Browsing by Author "Mansakul, Thanavin"

Now showing 1 - 2 of 2
  • Thumbnail Image
    ItemOpen Access
    Navigation for a mobile robot to inspect aircraft
    (IEEE, 2023-08-08) Mansakul, Thanavin; Fan, Ip-Shing; Tang, Gilbert
    Preflight inspection is an important part of aircraft maintenance, as it does not affect only safety but also expenditure. In order to reduce the risks from human errors and the cost of operation, a mobile robot is introduced as an effective solution. This research examines navigation for aircraft inspection using a mobile robot. The two path planning methods, Dijkstra with DWA and A* with TEB, are compared by navigation performance in the simulation and three environments which are office, atrium, and hangar, to ensure that the robot is able to handle a variety of situations. In addition, an ultrasonic sensor was installed to perform obstacle avoidance and support LIDAR when it failed. The result is that both algorithms have their advantages depending on the purpose; if an accurate position is required, A* with TEB should be selected, while Dijkstra with DWA offers a smooth path and less time spent in small and complex environments. The notable parameters in navigation for the mobile robot, TurtleBot3, are presented, and limitations are detailed. The use of the autonomous mobile robot could support the operation with high precision and repeatability.
  • Thumbnail Image
    ItemOpen Access
    The comprehensive review of vision-based grasp estimation and challenges
    (IEEE, 2024-08-28) Mansakul, Thanavin; Tang, Gilbert; Webb, Phil
    Robotic grasping has emerged as a fundamental skill and a vital task for a robotic manipulator in various sectors over recent decades. Although a preprogramming method is now a general application, the challenges to handling complicated and unstructured scenarios remain. Machine vision, therefore, has become a focus of interest from many researchers as a primary perception to provide flexible manipulation in unknown and uncertain environments rather than control working space. This research presents a comprehensive review of vision-based grasp detection for a parallel gripper, analyzing potential techniques, existing challenges, and future directions. It delves into fundamental concepts of grasp detection and estimation, including traditional and learning-based methods. Additionally, the study explores essential benchmark datasets and metrics. This paper not only offers opportunities to develop grasp detection methodologies but also applications in the real world, such as fruit picking in agriculture, pick-and-pack items in supermarkets and logistics, and pick-and-sort objects in manufacturing. This will enable substantial changes and impacts of the robotic manipulator in the modern world.