A temporal path planner for solving information inconsistency in an integrated path planner
- 126 Downloads
This paper proposes a temporal path planner (TPP) in an integrated path planner (IPP), which is composed of a global path planner (GPP) and a local path planner (LPP). The LPPs are able to avoid obstacles within the range of built-in sensors, but it is difficult to generate an efficient path outside of the sensor range and to avoid getting stuck in cul-de-sacs. The GPPs can generate efficient global paths in a target region using a built-in global map, but the accuracy is not always sufficient to avoid collision, and the performance is highly dependent upon the accuracy of the global map. A simple combination of a GPP and an LPP causes path mismatch problems due to inconsistencies between the information acquired from the local sensors and the information from the preliminary global map. When erroneous global waypoints caused by low-accuracy information or a change of terrain are given to the unmanned ground vehicle (UGV), the proposed method attempts to find a detour via the original global waypoints located nearby to accomplish successful navigation using only sensory information and the global waypoint sequence from the GPP result provided initially. The TPP includes three subalgorithms: the Temporal Waypoint Reviser (TWR), the Temporal Map Reviser (TMR) and the Temporal Distance-Heuristic-based Decision (TDHD). The simulation results demonstrate that the performance of the TPP outperforms other planners.
KeywordsInformation inconsistency integrated path planner path mismatch problem temporal path planner
Unable to display preview. Download preview PDF.
- J. Lee, B. Choi, K. Park, and J. Lee, “Comparison between heterogeneous ant colony optimization algorithm and genetic algorithm for global path planning of mobile robot,” Proc. of the IEEE Int. Symp. Ind. Electron., pp. 881–886, 2011.Google Scholar
- S. Park and B. Lee, “A new analytical representation to robot path generation with collision avoidance through the use of the collision map,” Int. J. Control, Automation, and Systems, vol. 4, no. 1, p. 77, 2006.Google Scholar
- N. Nilsson, “Problem-solving methods in,” Artificial Intelligence, 1971.Google Scholar
- A. Stentz, “The focused D* algorithm for real-time replanning,” Proc. of Int. Joint Conf. Artificial Intelligence, vol. 14, pp. 1652–1659, 1995.Google Scholar
- S. Koenig and M. Likhachev, “D* lite,” Proc. Int. Conf. Artificial Intelligence, pp. 476–483, 2002.Google Scholar