Prediction-based path planning with obstacle avoidance in dynamic target environment

Abstract EN

In this paper, a new algorithm for mobile robot navigation and polygonal obstacles avoidance in dynamic target environment is introduced.

In the dynamic target path planning the agent (robot) trying to reach a moving target in minimum path cost.

The introduced algorithm which called Prediction-based path planning with obstacle avoidance in dynamic target environment planning a path to a moving target by predicting the next target location, then computing a path from the robot current location to the predicted target location representing each visible obstacle by the smallest circle that enclosing the polygon obstacle, then determine the visible tangents between the robot and the circular obstacle that intersect its shortest path and compute the shortest path.

Three target movement scenarios were suggested and tested in different environment conditions.

The results show that the target was reached in all scenarios and under all environment conditions with good path cost.