Maja J. Matarić

Mobile Sensor Network Deployment using Potential Fields: A Distributed, Scalable Solution to the Area Coverage Problem

This paper considers the problem of deploying a mobile sensor network in an unknown environment. A mobile sensor network is composed of a distributed collection of nodes, each of which has sensing, computation, communication and locomotion capabilities. Such networks are capable of self-deployment; i.e., starting from some compact initial configuration, the nodes in the network can spread out such that the area ‘covered’ by the network is maximized. In this paper, we present a potential-field-based approach to deployment. The fields are constructed such that each node is repelled by both obstacles and by other nodes, thereby forcing the network to spread itself throughout the environment. The approach is both distributed and scalable.

Sold!: auction methods for multirobot coordination

The key to utilizing the potential of multirobot systems is cooperation. How can we achieve cooperation in systems composed of failure-prone autonomous robots operating in noisy, dynamic environments? We present a method of dynamic task allocation for groups of such robots. We implemented and tested an auction-based task allocation system which we call MURDOCH, built upon a principled, resource centric, publish/subscribe communication model. A variant of the Contract Net Protocol, MURDOCH produces a distributed approximation to a global optimum of resource usage. We validated MURDOCH in two very different domains: a tightly coupled multirobot physical manipulation task and a loosely coupled multirobot experiment in long-term autonomy. The primary contribution of the paper is to show empirically that distributed negotiation mechanisms such as MURDOCH are viable and effective for coordinating physical multirobot systems.

An Incremental Self-Deployment Algorithm for Mobile Sensor Networks

This paper describes an incremental deployment algorithm for mobile sensor networks. A mobile sensor network is a distributed collection of nodes, each of which has sensing, computation, communication and locomotion capabilities. The algorithm described in this paper will deploy such nodes one-at-a-time into an unknown environment, with each node making use of information gathered by previously deployed nodes to determine its deployment location. The algorithm is designed to maximize network ‘coverage’ while simultaneously ensuring that nodes retain line-of-sight relationships with one another. This latter constraint arises from the need to localize the nodes in an unknown environment: in our previous work on team localization (A. Howard, M.J. Matarić, and G.S. Sukhatme, in Proceedings of the IEEE/RSJ International Conference on Intelligent Robots and Systems, EPFL, Switzerland, 2002; IEEE Transactions on Robotics and Autonomous Systems, 2002) we have shown how nodes can localize themselves by using other nodes as landmarks. This paper describes the incremental deployment algorithm and presents the results from an extensive series of simulation experiments. These experiments serve to both validate the algorithm and illuminate its empirical properties.

Integration of representation into goal-driven behavior-based robots

An architecture that integrates a map representation into a reactive, subsumption-based mobile robot is described. This fully integrated reactive system removes the distinction between the control program and the map. The method was implemented and tested on a mobile robot equipped with a ring of sonars and a compass, and programmed with a collection of simple, incrementally designed behaviors. The robot performs collision-free navigation, dynamic landmark detection, map construction and maintenance, and path planning. Given any known landmark as a goal, the robot plans and executes the shortest known path to it. If the goal is not reachable, the robot detects failure, updates the map, and finds an alternate route. The topological representation primitives are designed to suit the robots sensors and its navigation behavior, thus minimizing the amount of stored information. Distributed over a collection of behaviors, the map itself performs constant-time localization and linear-time path planning. The approach is qualitative and robust. >

Behaviour-based control: examples from navigation, learning, and group behaviour

This paper describes the main properties of behaviour-based approaches to control. Different approaches to designing and using behaviours as basic units for control, representation, and learning are illustrated on three empirical examples of robots performing navigation and path-finding, group behaviours, and learning behaviour selection.

Most valuable player: a robot device server for distributed control

Successful distributed sensing and control require data to flow effectively between sensors, processors and actuators on single robots, in groups and across the Internet. We propose a mechanism for achieving this flow that we have found to be powerful and easy to use; we call it Player. Player combines an efficient message protocol with a simple device model. It is implemented as a multithreaded TCP socket server that provides transparent network access to a collection of sensors and actuators, often comprising a robot. The socket abstraction enables platform- and language-independent control of these devices, allowing the system designer to use the best tool for the task at hand Player is freely available from http://robotics.usc.edu/player.

A general algorithm for robot formations using local sensing and minimal communication

We study the problem of achieving global behavior in a group of distributed robots using only local sensing and minimal communication, in the context of formations. The goal is to have N mobile robots establish and maintain some predetermined geometric shape. We report results from extensive simulation experiments, and 40+ experiments with four physical robots, showing the viability of our approach. The key idea is that each robot keeps a single friend at a desired angle /spl theta/, using some appropriate sensor. By panning the sensor by /spl theta/ degrees, the goal for all formations becomes simply to center the friend in the sensors field of view. We also present a general analytical measure for evaluating formations and apply it to the position data from both simulation and physical robot experiments. We used two lasers to track the physical robots to obtain ground truth validation data.

Reinforcement learning in the multi-robot domain

This paper describes a formulation of reinforcement learning that enables learning in noisy, dynamic environments such as in the complex concurrent multi-robot learning domain. The methodology involves minimizing the learning space through the use of behaviors and conditions, and dealing with the credit assignment problem through shaped reinforcement in the form of heterogeneous reinforcement functions and progress estimators. We experimentally validate the approach on a group of four mobile robots learning a foraging task.

Defining socially assistive robotics

This paper defines the research area of socially assistive robotics, focusing on assisting people through social interaction. While much attention has been paid to robots that provide assistance to people through physical contact (which we call contact assistive robotics), and to robots that entertain through social interaction (social interactive robotics), so far there is no clear definition of socially assistive robotics. We summarize active social assistive research projects and classify them by target populations, application domains, and interaction methods. While distinguishing these from socially interactive robotics endeavors, we discuss challenges and opportunities that are specific to the growing field of socially assistive robotics.

Robots for Use in Autism Research

Autism spectrum disorders are a group of lifelong disabilities that affect peoples ability to communicate and to understand social cues. Research into applying robots as therapy tools has shown that robots seem to improve engagement and elicit novel social behaviors from people (particularly children and teenagers) with autism. Robot therapy for autism has been explored as one of the first application domains in the field of socially assistive robotics (SAR), which aims to develop robots that assist people with special needs through social interactions. In this review, we discuss the past decades work in SAR systems designed for autism therapy by analyzing robot design decisions, human-robot interactions, and system evaluations. We conclude by discussing challenges and future trends for this young but rapidly developing research area.