Y Z

Class Structure Q Method 0 Property

Fig. 15. Environment information class

The 3D Viewer is the component that displays the simulation process in 3D as seen in Fig. 16. The 3D viewer receives information from the environment manager as input and uses OpenGL to render the simulation process in 3D. OpenGL is the software interface to the graphical hardware allows the generation of objects or computations necessary in producing 3D applications. It can run on various hardware platforms but does not support commands with the ability to generate complex objects and can only generate primitives such as points, lines and polygons. For the representation of complex structures such as geography, obstacles and the autonomous underwater vehicle object, the primitives are combined to build the objects necessary for the simulation.

obstacle map uuv

Fig. 16. 3-D viewer for object obstacle map uuv

Fig. 16. 3-D viewer for object

The Collision Avoidance System, Collision Risk Computation System and the Simulation System were used together in the simulation to test the performance of the presented underwater vehicle's autonomous navigation. For the specifications necessary for the simulation, the autonomous underwater vehicle developed by the Korean Agency for Defense Development was used and is shown in Table 3.

Spec.

Value

Vehicle length/diameter

10 (ratio)

Max speed

8.0kts

Max operation depth

100m

Displacement tonnage

1.380kg

Table 3. Specification of UUV

The underwater vehicle's autonomous navigation system was tested using a scenario where three dynamic obstacles exist. The autonomous underwater vehicle's starting point and destination point were set to S(0,0,-10) and G(0,210,-10), respectively. The first obstacles starting point and destination point were set to 0(-20),150,-10) and 0(13,-60-10), respectively, where it approaches the autonomous underwater vehicle from the front left side. The second obstacle approaches the autonomous underwater vehicle from the rear with the starting point and destination point set to 0(30,-10,-17) and 0(-2,160,-17), and the last obstacle approaches the UUV directly from the front with the starting point and destination point set to 0(0,200,-10) and 0(0,-20,-10), respectively. Fig. 17 shows the actual

Fig. 17. Display of simulation simulation in progress and Fig. 18 shows the results as a map to help understand the simulation results. As shown in the simulation results, the autonomous underwater vehicle detected the first approaching obstacle 0(-11,87,-10) at point P(0,63,-10) and sends an avoidance command to point P(7,84,-17), then continues to avoid the second obstacle 0(18, 58, -17) to point P(-7, 105, -24), and this confirmed that the collision avoidance performed reasonably and efficiently.

(b). Simulation result in view of [Y-Z] axis Fig. 18. Simulation result with scenarios

5. Conclusion

This paper designed a RVC intelligent system model that can be applied to various unmanned vehicles and the underwater vehicle's intelligent autonomous navigation system was designed consisting of a collision avoidance system, a navigation system and a collision risk computation based on a Virtual world system. During the development of the Virtual world system, several points such as the fusion of different techniques, preservation of system consistency, real time system processing etc. were taken into consideration, and since it models a client/server structure, it also has the features of consistency, independence maximization, and load balancing. The RVC intelligent system can be applied not only to autonomous underwater vehicles, but to various autonomous robots such as unmanned aerial vehicles, mobile robots and autonomous submarines. To test the performance of the underwater vehicle's intelligent autonomous navigation system based on this RVC intelligent system model, a 3D simulator was developed, and through a scenario with dynamic obstacles existing in the navigational environment, the validity of the intelligent autonomous navigation system was verified.

6. References

Agre, E. & Chapman, D. (1987). An Implementation of a theory of activity, Proceedings of the

Sixth National Conference on Artificial Intelligence Arkin, R. (1989). Towards the Unification of Navigational Planning and Reactive Control,

Proceeding of the AAAI Spring Symposium on Robot Navigation, Mar. 1989 Bandler, W. & Kohout, L (1980a). Fuzzy Relational Products as a Tool for Analysis and Synthesis of the Behavior of Complex natural and Artificial System, In: Fuzzy Sets: Theory and Application to Analysis and Information Systems, Wang, K, & Chang, P. (Ed.)., (341-367), Plenum Press, New York Bandler, W. & Kohout, L. (1980b). Semantics of Implication Operators and Fuzzy Relational

Products, International Journal of Man-Machine Studies Bandler, W & Kohout L. (1980c). Fuzzy Power Sets and Fuzzy Implication Operator, Fuzzy

Set and System, No. 4, (13-30) Brooks, A. (1986), A robust layered control system for a mobile robot," IEEE Journal of

Robotics and Automation Bui, L. & Kim, Y. (2006). An Obstacle Avoidance Technique for Autonomous Underwater Vehicles Based on BK-Products of Fuzzy Relation, Fuzzy Sets and Systems, Vol. 157, (560-577)

Cliff, D. (1991), A provisional manifesto, Proceedings of the First International Conference on

Simulation of Adaptive Behavior, The MIT Press Hara, K. & Hammer, A. (1993). A safe Way of Collision Avoidance Maneuver based on Maneuvering Standard using Fuzzy Reasoning Model, Proceedings of MARSIM 93, 1993, St. John's

Kim, E. (2001). Collision-risk computation system for collision avoidance. Transaction of

Korean Fuzzy and Intelligent System Association, Vol. 2, (524-527) Kim, Y. (2005). Autonomous ship control system using intelligence techniques, Technical

Report, TECD-417, Korean Agency for Defense Development Kohout, L.; Keravnou, E. & Bandler, W. (1984). Automatic Documentary Information Retrieval by Means of Fuzzy Relational Products, In: Fuzzy Sets in Decision Analysis, Gaines, B. R.; Zadeh, L. A. & Zimmermann, H. J., (Ed.), (308-404), North-Holland, Amsterdam

Kohout, L. & Kim E. (1998). Semiotic descriptors in fuzzy relational computations, Proc IEEE Int Symp Intelligent Control, IEEE Int Symp Computational Intelligence in Robotics and Autonomous and Intelligent Systems and Semiotic (A Joint Conf Science and Technology of Intelligent Systems), pp. 828-833, 1998, Piscataway Kohout L. & Kim E. (2002). The role of BK-products of Relations in Soft Computing, Soft

Computing, Springer-Verlag, No. 6, 92-115 Lee, Y. & Kim, Y. (2001). An Intelligent Navigation System for AUVs using Fuzzy Relational Products, IFSA World Congress and 20th NAFIPS International Conference, Joint 9th, Vol.2 , 709-714

Lee, Y.; Kim, Y. & Kohout, L. (2004). An Intelligent Collision Avoidance System for AUVs using Fuzzy Relational Products, Information Sciences, Vol. 158, 209-232 Lee, Y.; Noe, C. & Kim, Y. (2002).Implication Operators in Fuzzy Relational Products for a Local Path-Planning of AUVs, Proceedings of NAFIPS, Annual Meeting of the North American, Fuzzy Information Processing Society, 22

Ong, M. (1990). A Mission Planning knowledge-based system with Three-Dimensional Path Optimization for the NPS Model 2 Autonomous Underwater Vehicle, Master's Thesis, Naval Postgraduate School Oommen, B. et al. (1987). Robot Navigation in Unknown Terrains Using Learned Visibility Graphs. Part I: The Disjoint Convex Obstacle case, IEEE journal of Robotics and Automation, Vol. RA-3, No. 6, (672-681) Scerri, P. & Reed, N. (1999). Requirements for a General Agent Architecture for Agent-Based Simulation Environments, Agents'99 Workshop on Autonomy Control Software, May, 1999

Turner, R.; Blidberg, R.; Chappell, S. & Jalbert, J. (1993). Generic behaviors: An approach to modularity in intelligent systems control, Proceedings of the 8th International Symposium on Unmanned Untethered Submersible Technology, 1993 Vasudevan, C. & Ganesan, K. (1996). Case-Based path Planning for Autonomous Underwater Vehicles, In: Underwater Robots, Yuh, Ura and Bekey (Eds.), (1-15), Kluwer Academic Publishers, Boston

Learn Photoshop Now

Learn Photoshop Now

This first volume will guide you through the basics of Photoshop. Well start at the beginning and slowly be working our way through to the more advanced stuff but dont worry its all aimed at the total newbie.

Get My Free Ebook


Post a comment