In robotic Field, Manipulator obstacle avoidance is one of the most highlighted aspect where robots can ensure secure and reliable movement in inaccessible environment. Including, the development of algorithms that might assist the manipulators in generating a collision free trajectory while co-operating with their kinematic constraints and working space. Research in this area explores various techniques for path planning, proximity sensing, reactive control and static and dynamic obstacle avoidance. Previously, several path planning algorithms have proposed, among them is a novel path planner developed in this paper called Chaos-Focused D* which has been tackled for improving reliability and versatility of path planning with 3R robotic arms subjected to high density obstacle environment. The proposed strategy is based on the deterministic computational efficiency of the Focused D* algorithm and adaptive exploration ability of chaotic sequences to ensure that the planner can escape local traps and traverse alternative candidate paths without lost sight of the goal. A combined workspace classification scheme is used to define and identify areas as reachable, singular, obstructed or unreachable. Obstacle avoidance is achieved via a link-segmentation method in which each of the three links that the manipulator has are searched against geometric limits of obstacle with added buffer space in order to ensure safe passage, even around irregular geometries. The proposed algorithm has been evaluated on three increasingly difficult conditions and compared to the classical Focused D*. It is found that Chaos-Focused D* reach higher success rates, especially when dense static obstacle scenarios are used, and the joint motions remain smooth and efficient. The current results suggest that it has a high potential to actual robotic navigation tasks that need to be adaptable as well as efficient.
Flaieh et al. (Tue,) studied this question.