Path planning of mobile robot in dynamic environment: fuzzy artificial potential field and extensible neural network

Abstract

Path planning in dynamic environment is a great challenge for mobile robot. A large number of approaches have been used to deal with it. Since the neural network algorithm has the ability to find the optimal solution at high speed and self-learning function, it has achieved extensive applications in the path planning tasks. Considering that the optimization performance of the neural network heavily depends on the quality of the training sample, this paper proposes a novel way to provide the training samples for the neural network. Work space of the robot is divided into two parts: global safe area and local dangerous area. In the global safe area, the robot only receives the attraction force from the target and it moves towards the target directly. In the dangerous area, except the attraction force, the robot also receives the repulsion force from the obstacle(s). The repulsion force and the angle between the obstacle and the target (origin of the coordinate is in the position of the robot) are used to be the inputs of the fuzzy inferencing system, and the deflection angle of the robot is the output. The final moving direction of the robot is determined by summing this deflection angle and the direction of the attraction force. The coordinates of the target and obstacle, and the moving direction of the robot corresponding to this position relationship, constitute the training samples for the neural network. Benefited from the precise moving direction obtained by the fuzzy artificial potential field algorithm, the neural network gets excellent path optimization ability. Simulation and physical experiment results demonstrate the potential of the proposed algorithm.

A Consolidated Review of Path Planning and Optimization Techniques: Technical Perspectives and Future Directions

“…Dongshu Wang et al [218] have presented the enhanced performance of the neural network by refining the training samples using an artificial potential field. They accomplished this task in two steps: (i) defining the global safe area and (ii) dangerous local area.…”

Collaborative Multi-Robot Formation Control and Global Path Optimization

“…Many scholars focus on mobile robot path planning, and, so far, a large number of control optimization methods have been proposed. These include the Dijkstra algorithm [3], genetic algorithm [4], firefly algorithm [5], A* algorithm [6], artificial potential field method [7], RRT algorithm [8], neural network algorithm [9], etc. However, due to their own defects, these heuristic algorithms often cannot complete the task satisfactorily.…”

Entry Guidance Command Generation for Hypersonic Glide Vehicles Under Threats and Multiple Constraints

“…Designing a heading error corridor-based bank angle reversal logic is an effective way to satisfy geographic constraints. The artificial potential field (APF) method is one of the most popular algorithms in obstacle avoidance for mobile robots [19], unmanned aerial vehicles (UAVs) [20], autonomous vehicles [21], [22], and manipulators [23], which has the benefits of brief mathematical description, simplicity, high efficiency, and strong adaptability. But the local minimum problem is a drawback of the APF method that should be noticed.…”