Vision based mobile robot guidance has proven difficult for classical machine vision methods because of the diversity and real time constraints inherent in the task. This thesis describes a connectionist system called ALVINN (Autonomous Land Vehicle In a Neural Network) that overcomes these difficulties. ALVINN learns to guide mobile robots using the back-propagation training algorithm. Because of its ability to learn from example, ALVINN can adapt to new situations and therefore cope with the diversity of the autonomous navigation task. But real world problems like vision based mobile robot guidance presents a different set of challenges for the connectionist paradigm.

. It is argued that Situated Agents should be designed using a unitaryon-line computational model. The Constraint Net model of Zhang and Mackworth satisfiesthat requirement. Two systems for situated perception built in our laboratory are describedto illustrate the new approach: one for visual monitoring of a robot’s arm, the other forreal-time visual control of multiple robots competing and cooperating in a dynamic world.First proposal for robot soccer.Proc. VI-92, 1992. later published in a book Computer Vision: System, Theory, and Applications, pages 1-13, World Scientific Press, Singapore, 1993.

In AAAI-92, pp. 816–822.

Tech. rep. Papers from the AAAI Robot Competition, RC-92-01, American Association for Artificial Intelligence.

In ECAI-92, pp. 689–693.

At the control level, distinctive places and distinctive travel edges are identified based on the interaction between the robot's control strategies, its sensorimotor system, and the world. A distinctive place is defined as the local maximum of a distinctiveness measure appropriate to its immediate neighborhood, and is found by a hill-climbing control strategy. A distinctive travel edge, similarly, is defined by a suitable measure and a path-following control strategy. The topological network description is created by linking the distinctive places and travel edges. Metrical information is then incrementally assimilated into local geometric descriptions of places and edges, and finally merged into a global geometric map.

IEEE Transactions on Robotics and Automation, 7 (3), 278-88

AAAI-90.

"We describe a robot control architecture which combines a stimulus-response subsystem for rapid reaction, with a search-based planner for handling unanticipated situations. The robot agent continually chooses which action it is to perform, using the stimulusresponse subsystem when possible, and falling back on the planning subsystem when necessary. Whenever it is forced to plan, it applies an explanation-based learning mechanism to formulate a new stimulus-response rule to cover this new situation and others similar to it. With experience, the agent becomes increasingly reactive as its learning component acquires new stimulus-response rules that eliminate the need for planning in similar subsequent situations. This Theo-Agent architecture is described, and results are presented demonstrating its ability to reduce routine reaction time for a simple mobile robot from minutes to under a second."In AAAI-90, Vol. 2, pp. 1051– 1058

This article presents an algorithm for autonomous map building and maintenance for a mobile robot. We believe that mobile robot navigation can be treated as a problem of tracking ge ometric features that occur naturally in the environment. We represent each feature in the map by a location estimate (the feature state vector) and two distinct measures of uncertainty: a covariance matrix to represent uncertainty in feature loca tion, and a credibility measure to represent our belief in the validity of the feature. During each position update cycle, pre dicted measurements are generated for each geometric feature in the map and compared with actual sensor observations. Suc cessful matches cause a feature's credibility to be increased.