Zhang

Yang

et al. 2019

This paper presents a traversability assessment method and a trajectory planning method. They are key features for the navigation of an unmanned ground vehicle (UGV) in a non-planar environment. In this work, a 3D light detection and ranging (LiDAR) sensor is used to obtain the geometric information about a rough terrain surface. For a given SE(2) pose of the vehicle and a specific vehicle model, the SE(3) pose of the vehicle is estimated based on LiDAR points, and then a traversability is computed. The traversability tells the vehicle the effects of its interaction with the rough terrain. Note that the traversability is computed on demand during trajectory planning, so there is not any explicit terrain discretization. The proposed trajectory planner finds an initial path through the non-holonomic A*, which is a modified form of the conventional A* planner. A path is a sequence of poses without timestamps. Then, the initial path is optimized in terms of the traversability, using the method of Lagrange multipliers. The optimization accounts for the model of the vehicle’s suspension system. Therefore, the optimized trajectory is dynamically feasible, and the trajectory tracking error is small. The proposed methods were tested in both the simulation and the real-world experiments. The simulation experiments were conducted in a simulator called Gazebo, which uses a physics engine to compute the vehicle motion. The experiments were conducted in various non-planar experiments. The results indicate that the proposed methods could accurately estimate the SE(3) pose of the vehicle. Besides, the trajectory cost of the proposed planner was lower than the trajectory costs of other state-of-the-art trajectory planners.

“…As a first step, most of the works start with defining an obstacle’s location and shape, and then define the best heading to avoid them while navigating to the goal [5]. The simplest method in this direction is based on line extraction [11,12]. Here, the LiDAR’s readings are grouped into small clusters, and each cluster is analyzed in order to define potential segments.…”

Section: Introductionmentioning

confidence: 99%

The Heading Weight Function: A Novel LiDAR-Based Local Planner for Nonholonomic Mobile Robots

Harik

Korsæth

2019

In this paper, we present a novel method for obstacle avoidance designed for a nonholonomic mobile robot. The method relies on light detection and ranging (LiDAR) readings, which are mapped into a polar coordinate system. Obstacles are taken into consideration when they are within a predefined radius from the robot. A central part of the approach is a new Heading Weight Function (HWF), in which the beams within the aperture angle of the LiDAR are virtually weighted in order to generate the best trajectory candidate for the robot. The HWF is designed to find a solution also in the case of a local-minima situation. The function is coupled with the robot’s controller in order to provide both linear and angular velocities. We tested the method both by simulations in a digital environment with a range of different static obstacles, and in a real, experimental environment including static and dynamic obstacles. The results showed that when utilizing the novel HWF, the robot was able to navigate safely toward the target while avoiding all obstacles included in the tests. Our findings thus show that it is possible for a robot to navigate safely in a populated environment using this method, and that sufficient efficiency in navigation may be obtained without basing the method on a global planner. This is particularly promising for navigation challenges occurring in unknown environments where models of the world cannot be obtained.