Abstract
The methods of task assignment and path planning have been reported by many researchers, but they are mainly focused on environments with prior information. In unknown dynamic environments, in which the real-time acquisition of the location information of obstacles is required, an integrated multi-robot dynamic task assignment and cooperative search method is proposed by combining an improved self-organizing map (SOM) neural network and the adaptive dynamic window approach (DWA). To avoid the robot oscillation and hovering issue that occurs with the SOM-based algorithm, an SOM neural network with a locking mechanism is developed to better realize task assignment. Then, in order to solve the obstacle avoidance problem and the speed jump problem, the weights of the winner of the SOM are updated by using an adaptive DWA. In addition, the proposed method can search dynamic multi-target in unknown dynamic environment, it can reassign tasks and re-plan searching paths in real time when the location of the targets and obstacle changes. The simulation results and comparative testing demonstrate the effectiveness and efficiency of the proposed method.
Highlights
Multi-robot systems have become a prominent research area and have attracted increasing attention from researchers
To solve the problems in the task assignment and cooperative search research of multi-robot systems described in this paper, an improved self-organizing map (SOM) method combined with the adaptive dynamic window approach (DWA) was proposed
(1) The SOM algorithm is improved by building a locking mechanism on each competing neuron to restrict its self-organizing behavior in order to avoid situations of robot oscillation and hovering
Summary
Multi-robot systems have become a prominent research area and have attracted increasing attention from researchers. In unknown dynamic environments where the location information of obstacles requires real-time acquisition, an improved DWA is introduced into an improved SOM neural network to solve the problem of task assignment and cooperative search for multi-robot systems, the proposed method is called the DSOM method. An adaptive DWA is introduced to adjust the velocities of the robots in order to update the weights of the winning neurons and their neighboring neurons in the SOM in such a way that the robot can automatically avoid speed jumps and obstacles, and achieve a better planning search path in unknown environments. The robot acquires real-time distance information with obstacles through sensors, and it adjusts the linear and angular velocities of the robot through the adaptive DWA to achieve path planning in unknown dynamic environments.
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
Free) 
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a call
