Obstacle avoidance strategy

According to the following obstacle avoidance strategy as seen in Fig. 3.17, a control system is considered and developed in order to guide the visually impaired person. During the design of a control system, fiizzy and neural network approaches are used. 

Figure 3.17 Basic flow diagram of obstacle avoidance strategy.

If (ai(i+i)> a max) A (a2(i+i) > tmax). which represents that there is no obstacle in the detection range, then there will be no avoidance strategy. This means go straight (zero) or wb = 0 (Table 3.1). 

After determining object s position with Algorithm 1 (Algorithm 1 is tested with real-time measurements, and the success of the algorithm is found 97.98% by using MATLAB), data is sent to one of the avoidance strategies left, front, and right obstacle avoidance. 

Q. Zhu, and N. K. Loh, "Modeling and Control Strategies for Dynamic Obstacle Avoidance By Mobile Robots", Proceedings of 1989 Korean Automatic Control Conference, Seoul, Korea, October 1989. 

While executing the algorithm, each robot in the network has to move inside the rooms. In order to make each robot reach some desired point inside the apartment, as well as avoiding obstacles and walls, a trajectory strategy had to be considered in the implementation. In this case, the use of preprogrammed potential fields is considered in each robot. Potential fields are functions that map all the points of a specific area into a specific value. 

A dynamic and kinematic strategy was implemented on die onboard control of the mobile robot, in order to find best trajectory and avoid obstacles, as can seen in Figure 11. 

---