No abstract

No abstract

Abstract. Aiming at the problems that BP algorithm has slow convergence rate and is likely to fall into local minimum point. This paper presents a modified fuzzy neural network which takes the distances between the robot and obstacles as input variables, and the velocity and the steering angle of the robot as output variables. Besides, the accurate environmental information can be obtained by fusing the information of ultrasonic sensors, and the network parameters can be adjusted by training the network. With the application of Matlab simulation software, the result shows that the improved fuzzy neural network has good performances in optimizing the convergence speed, learning speed and stability of the network.

Purpose The research of unmanned air/ground vehicle (UAV/UGV) cooperation has attracted much attention due to its potential applications in disaster rescue and target surveillance. This paper aims to focus on the UAV/UGV cooperative target tracking and enclosing, considering the limits of detection and sensor failures. Design/methodology/approach The UAV/UGV cooperation structure is designed, contributing to homogeneous consistency and heterogeneous communication. The target tracking of UAVs is converted into a constraint optimization problem involving tracking cost, and the target enclosing of UGVs is modeled as formation control. Findings The energy estimation pigeon-inspired optimization is developed to generate control inputs for UAVs. And the controller combined with switchable topology is proposed, where the switching rule is flexible in dealing with some emergencies. Practical implications The proposed structure and algorithms can be easily applied to practice and help design the UAV/UGV control system. Originality/value The energy estimation mechanism is proposed for the target tracking of UAVs, and the rules of switching topologies ensure the target enclosing process of UGVs.

No abstract