MoDeT: a low-cost obstacle tracker for self-driving mobile robot navigation using 2D-laser scan

Abstract

Purpose Collision avoidance is considered as a crucial issue in mobile robotic navigation to guarantee the safety of robots as well as working surroundings, especially for humans. Therefore, the position and velocity of obstacles appearing in the working space of the self-driving mobile robot should be observed to help the robot predict the collision and choose traversable directions. This paper aims to propose a new approach for obstacle tracking, dubbed MoDeT. Design/methodology/approach First, all long lines, such as walls, are extracted from the 2D-laser scan and considered as static obstacles (or mapped obstacles). Second, a density-based procedure is implemented to cluster nonwall obstacles. These clusters are then geometrically fitted as ellipses. Finally, the combination of Kalman filter and global nearest-neighbor (GNN) method is used to track obstacles’ position and velocity. Findings The proposed method (MoDeT) is experimentally verified by using an autonomous mobile robot (AMR) named AMR SR300. The MoDeT is found to provide better performance in comparison with previous methods for self-driving mobile robots. Research limitations/implications The robot can only see a part of the object, depending on the light detection and ranging scan view. As a consequence, geometrical features of the obstacle are sometimes changed, especially when the robot is moving fast. Practical implications This proposed method is to serve the navigation and path planning for the AMR. Originality/value (a) Proposing an extended weighted line extractor, (b) proposing a density-based obstacle detection and (c) implementing a combination of methods [in (a) and (b) constant acceleration Kalman and GNN] to obtain obstacles’ properties.

Obstacle Avoidance for Automated Guided Vehicles in Real-World Workshops Using the Grid Method and Deep Learning

“…(1) Video images of the AGV passage in the tobacco production workshop are obtained through cameras. (2) The object detection algorithm is used to analyze whether there are obstacles in the image after the image is obtained on the visual AI basic platform, and the obstacles are pushed to the AGV scheduling system. (3) The grid method is used to plan the route after obtaining obstacle information, and the optimal route is pushed to the AGV.…”

“…Collision avoidance is considered a key issue in mobile robot navigation. The long lines from 2D laser scanning were extracted by Toan Van Nguyen et al [2] to detect static obstacles. Furthermore, the Kalman filter and global nearest neighbor (GNN) method were combined to track the position and velocity of dynamic obstacles, and the spatial information of the obstacles was obtained.…”

AGV robot for laser-SLAM based method testing in automated container terminal

“…Laser simultaneous location and mapping navigation of automated guided vehicle A navigation system is a critical technology for terminal AGV transportation. Scholars have carried out much research to improve the stability and effectiveness of various navigation systems, such as magnetic navigation (Lee and Yang, 2012), visual navigation (Hou et al, 2007) and laser navigation (Nguyen et al, 2022). The laser navigation system used light detection and ranging (LiDAR) to continuously launch laser scanning surrounding reflectors to measure the distance and angle to each target location (Dobrzanska and Dobrzanski, 2022).…”

A Modified Dijkstra Algorithm for ROS Based Autonomous Mobile Robots

“…They also gave comparative basic information on autonomous robot architecture and explained the disadvantages of AGVs (Arkin & Murphy, 1990). Efficient navigation is one of the most important capabilities of autonomous mobile robots (AMRs) to successfully perform industrial tasks, especially in irregular environments with moving obstacles (Nguyen et al, 2022).…”