Optimum Mobile Robot Path Planning Using Improved Artificial Bee Colony Algorithm and Evolutionary Programming

The optimal/shortest path planning is one of the fundamental needs for efficient operation ofmobile robot. This research article explores the application of artificial bee colony (ABC) algorithm and evolutionary programming (EP) optimization algorithm to resolve the problem of path planning in an unknown or partially known environment. The ABC algorithm is used for native ferreting procedure and EP for refinement of achieved feasible path. Conventional path planning methods based on ABC-EP didn't consider the distance between newbee position and nearby obstacles for finding the optimal path, which in turn increases the path length, path planning time, or search cost. To overcome these issues, a novel strategy based on improved ABC-EP has been proposed. The improved ABC-EP finds the optimum path towards the goal position and gets rid of obstacles without any collision using food points which are randomly distributed in the environment. The criteria on which it selects the best food point (V-best) not only depend upon the shortest distance of that food point to the goal position but also depend upon the distance of that food point from the nearest obstacles. A number of comparative analyses have been performed in simulation scenario to verify improved ABC-EP's performance and efficiency. The results demonstrate that proposed improved ABC-EP performs better and more effectively as compared to conventional ABC-EP with the improvement of 5.75% in path length, 44.38% in search cost, and 41.08% in path smoothness. The improved ABC-EP achieved optimum path with shortest path length in less time.