Hybrid position/virtual-force control for obstacle avoidance of wheeled robots using Elman neural network training technique

Abstract

The hybrid force position control algorithm based on neural network is considered for a class of robot system with nonlinear uncertainties. Compared with previous work, not only the steady-state performance but also the transient-state performance is considered. Firstly, in order to relax the control design dependent on detailed system information, a fast hybrid position/virtual-force controller is presented to build a virtual-force field between the obstacles and robot. The virtual force is the control parameter, which is set to maintain an expected distance between obstacles and the robot with unknown nonlinear and parameter uncertainty. Secondly, in order to alleviate the computation burden of parameter learning, and enhance the dynamic mapping of network ability, the Elman neural network is introduced. The output signal come from hybrid position/virtual-force controller is fed back to Elman neural network. Furthermore, since uncertainties of robot dynamics and obstacle location information, Elman neural network is also used to compensate for uncertainties and improve system stability performance. The control design conditions are relaxed because of the developed dynamic compensator. Finally, both simulations and results of obstacle avoidance are performed to show the potential of the proposed methods.

Development of simulation software for mobile robot path planning within multilayer map system based on metric and topological maps

“…As mentioned by Zheng et al, 4 grid map-based navigation methods achieve self-navigation while reducing the cost of resources and promoting the running efficiency and speed. In general, grid maps can be divided into twodimensional (2-D) and three-dimensional (3-D) 14 grid maps, where objects are described by their shape and dimensions.…”

“…8,9 Recently, many researchers have dealt with the design of control laws for obstacle avoidance and path planning of wheeled (as well as other locomotion systems) mobile robots. 4 Many different methods have been proposed in the literature by Siegwart and Nourbakhsh, 1 Zheng et al, 4 Zavlangas and Tzafestas., 12 Thrun, 11 Hedjar and Bounkhel, 13 Shi et al, 14 and their colleagues, dealing with obstacle avoidance for mobile robotics during last years. The well-known methods among them are the so-called reactive approaches, which have been proposed mainly for a single mobile robot path generation and which are suitable for real-time navigation in unknown environments.…”

“…In their work, Turygin et al 19 proposed the method of enhancing the reliability of mobile robot control process via reverse validation. According to the work of Zheng et al, 4 the tracking control problem for extended non-holonomic chained-form robot systems has received increasing attention and so has the global finite-time stabilization problem in the last few years. The basic idea of these algorithms is based on the parameters measured by the sensor and on drawing of an environmental map around the mobile robot, with the aim of avoiding a collision between the robot and the wall object in its path.…”

“…The basic idea of these algorithms is based on the parameters measured by the sensor and on drawing of an environmental map around the mobile robot, with the aim of avoiding a collision between the robot and the wall object in its path. 4 Zhao et al 20 describe the novel iterative learning path-tracking control for non-holonomic mobile robots against initial shifts. Matik and Uricek 8 and others describe approach called simultaneous localization and mapping (SLAM) based on simultaneous localization and mapping.…”

“…1,3 At the same time, mobile robots are becoming closer to human beings with their moving closer to our families. 4 Those are the mobile robots for autonomous vacuum cleaning, grass cutting (in a garden or in football fields-Hameed et al 5 ), sport and free time activities 6,7 or as helpmates for Ambient assisted living systems, 8 and so on. According to its application, any mobile robot can have a different level of its autonomous behavior.…”