We describe an algorithm which allows a behavior-based robot to learn on the basis of positive and negative feedback when to activate its behaviors. In accordance with the philosophy of behavior-based robots, the algorithm is completely distributed: each of the behaviors independently tries to find out (i) whether it is relevant (ie. whether it is at all correlated to positive feedback) and (ii) what the conditions are under which it becomes reliable (i.e. the conditions under which it maximizes the probability of receiving positive feedback and minimizes the probability of receiving negative feedback). The algorithm has been tested successfully on an autonomous 6-legged robot which had to learn how to coordinate its legs so as to walk forward. Situation of the Problem Since 1985, the MIT Mobile Robot group has advocated a radically different architecture for autonomous intelligent agents (Brooks, 1986). Instead of decomposing the architecture into functional modules, such as percept...

What plans are like depends on how they're used. We contrast two views of plan use. On the plan-as-program view, plan use is the execution of an effective procedure. On the plan-as-communication view, plan use is like following natural language instructions. We have begun work on computational models of plans-as-communications, building on our previous work on improvised activity and on ideas from sociology.

This article describes a methodology for programming robots known as probabilistic robotics. The probabilistic paradigm pays tribute to the inherent uncertainty in robot perception, relying on explicit representations of uncertainty when determining what to do. This article surveys some of the progress in the field, using in-depth examples to illustrate some of the nuts and bolts of the basic approach. Our central conjecture is that the probabilistic approach to robotics scales better to complex real-world applications than approaches that ignore a robot's uncertainty.

This paper describes Minerva, an interactive tour-guide robot that was successfully deployed in a Smithsonian museum. Minerva's software is pervasively probabilistic, relying on explicit representations of uncertainty in perception and control. This article describes

Delayed reinforcement learning is an attractive framework for the unsupervised learning of action policies for autonomous agents. Some existing delayed reinforcement learning techniques have shown promise in simple domains. However, a number of hurdles must be passed before they are applicable to realistic problems. This paper describes one such difficulty, the input generalization problem (whereby the system must generalize to produce similar actions in similar situations) and an implemented solution, the G algorithm. This algorithm is based on recursive splitting of the state space based on statistical measures of differences in reinforcements received. Connectionist backpropagation has previously been used for input generalization in reinforcement learning. We compare the two techniques analytically and empirically. The G algorithm's sound statistical basis makes it easy to predict when it should and should not work, whereas the behavior of backpropagation is unpredictable. We found that a previous successful use of backpropagation can be explained by the linearity of the application domain. We found that in another domain, G reliably found the optimal policy, whereas none of a set of runs of backpropagation with many combinations of parameters did. 1

Abstract not found

This chapter surveys basic methods for learning maps and high speed autonomous navigation for indoor mobile robots. The methods have been developed in our lab over the past few years, and most of them have been tested thoroughly in various indoor environments. The chapter is targeted towards researchers and engineers who attempt to build reliable mobile robot navigation software.

A selective vision system sequentially collects evidence to support a specified hypothesis about a scene, as long as the additional evidence is worth the effort of obtaining it. Efficiency comes from processing the scene only where necessary, to the level of detail necessary, and with only the necessary operators. Knowledge representation and sequential decision-making are central issues for selective vision, which takes advantage of prior knowledge of a domain's abstract and geometrical structure and models for the expected performance and cost of visual operators. The TEA-1 selective vision system uses Bayes nets for representation and benefitcost analysis for control of visual and non-visual actions. It is the high-level control for an active vision system, enabling purposive behavior, the use of qualitative vision modules and a pointable multiresolution sensor. TEA-1 demonstrates that Bayes nets and decision theoretic techniques provide a general, re-usable framework for constructi...

. Specifying a reactive behavioral configuration for use by a multiagent team requires both a careful choice of the behavior set and the creation of a temporal chain of behaviors which executes the mission. This difficult task is simplified by applying an object-oriented approach to the design of the mission using a construction called an assemblage and a methodology called temporal sequencing. The assemblage construct allows building high level primitives which provide abstractions for the designer. Assemblages consist of groups of basic behaviors and coordination mechanisms that allow the group to be treated as a new coherent behavior. Upon instantiation, the assemblage is parameterized based on the specific mission requirements. Assemblages can be re-parameterized and used in other states within a mission or archived as high level primitives for use in subsequent projects. Temporal sequencing partitions the mission into discrete operating states with perceptual triggers causing tra...

Introduction Despite considerable diversity among theories about how humans process language, there are a number of fundamental assumptions which are shared by most such theories. This consensus extends to the very basic question about what counts as a cognitive process. So although many cognitive scientists are fond of referring to the brain as a `mental organ' (e.g., Chomsky, 1975)---implying a similarity to other organs such as the liver or kidneys---it is also assumed that the brain is an organ with special properties which set it apart. Brains `carry out computation' (it is argued)