A. Saffiotti, E. H. Ruspini, and K. Konolige, Using Fuzzy Logic for Mobile Robot Control, in Zimmermann, H. J., editor, Practical Applications of Fuzzy Technologies, Kluwer Academic Publisher, pages 185-206, 1999.  Home/Search   Document Details and Download   Summary   Related Articles   Check

.... values of a dynamical system type BBS are well suited for fact extraction in that their formal background in dynamical systems theory provides both the motivation and the mathematical inventory to make them change smoothly over time compare, e.g. the curves in Figure 3 with the ragged ones in [SRK99, Fig. 5.10] This typical smoothness is handy for defining qualitative activations, which aggregate particular patterns in terms of edges and levels of the curves of individual behaviors, which are recorded as they emerge over time. These then serve as a stable basis for chronicle recognition ....

....planner instead of coding all goal directed knowledge directly into the BBS makes it much easier to define and change high level mission goals and to communicate plans between agents. Most robot control architecture used a kind of situation depending context called context dependend blending [SRK99] or sensor context [SS98] which helps regulating the behavior activation. DD P supports this context via activation value biasing in a very flexible way without touching the BBS description. Validation of the overall architecture is even easier with a clear view on the operator that is ....

A. Saffiotti, E.H. Ruspin, and K. Konolige. Using fuzzy logic for mobile robot control. In H-J. Zimmermann, editor, Practical Applications of Fuzzy Technologies, chapter 5, pages 185--205. Kluwer Academic, 1999. Handbook of Fuzzy Sets, vol.6.

.... of a dynamical system type BBS are well suited for fact extraction in that their formal background in dynamical systems theory provides both the motivation and the mathematical inventory to make them change smoothly over time compare, e.g. the curves in Figures 3 and 4 with the ragged ones in [SRK99, Fig. 5.10] This typical smoothness is handy for defining qualitative activations, which aggregate particular patterns in terms of edges and levels of the curves of individual behaviors, which are recorded as they emerge over time. These then serve as a stable basis for chronicle recognition ....

A. Saffiotti, E.H. Ruspini, and K. Konolige. Using fuzzy logic for mobile robot control. In H-J. Zimmermann, editor, Practical Applications of Fuzzy Technologies, chapter 5, pages 185--205. Kluwer Academic, 1999. Handbook of Fuzzy Sets, vol.6.

....regions and designing a Kalman filter for each region. The filter estimates the true depth of each region by propagating an assumed conditional probability density function from sometime, arbitrary deep in the past, up to the present time. In applying fuzzy control we depart from Saffiotti et al. [13] by discarding the context blender. Here we build a clean monolithic rule bank for an atomic task. Our controller has 1000 fuzzy rules and two crisp outputs. The outputs of the controller are motor velocity and jograte. The implemented controller has successfully steered both the TRC mobile robot ....

....Borenstein et al. 1] have eliminated the noise due to sensor crosstalk using a special sensor firing scheme called (EERUF) However, their method is not easily transferable to a system, such as ours, where both firing sequence and firing intervals are hardware fixed. Perhaps our work is close to [13] who implement a hierarchical fuzzy control architecture, similar to [4] on the Flakey. They decomposed the overall control into a number of modules, which they call fuzzy behaviors, and have used a context dependent blending scheme to combine behaviors outputs. But we argue that in fuzzy logic, ....

[Article contains additional citation context not shown here]

Alessandro Saffiotti, Enrique H. Ruspini, and Kurt Konolige. Using fuzzy logic for mobile robot control. In D. Dubois, H. Prade, and H.J. Zimmermann, editors, Handbook of Fuzzy Sets and Possibility Theory. Kluwer Academic, 1997.

....and precision of mathematical or logical models. Fuzzy control (FC) provides a flexible tool to model the relationship among input information and control output. For some years FLCs are used for a variety of complex control problems [BONI96] MAR94] including the control of mobile robots [BEO95][SAF97][SUR95] YEN95] They are distinguished by their robustness with respect to noise and variations of system parameters. GAs are optimization methods guided by the principles of natural evolution, which they simulate in a computer environment [GOL89a] HOL92] They imitate the underlying genetic ....

....model are afterwards tested on the mobile robot in order to verify if they are robust enough to deal 13 with real world situations as well. If both behaviours come into conflict, the decision process has to resolve, which of the control outputs to apply in the actual context. Saffiotti et al. [SAF97] add a context restriction to each rule, which defines the importance of a goal and mission of the agent or the environmental context, for a behaviour. The overall behaviour of the agent emerges from this contextdependent blending of basic behaviours. Bonarini et al. BONA96b] developed S ELF ....

A. Saffiotti, E. H. Ruspini, K .Konolige, "Using Fuzzy Logic for Mobile Robot Control", in D. Dubois, H. Prade, H. J. Zimmermann (Eds. ), Handbook of Fuzzy Sets and Possibility Theory, Kluwer Academic, forthcoming.

....a high level missionplanning element invokes low level perception motion elements and interprets their outcomes. It is able to navigate reactively at high speeds of 300mm sec, however it does not have vision capabilities and relies on artificial markers to recognize objects. The scope of the FLAKEY(Saffiotti et al. 1997) and XAVIER(Nourbakhsh et al. 1993) projects is much larger than DAVID s. We should mention however, that FLAKEY, due to the inherently parallel nature of fuzzy control, has a more distributed architecture with a quite extended range of capabilities, such as object recognition, people tracking, ....

A. Saffiotti, E.H. Ruspini, K. Konolige. Using Fuzzy Logic for Mobile Robot Control. In Int. Handbook of Fuzzy Sets and Possibility Theory. D. Dubois, H. Prade and H.J. Zimmermann (Eds.), Kluwer Academic, forthcoming 1997.

No context found.

A. Saffiotti, E.H. Ruspini, and K. Konolige. Using fuzzy logic for mobile robot control. In H. Prade D. Dubois and H.J. Zimmermann, editors, International Handbook of Fuzzy Sets and Possibility Theory, volume 5. Kluwer Academic, Norwell, MA, 1997. Forthcoming.

No context found.

A. Saffiotti, E. H. Ruspini, and K. Konolige, Using Fuzzy Logic for Mobile Robot Control, in Zimmermann, H. J., editor, Practical Applications of Fuzzy Technologies, Kluwer Academic Publisher, pages 185-206, 1999.

No context found.

Saffiotti, A., Ruspini, E.H. and Konolige, K., "Using Fuzzy Logic for Mobile Robot Control", in International Handbook of Fuzzy Sets and Possibility Theory (Dubois D, Prade H. and Zimmermann H.J. Eds.), Kluwer Academic, 1997.

No context found.

Saotti, A., Ruspini, H., and K.Konolige (1999). Using fuzzy logic for mobile robot control. In International Handbook of Fuzzy Sets and Possibility Theory. Kluwer Academic Publisher.

No context found.

A. Saffioti, E. Ruspini, and K. Konolige, "Using Fuzzy Logic for Mobile Robot Control," Handbook of Fuzzy Sets and Possibility Theory, Kluwer Academic, 1997.

Online articles have much greater impact   More about CiteSeer.IST   Add search form to your site   Submit documents   Feedback  

CiteSeer.IST - Copyright Penn State and NEC