|
|
|
|
|
|
|
Abstract
As robots move out of factory based (and other) structured environments, richer sensory data and larger amounts of Artificial Intelligence are required to cope with the varying degrees of unstructuredness (uncertainty). Currently there are many operational environments which are too complex to permit fully autonomous robotic functionality or where the expense of providing such a capability is not yet justifiable. Teleoperation and Tele-Autonomous modes of control can often provide useful solutions whilst progress towards full automation is being realised incrementally. One consistent approach to developing useful mobile systems for supporting practical applications such as search and rescue and bushfire fighting (amongst many others) is to study the requirements of full autonomy, assess the viability of providing such capability and then stepping back from this extreme to include human judgement based intervention where either needed or regarded as cost effective.
This strategy has the advantage of being able to provide a useful capability here and now whilst allowing (gracefully) for future developments in sensor quality and affordability, computational power at low cost and new methodologies to move the application solution to full automation without sacrificing reliability.
This presentation will outline the basic ingredients of outdoor mobile robot navigation systems (subject to the modalities of teleoperation to full autonomy) and illustrate these concepts and methodologies using case studies.
A number of robotic vehicle projects (within the Intelligent Robotics Research Centre at Monash University), including work on an excavator, a Martian rover model, an amphibious vehicle, a heavy duty tracked vehicle and several water craft will provide these case studies which will be illustrated with video clip sequences.
The current potential for establishing new Australian industries based upon the developments of outdoor robot navigation systems will be promoted.
Short Biographical Note
Ray Jarvis completed his BE (Elec.) and Ph.D. (Elec.) at the University of Western Australian in 1962 and 1968, respectively. After two years at Purdue University he was appointed to the Australian National University (ANU) to teach Computer Science. He was instrumental in establishing the Department of Computer Science at ANU and was its first Head of Department. He joined Monash University in 1985 and established the Intelligent Robotic Research Centre in 1987. He has been the Centre's Director since then. His research interests are in Computer Vision and Robotics. Both robotic manipulators and mobile robots of various sizes have been part of his interests. Most recently he has been working on autonomous and teleoperated vehicles and vessels including a tacked vehicle, several boats, an amphibious craft, an excavator and a half scale Russian built Martian Rover. He has also recently developed a research interest in Humanoid Robotics. From an AI perceptive his main interest are in Computer Vision and Path Planning.
Limited progress toward a realization of deduction capability is achievable through application of methods based on bivalent logic and standard probability theory. But to move beyond the reach of standard methods it is necessary to change direction. In the approach which is outlined, a concept which plays a pivotal role is that of a prototype -- a concept which has a position of centrality in human reasoning, recognition, search and decision processes.
Informally, a prototype may be defined as a sigma-summary, that is, a summary of summaries. With this definition as the point of departure, a prototypical form, or protoform, for short, is defined as an abstracted prototype. As a simple example, the protoform of the proposition "Most Swedes are tall" is "QA's are B's," where Q is a fuzzy quantifier, and A and B are labels of fuzzy sets.
Abstraction has levels, just as summarization does. For example, in the case of "Most Swedes are tall," successive abstracted forms are "Most A's are tall," "Most A's are B's" and "QA's are B's."
At a specified level of abstraction, propositions are PF-equivalent if they have identical protoforms. For example, propositions "Usually Robert returns from work at about 6 pm" and "In winter, the average daily temperature in Berkeley is usually about fifteen degrees centigrade," are PF-equivalent. The importance of the concepts of protoform and PF-equivalence derives in large measure from the fact that they serve as a basis for knowledge compression.
A knowledge base is assumed to consist of a factual database, FDB, and a deduction database, DDB. In both FDB and DDB, knowledge is assumed to fall into two categories: (a) crisp and (b) fuzzy. Examples of crisp items of knowledge in FDB might be: "The height of the Eiffel tower is 324m" and "Paris is the capital of France." Examples of fuzzy items might be "Most Swedes are tall," and "California has a temperate climate." Similarly, in DDB, an example of a crisp rule might be "If A and B are crisp convex sets, then their intersection is a crisp convex set." An example of a fuzzy rule might be "If A and B are fuzzy convex sets, then their intersection is a fuzzy convex set."
The deduction database is assumed to consist of a logical database and a computational database, with the rules of deduction having the structure of protoforms. An example of a computational rule is "If Q A's are B's and Q (A and B)'s are C's," then "Q Q A's are (B and C)'s," where Q and Q are fuzzy quantifiers, and A, B and C are labels of fuzzy sets. The number of rules in the computational database is assumed to be very large in order to allow a chaining of rules that may be query-relevant.
A very simple example of deduction in the prototype-centered approach-an example which involves string matching but no chaining -- is the following. Suppose that a query is "How many Swedes are very tall?" A protoform of this query is: ?Q A's are B, where Q is a fuzzy quantifier and B is assumed to represent the meaning of "very B," with the membership function of B being the square of the membership function of B. Searching DDB, we find the rule "If Q A's are B then Q A's are B," whose consequent matches the query, with ?Q instantiated to Q , A to "Swedes" and B to "tall." Furthermore, in FDB, we find the fact "Most Swedes are tall," which matches the antecedent of the rule, with Q instantiated to "Most." A to "Swedes" and B to "tall." Consequently, the answer to the query is "Most Swedes are very tall," where the membership function of "Most " is the square root of Most in fuzzy arithmetic.
The concept of a prototype is intrinsically fuzzy. For this reason, the prototype-centered approach to deduction is based on fuzzy logic and perception-based theory of probabilistic reasoning, rather than on bivalent logic and standard probability theory.
What should be underscored is that the problem of adding deduction capability to search engines is many-faceted and complex. It would be unrealistic to expect rapid progress toward its solution.
Biography
Lotfi A. Zadeh is Professor in the Graduate School and director,
Berkeley initiative in Soft Computing (BISC),
Computer Science Division and the Electronics Research Laboratory,
Department of EECS,
University of California,
Berkeley, CA 94720-1776;
Telephone: 510-642-4959;
Fax: 510-642-1712;
Research supported in part by
ONR Contract N00014-99-C-0298,
NASA Contract NCC2-1006,
NASA Grant NAC2-117,
ONR Grant N00014-96-1-0556,
ONR Grant FDN0014991035,
ARO Grant DAAH 04-961-0341
and the BISC Program of UC Berkeley.