Anytime Reactive Planning with Decision Automation

Abstract:

In many outdoor robotic applications several factors have to be taken into account during a path planning process. In different situations the importance of these factors vary. This paper presents a path planning method for mobile robots that incorporates decision theory to guide the search. A neural structure is proposed to determine the relative importance of the objectives that makes the robot capable of planning in unfamiliar situations. The method is able to handle an arbitrary number of objectives simultaneously and also enables the incorporation of human logic into the planning process. All parts of the algorithm suit real-time implementation.

• Periodical: Advanced Materials Research (Volume 1117)
• Pages: 245-248
• DOI: https://doi.org/10.4028/www.scientific.net/AMR.1117.245
• Online since: July 2015
• Authors: István Komlósi*
• Keywords: Mobile Robots, Multi-Criteria Decision Making, Neural Network, Planning Algorithms

References

[1] J.C. Latombe: Robot Motion Planning. Kluwer Academic Publishers, Boston, MA, (1991).

[2] Steven M. LaValle: Planning algorithms. Cambridge University Press, (2006).

[3] Hart, P. E.; Nilsson, N. J.; Raphael, B.: A Formal Basis for the Heuristic Determination of Minimum Cost Paths. IEEE Transactions on Systems Science and Cybernetics SSC4 4 (2), 1968, p.100–107.

DOI: 10.1109/tssc.1968.300136

[4] Anthony (Tony) Stentz: Optimal and Efficient Path Planning for Partially-Known Environments. Proceedings of the IEEE International Conference on Robotics and Automation (ICRA '94), May, 1994, pp.3310-3317.

DOI: 10.1109/robot.1994.351061

[5] Joseph Carsten, Arturo Rankin, David Ferguson, and Anthony (Tony) Stentz: Global Path Planning on-board the Mars Exploration Rovers. IEEE Aerospace Conference, (2007).

DOI: 10.1109/aero.2007.352683

[6] Maxim Likhachev, David Ferguson, Geoffrey Gordon, Anthony (Tony) Stentz, and Sebastian Thrun: Anytime Dynamic A*: An Anytime, Replanning Algorithm. Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), June, (2005).

DOI: 10.1016/j.artint.2007.11.009

[7] Várkonyi-Kóczy, A. R., T. Kovácsházy, O. Takács, and Cs. Benedecsik: Anytime Algorithms in Intelligent Measurement Control. In CD- ROM Proc. of the 2000 World Automation Congress, WAC 2000, Maui, USA, June 11-16, 2000, ISBN: 1-889335-10-X, pp. ISIAC-156. 1-6.

DOI: 10.1016/s1474-6670(17)36827-1

[8] Várkonyi-Kóczy, A. R.: Model Based Anytime Sof Computing Approaches in Engineering Applications. In Balas, V, J, Fodor, A. R. Várkonyi-Kóczy (eds. ), Soft Computing Modelling in Intelligent Systems (Ser. Studies in Computational Intelligence), Springer Verlag, 2008, pp.63-92.

DOI: 10.1007/978-3-642-00448-3_4

[9] Kiss, L.,A. R. Várkonyi-Kóczy, and P. Baranyi: Autonomous Navigation in a Known Dynamic Environment. In Proc of the 12th IEEE Int. Conference on Fuzzy Systems, FUZZ-IEEE'2003, St. Louis, USA, May 25-28, 2003, pp.266-271.

DOI: 10.1109/fuzz.2003.1209373

[10] Lászka, Á., A. R. Várkonyi-Kóczy, G. Pék, P. Várlaki: Universal Autonomous Robot Navigation Using Quasi Optimal Path Generation. In CD-ROM Proc. of the 4th IEEE Int. Conf. on Autonomous Robots and Agents, ICARA'2009, Wellington, New Zealand, Feb. 9-12, 2009, pp.458-463.

DOI: 10.1109/icara.2000.4804008

[11] Saaty, T.L., The analytic hierarchy process, McGrawHill, New York. (1980).

[12] István Komlósi: The AD-AHP planner: Incremental path planning for robots incorporating decision theory. AARMS: Academic & Applied Research in Military Science . 2013, Vol. 12 Issue 2, pp.289-301. 13p.

DOI: 10.32565/aarms.2013.2.10

[13] Ronald C. Arkin: Behaviour based robotics, MIT Press Cambridge, MA, USA , 1998, ISBN: 0262011654.

[14] Arkin, R.C. (1989) Towards the unification of navigational planning and reactive control, in AAAI Spring Symposium on Robot Navigation, p.1–5, AAAI Press.