Human-Like Path Planning in the Presence of Landmarks
This work proposes a path planning algorithm for scenarios where the agent has to move strictly inside the space defined by signal emitting bases. Considering a base can emit within a limited area, it is necessary for the agent to be in the vicinity of at least one base at each point along the path in order to receive a signal. The algorithm starts with forming a specific network, based on the starting point such that only the bases which allow the described motion are included. A second step is based on RRT*, where each edge is created solving an optimal control problem that at the end provides a human-like path. Finally the best path is selected among all the ones that reach the goal region with the minimum cost.
KeywordsHuman-like path planning Planning with landmarks
- 3.Devaurs, D., Simon, T., Corts, J.: Efficient sampling-based approaches to optimal path planning in complex cost spaces. In: Akin, H.L., Amato, N.M., Isler, V., van der Stappen, A.F. (eds.) Algorithmic Foundations of Robotics XI. Springer Tracts in Advanced Robotics, vol. 107, pp. 143–159. Springer, Heidelberg (2015)Google Scholar
- 4.Jeon, J.H., Karaman, S., Frazzoli, E.: Anytime computation of time-optimal off-road vehicle maneuvers using the RRT*. In: Decision and Control and European Control Conference (CDC-ECC) (2011)Google Scholar
- 9.Perez, A., Platt Jr., R., Konidaris, G., Kaelbling, L., Lozano-Perez, T.: LQR-RRT*: optimal sampling-based motion planning with automatically derived extension heuristics. In: Robotics and Automation (ICRA) (2012)Google Scholar
- 10.Puydupin-Jamin, A.S., Johnson, M., Bretl, T.: A convex approach to inverse optimal control and its application to modeling human locomotion. In: IEEE International Conference on Robotics and Automation (ICRA) (2012)Google Scholar