Avoidance of Multiple Dynamic Obstacles

this article is a continuation of the previous article called “Obstacle Avoidance in Dynamic Environment: a Hierarchical Solution”, which presented the concept for obstacle avoidance in dynamic environment suitable for mobile robot. The task of obstacle avoidance is divided in three principal groups: local, global and for emergencies. The global avoidance is here approached, in which the concept used is based on reinforcement learning and on an algorithm for planning the avoidance, in such a way that the situations are divided into four states and two kinds of actions are possible. The states define in what situation the movement relationship between the robot and the dynamic obstacles is present, and the actions decide in which direction the robot must follow, in order to avoid a possible collision. The algorithm plans in order to decide an action, which certainly is not the best for each obstacle, but normally is the best considering the group.