Programming Khepera II robot for autonomous navigation and exploration using the hybrid architecture

ABSTRACT

This project investigated the feasibility of programming the Khepera II robot for autonomous navigation and exploration using the hybrid robot architecture. At the deliberative layer of the system, the D* Lite algorithm was implemented to find the shortest path between a starting and a destination state, and to perform efficient re-planning during exploration. At the reactive layer, instructions along the shortest path are executed one instruction at a time. Each instruction is executed by following a behavior until a terminator state is reached. Robot exploration is activated when an unexpected world situation is detected along the navigation path. This information is fed to the deliberative layer where the map is updated, and the shortest path was recomputed. A separate visualization module was built to monitor the progress of the navigation and exploration progress. The tool provides a real time feed for the state of robot navigation progress.

REFERENCES

• 1: Antonelli, G., Arrichiello, F., and Chiaverini, S., "Experiments of Formation Control with Multi-Robot Systems using the Null-Space-Based Behavioral Control", in Proceedings of the 14th Mediterranean Conference on Control and Automation, pp. 1--6, 2006.
• 2: Antonelli, G., Arrichiello, F., and Chiaverini, S., "An Experimental Study of the Entrapment/Escorting Mission for a Multi-Robot System", IEEE Robotics and Automation Magazine. Special Issues on Design, Control, and Applications of Real-World Multi-Robot Systems, vol. 15, n. 1, pp. 22--29, 2008.
• 3: Judith Challinger, Efficient use of robots in the undergraduate curriculum, Proceedings of the 36th SIGCSE technical symposium on Computer science education, February 23-27, 2005, St. Louis, Missouri, USA
• 4: Arieo, A. and Gerstner, W., "Hipppocampal spatial model for state space representation in robotic reinforcement learning", in Proceedings of the fifth European Workshop on Reinforcement learning, 2001, p. 1--3, CKI, Utrecht University, 2001.
• 5: Robert M. Harlan , David B. Levine , Shelley McClarigan, The Khepera robot and the kRobot class: a platform for introducing robotics in the undergraduate curriculum, Proceedings of the thirty-second SIGCSE technical symposium on Computer Science Education, p.105-109, February 2001, Charlotte, North Carolina, United States
• 6: Robert M. Harlan , Shelley McClarigan, Creating emergent behaviors: two robotics labs that combine reactive behaviors, Proceedings of the 36th SIGCSE technical symposium on Computer science education, February 23-27, 2005, St. Louis, Missouri, USA
• 7: Koenig, S. and Likhachev, M., "Improved fast replanning for robot navigation in unknown terrain", in the proceedings of the IEEE International conference on robotics and automation, pp. 968--975, Washington, DC, May 11--15^th, 2002.
• 8: Amruth N. Kumar, Three years of using robots in an artificial intelligence course: lessons learned, Journal on Educational Resources in Computing (JERIC), v.4 n.3, p.2-es, September 2004 [doi>10.1145/1083310.1083311]
• 9: Robin R. Murphy, Introduction to AI Robotics, MIT Press, Cambridge, MA, 2000
• 10: S. Nolfi, D. Floreano, Evolutionary Robotics, MIT Press, 2000.
• 11: Stuart J. Russell , Peter Norvig, Artificial Intelligence: A Modern Approach, Pearson Education, 2003
• 12: Stentz, A., "Optimal and efficient path planning for partially-known environments", in proceedings of the IEEE International conference on robotics and automation, pp. 3310--3317. 1994.
• 13: Stentz, A. "The focused D* algorithm for real-time replanning". In Proceedings of the International Joint Conference on Artificial Intelligence, pp. 1652--1659, 1995.

INDEX TERMS

Primary Classification:
  I. Computing Methodologies
  I.2 ARTIFICIAL INTELLIGENCE
      I.2.9 Robotics

General Terms:
Algorithms, Design, Experimentation

Keywords:
D* lite, navigation, planning, robotics, visualization