Neural-Network-Based Switching Formation Tracking Control of Multiagents With Uncertainties in Constrained Space
提出一种在受限空间中多智能体系统切换编队跟踪控制方法，通过局部路径重规划避免轨迹抖动，并用神经网络控制器和Lyapunov函数验证性能。
In this paper, we present a novel approach for tracking control with switching formation in nonomniscient constrained space for multiagent system (MAS). The introduction of switching formation results from the situation where MAS is maneuvering in restricted path which is often the case for real world application. The preplanned trajectory may be inaccurate due to the lack of sufficient environmental information. In this case, agents may have to rapidly avoid collisions with unexpected obstacles or even switch the formation to guarantee the passability. A concept of avoidless disturbance is proposed. To solve the undesirable chattering on resulting trajectory caused by avoidless disturbance and the existing adaptation algorithm for neural network (NN) weights, a local path replanning approach is designed such that the potential force generated by avoidless disturbance is acted on the original desired trajectory outputting the locally replanned path for an agent. An NN-based controller is designed and the performance is validated using Lyapunov functions. Simulations are carried out to illustrate the effectiveness of proposed strategies.