Abstract
To coexist with human, a robot has to avoid obstacles based on human-like flexible decision-making. In this article, we recorded the angle and speed that human operates the robot to avoid an obstacle on the simulator. Using those, fuzzy rules to decide the moving direction and control speed at every moment were derived as follows: as the input variables, distance to obstacle (x1), angle to obstacle (x2), speed of obstacles (x3), and the direction of movement of obstacle (x4), are adopted. As the output variable, steering angle (y1) and control speed (y2) of robot is adopted. Based on fuzzy-neural networks method, two network of 4 inputs (x1～x4) and 1 output (y1 or y2) is prepared. A membership function of each variable has 5 isosceles triangles. Fuzzy rules, number of which is 625 (=54), are assumed. Optimal center and width of each triangle are obtained so as that the network reproduces the trajectories of simulation experiment with minimum errors. The obtained fuzzy rules with tuned membership functions successfully produce the trajectory which is similar to human ones. Also, if there are plural obstacles, they can be avoided by applying the fuzzy rule to each obstacle and adopting the largest outputs among them.
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
