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...

This paper presents control and coordination algorithms for groups of vehicles. The focus is on autonomous vehicle networks performing distributed sensing tasks where each vehicle plays the role of a mobile tunable sensor. The paper proposes gradient descent algorithms for a class of utility functions which encode optimal coverage and sensing policies. The resulting closed-loop behavior is adaptive, distributed, asynchronous, and verifiably correct.

Abstract. Multiple cooperating robots are able to complete many tasks more quickly and reliably than one robot alone. Communication between the robots can multiply their capabilities and e ectiveness, but to what extent? In this research, the importance of communication in robotic societies is investigated through experiments on both simulated and real robots. Performance was measured for three di erent types of communication for three di erent tasks. The levels of communication are progressively more complex and potentially more expensive to implement. For some tasks, communication can signi cantly improve performance, but for others inter-agent communication is apparently unnecessary. In cases where communication helps, the lowest level of communication is almost as e ective as the more complex type. The bulk of these results are derived from thousands of simulations run with randomly generated initial conditions. The simulation results help determine appropriate parameters for the reactive control system which was ported for tests on Denning mobile robots.

A formalism is presented for computing and organizing actions for autonomous agents in dynamic environments. We introduce the notion of teleo-reactive (T-R) programs whose execution entails the construction of circuitry for the continuous computation of the parameters and conditions on which agent action is based. In addition to continuous feedback, T-R programs support parameter binding and recursion. A primary di erence between T-R programs and many other circuit-based systems is that the circuitry of T-R programs is more compact; it is constructed at run time and thus does not have toanticipate all the contingencies that might arise over all possible runs. In addition, T-R programs are intuitive and easy to write and are written in a form that is compatible with automatic planning and learning methods. We brie y describe some experimental applications of T-R programs in the control of simulated and actual mobile robots. 1.

This paper presents a novel approach to the problem of action selection for an autonomous agent. An agent is viewed as a collection of com- petence modules. Action selection is modeled as an emergent property of an activation/inhibition dynamics among these modules. A con- crete action selection algorithm is presented and a detailed account of the results is given. This algorithm combines characteristics of both traditional planners and reactive systems: it produces fast and robust activity in a tight interaction loop with the environment, while at the same time allowing for some prediction and planning to take place. It provides global parameters, which one can use to tune the action selection behavior to the characteristics of the task environment. As such one can smoothly trade off goal-orientedness for situation-orientedness, bias towards ongoing plans (inertia) for adaptivity, thoughtfulness for speed, and adjust its sensitivity to goal conflicts.

One category of researchers in artificial life is concerned with modeling and building so-called adaptive autonomous agents. Autonomous agents are systems that inhabit a dynamic, unpredictable environment in which they try to satisfy a set of time-dependent goals or motivations. Agents are said to be adaptive if they improve their competence at dealing with these goals based on experience. Autonomous agents constitute a new approach to the study of artificial intelligence (AI) which is highly inspired by biology, in particular ethology, the study of animal behavior. Research in autonomous agents has brought about a new wave of excitement into the field of AI. This paper reflects on the state of the art of this new approach.

This paper describes the main properties of behavior-based approaches to control. Different approaches to designing and using behaviors as basic units for control, representation, and learning are illustrated on three empirical examples of robots performing navigation and path-finding, group behaviors, and learning behavior selection. 1 Introduction An architecture provides a set of principles for organizing control systems. In addition to supplying structure, it imposes constraints on the way control problems can be solved. In this paper we explore the constraints of behavior-based approaches to control, and demonstrate them on three architectures that were used to implement robots that successfully performed navigation and pathfinding, group behaviors, and learning of behavior selection. In each case, we focus on the different ways behaviors are defined, modularized, and combined. This paper is organized as follows. Section 2 gives an overview of basic approaches to autonomous agent...

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.

Adaptive Execution in Complex Dynamic Worlds Robert James Firby Yale University 1989 A robot acting in the real world must use flexible plans because actions will sometimes fail to produce desired effects, and unexpected events will sometimes demand the robot shift its attention. A plan is usually construed as a list of primitive robot actions to be executed one after another but in a complex domain, a plan must be structured to cope effectively with the myriad unpredictable details it will encounter during execution. However, adding structure to a plan involves more than augmenting the primitive plan representation; it requires a complete model of interaction with the world called situation-driven execution. Situation-driven execution assumes that a plan consists of tasks with three major components: a satisfaction test, a window of activity, and a set of execution methods that are appropriate in different circumstances. Execution of such a plan proceeds by selecting an unsatisfied t...

The development of reasoning systems that can reason and plan in a continuously changing environment is emerging as an important area of research in Artificial Intelligence. This paper describes some of the features of a Procedural Reasoning System (PRS) that enables it to operate e ectively in such environments. The basic system design is first described and it is shown how this architecture supports both goal-directed reasoning and the ability toreact rapidly to unanticipated changes in the environment. The decision-making capabilities of the system are then discussed and it is indicated how the system integrates these components in a manner that takes account of the bounds on both resources and knowledge that typify most real-time operations. The system has been applied to handling malfunctions on the space shuttle, threat assessment, and the control of an autonomous robot.