Dynamic Programming Agent for mobile robot navigation with moving obstacles

Abstract

Dynamic programming (DP) approach to shortest path algorithm provides a global optimal solution to robot path planning in an indoor environment. The proposed DP shortest path algorithm for real-time provides collision-free robot-path planning in which the barriers is permitted to move in an indoor environment. Environment is represented as a grid map, each grid point records the distance to the target. The information stored at each point is a current estimate of the distance to the nearest target and the neighbor from which this distance was determined. Updating the distance estimate at each grid point is done using the information gathered from the point's neighbors. Dynamic Programming Agent requires the distance information in the neighbor grid points and no prior knowledge about the obstacle position is required. At each time step collision free shortest path is generated by propagating the distance to the target and updating them in an order depending on the distance to the target for intelligent navigation