Author : E.K. Xidias, N.A. Aspragathos
In this paper, we introduce a new method based on the Bump-Surface concept for global, near-optimal, motion planning of a robot moving in 2D weighted regions with arbitrary shape and size. The proposed method generates a near-optimal path from a start point to a destination point, conformal to the objectives and criteria of motion planning, by performing a search on the modified Bump-Surface. Extensive experimental work shows the efficiency and the effectiveness of the proposed method in a variety of complex weighted environments.
| Attachment | Size |
|---|---|
| Path Planning in Weighted Regions Using the Bump-Surface Concept.wmv | 4.7 MB |
| PID154742.pdf | 214.36 KB |
In your paper, you have considered two criteria and constraints:
i. The robot should travel from the start point to the
destination point with minimum cost.
ii. The path should be smooth with the minimum
curvature
which can be classed as multi-objectives problems, but you have chosen weighted-sum approach to aggregate these criteria and constraints into single objective and thus, one solution can be found at each test case. I would suggest further work to enhance your research using multi-objective evolutionary algorithms (MOEA). There are quite a number of research works comparing and replacing weighted-sum approach with MOEA in similar robotic path planning problems since 1996.