Effective task allocation is an essential component to the coordination of heterogeneous robots. This paper proposes a hybrid task allocation algorithm that improves upon given initial solutions, for example from the popular decentralized market-based allocation algorithm, via a derivative-free optimization strategy called Speeding-Up and Slowing-Down (SUSD). Based on the initial solutions, SUSD performs a search to find an improved task assignment. Unique to our strategy is the ability to apply a gradient-like search to solve a classical integer-programming problem. The proposed strategy outperforms other state-of-the-art algorithms in terms of total task utility and can achieve near optimal solutions in simulation. Experimental results using the Robotarium are also provided.

Expanding our work in understanding the relationships maintained in teams of humans and robots, this talk describes research on deception and its application within robotic systems. Earlier we explored the use of psychology as the basis for producing deceit in robotic systems in order to evade capture. More recent work involves studying squirrel hoarding and bird mobbing behavior as it applies to deception, in the first case for misleading a predator, and in the second for feigning strength when none exists. Next, we discuss other-deception, where deceit is performed for the benefit of the mark. Finally, newly completed research on team deception where groups of agents using shills that serve to mislead others is presented. Results are presented in both simulation and simple robotic systems, as well as consideration of the ethical implications of this research.

Leveraging both the autonomy of robots and the expert knowledge of humans can enable a multi-robot system to complete missions in challenging environments with a high degree of adaptivity and robustness. This paper proposes a multi-modal task-based graphical user interface for controlling a heterogeneous multi-robot team. The core of the interface is an integrated multi-robot task allocation system to allow the user to encode his/her intents to guide the heterogeneous multi-robot team. The design of the interface aims to provide the human operator continuous situational awareness and effective control for rapid decision-making in time-critical missions. Team CSIRO Data61 came in second place utilizing this interface for the DARPA Subterranean (SubT) Challenge. The ideas used for this user interface can apply to other multi-robot applications.

When disagreements arise in hierarchical relationships, relationship members sometimes prefer conflict management strategies that avoid or quickly end the overt conflict even if the relationship is left in a state of dissatisfaction. Our lab has proposed that a peripheral robotic agent may be able to support these types of relationships during conflict. In this paper, we present the results of an IRB-approved human-robot interaction study that examines how the members of a hierarchical relationship involved in conflict respond to the presence of an unengaged robot. This study serves as a baseline for additional studies. The unengaged robot appears to have a minimal influence on the interaction. The observed conflicts followed the patterns typically described in mediation literature. Our lab previously proposed a computational model to identify weakness and alienation in these relationships. We discuss a partial implementation of this model, and its ability to recognize problems in certain relationships within the data collected. Based on our observations, and the performance of the model's partial implementation, we suggest considerations that need to be made for an intervening robotic agent.

A robot mediator can enhance the quality of patient care in a health care context. Patients with Parkinson's disease can experience difficulties in precisely expressing their emotions due to the loss of control of their facial musculature, leading to their stigmatization by caregivers. To remedy this challenge, a robot mediator can be inserted into a patient-caregiver relationship. In this context, it is essential to handle the ethical issues of neglect to ensure human dignity. In an earlier paper [19], we proposed an intervening ethical governor (IEG) model, which enables a robot to ethically intervene in a situation where patients or caregivers go across accepted ethical boundaries. In this paper, we show how the IEG model can be implemented and applied in a real robotics system. In addition, by conducting interviews with the target population (adults 60 years of age or older), we evaluate the current intervention rules in the model, discuss potential improvements to the model, and consider uses of the model in real clinical contexts.

A key challenge in the automatic verification of robot mission software, especially critical mission software, is to be able to effectively model the performance of a human operator and factor that into the formal performance guarantees for the mission. We present a novel approach to modelling the skill level of the operator and integrating it into automatic verification using a linear Gaussians model parameterized by experimental calibration. Our approach allows us to model different skill levels directly in terms of the behavior of the lumped, robot plus operator, system. Using MissionLab and VIPARS (a behavior-based robot mission verification module), we present a comparison of our predicted performance guarantees for two missions in which a teleoperated quadrotor identifies a target for an autonomous ground robot to intercept: one mission in which the operator flies the quadrotor by line of sight to locate the target and one where the operator flies the quadrotor using its video feed. We demonstrate the effectiveness of our approach by comparing predicated performance to experimentally measured performance.

Localization and mapping algorithms can allow a robot to navigate well in an unknown environment. However, whether such algorithms enhance any specific robot mission is currently a matter for empirical validation. In this paper we apply our MissionLab/VIPARS mission design and verification approach to an autonomous robot mission that uses probabilistic localization software. Two approaches to modeling probabilistic localization for verification are presented: a high-level approach, and a sample-based approach which allows run-time code to be embedded in verification. Verification and experimental validation results are presented for two different missions, each using each method, demonstrating the accuracy of verification, and both are compared with verification of an odometry-only mission, to show the mission-specific benefit of localization.

Previously, our lab has hypothesized that a peripheral social robot may be able to help uphold the dignity of Parkinson's patients who are stigmatized by their caregivers. The presence of a robotic agent is liable to influence the patient-caregiver relationship. Patient self-disclosure is a key element of a healthy patient-caregiver relationship. This new study examined how the apparent attentiveness of a peripheral robot influences personal disclosure during a scripted interview. The study did not draw from a patient-caregiver population and was conducted as a Wizard of Oz study. The attentiveness of the robot did not make a difference in the interviewees' depth of disclosure. Self-report measures indicated a difference between the attentive robot condition and the other two conditions when participants were asked if they felt like the robot was listening to them.

Examines the technology of autonomous systems and explores its ethical and social implications. Artificial intelligence (AI) and its role in autonomous systems have promised everything from utopian freedom to existential dystopia. The unfilled hyperbole surrounding past and present promises regarding AI futures has left many people skeptical, afraid, or just confused. Rational discussion is often left in the wake due to the fears and fantasy evoked by the press and Hollywood. Fortunately, as a byproduct, this has resulted in a blossoming of worldwide discourse on the ethical implications of the intelligent machines we are creating. Many near and mid-term ethical concerns have arisen with the advent of autonomous systems: particularly regarding driverless cars, privacy and drones, companion- and intimate robotics, the displacement of jobs by intelligent machines, and warfighting robots among others. The IEEE Global Initiative on the Ethics of Autonomous Systems, the United Nations, the International Committee of the Red Cross, the White House, and the Future of Life Institute are among many responsible organizations that are now considering the ramifications of the real-world consequences of machine autonomy as we continue to stumble about trying to find a way forward.

The effective use of autonomous robot teams in highly-critical missions depends on being able to establish performance guarantees. However, establishing a guarantee for the behavior of an autonomous robot operating in an uncertain environment with obstacles is a challenging problem. This paper addresses the challenges involved in building a software tool for verifying the behavior of a multi-robot waypoint mission that includes uncertain environment geometry as well as uncertainty in robot motion. One contribution of this paper is an approach to the problem of a-priori specification of uncertain environments for robot program verification. A second contribution is a novel method to extend the Bayesian Network formulation to reason about random variables with different subpopulations, introduced to address the challenge of representing the effects of multiple sensory histories when verifying a robot mission. The third contribution is experimental validation results presented to show the effectiveness of this approach on a two-robot, bounding overwatch mission.

The objectives of this article are: 1) to present a taxonomy for mixed-initiative human-robot interaction and 2) to survey its state of practice through the examination of past research along each taxonomical dimension. The paper starts with some definitions of mixed-initiative interaction (MII) from the perspective of human-computer interaction (HCI) to introduce the basic concepts of MII. We then synthesize these definitions to the robotic context for mixed-initiative human robot teams. A taxonomy for mixed-initiative in human-robot interaction is then presented. The goal of the taxonomy is to inform the design of mixed-initiative human-robot systems by identifying key elements of these systems. The state of practice of mixed-initiative human-robot interaction is then surveyed and examined along each taxonomical dimension.

Certain robot missions need to perform predictably in a physical environment that may have significant uncertainty. One approach is to leverage automatic software verification techniques to establish a performance guarantee. The addition of an environment model and uncertainty in both program and environment, however, means that the state space of a model-checking solution to the problem can be prohibitively large. An approach based on behavior-based controllers in a process-algebra framework that avoids state-space combinatorics is presented here. In this approach, verification of the robot program in the uncertain environment is reduced to a filtering problem for a Bayesian network. Validation results are presented for the verification of a multiple-waypoint and an autonomous exploration robot mission.

We have developed an approach that can be used by mission designers to determine whether or not a performance guarantee for their mission software, when carried out under the uncertain conditions of a real-world environment, will hold within a threshold probability. In this paper we demonstrate its utility for verifying multirobot missions, in particular a bounding overwatch mission.

Certain robot missions need to perform predictably in a physical environment that may only be poorly characterized in advance. We have previously developed an approach to establishing performance guarantees for behavior-based controllers in a process-algebra framework. We extend that work here to include random variables, and we show how our prior results can be used to generate a Dynamic Bayesian Network for the coupled system of program and environment model. Verification is reduced to a filtering problem for this network. Finally, we present validation results that demonstrate the effectiveness of the verification of a multiple waypoint robot mission using this approach.

Deception is a common and essential behavior in humans. Since human beings gain many advantages from deceptive capabilities, we can also assume that robotic deception can provide benefits in several ways. Particularly, the use of robotic deception in human-robot interaction contexts is becoming an important and interesting research question. Despite its importance, very little research on robot deception has been conducted. Furthermore, no basic metrics or definitions of robot deception have been proposed yet. In this paper, we review the previous work on deception in various fields including psychology, biology, and robotics and will propose a novel way to define a taxonomy of robot deception. In addition, we will introduce an interesting research question of robot deception in HRI contexts and discuss potential approaches.

This paper describes the need and methods required to construct an integrated software verification and mission specification system for use in robotic missions intended for counter-weapons of mass destruction (c-WMD) operations, as part of a 3-year effort for the Defense Threat Reduction Agency. The overall system architecture is described. The principal tool for verification is a process algebra, PARS, based on port automata theory. PARS is introduced, emphasizing its ability to represent probabilistic programs and uncertain and dynamic environments, followed by the analysis of mission properties for an example robotic mission.

As humans are being progressively pushed further downstream in the decision-making process of autonomous systems, the need arises to ensure that moral standards, however defined, are adhered to by these robotic artifacts. While meaningful inroads have been made in this area regarding the use of ethical lethal military robots, including work by our laboratory, these needs transcend the warfighting domain and are pervasive, extending to eldercare, robot nannies, and other forms of service and entertainment robotic platforms. This paper presents an overview of the spectrum and specter of ethical issues raised by the advent of these systems, and various technical results obtained to date by our research group, geared towards managing ethical behavior in autonomous robots in relation to humanity. This includes: 1) the use of an ethical governor capable of restricting robotic behavior to predefined social norms; 2) an ethical adaptor which draws upon the moral emotions to allow a system to constructively and proactively modify its behavior based on the consequences of its actions; 3) the development of models of robotic trust in humans and its dual, deception, drawing on psychological models of interdependence theory; and 4) concluding with an approach towards the maintenance of dignity in human-robot relationships.

This article presents an investigation into the theoretical and computational aspects of trust as applied to robots. It begins with an in-depth review of the trust literature in search of a definition for trust suitable for implementation on a robot. Next we apply the definition to our interdependence framework for social action selection and develop an algorithm for determining if an interaction demands trust on the part of the robot. Finally, we apply our algorithm to several canonical social situations and review the resulting indications of whether or not the situation demands trust.

This paper provides the motivation and philosophy underlying the design of an ethical control and reasoning system potentially suitable for constraining lethal actions in an autonomous robotic system, so that its behavior will fall within the bounds prescribed by the Laws of War and Rules of Engagement. This research, funded by the U.S. Army Research Office, is intended to ensure that robots do not behave illegally or unethically in the battlefield. Reasons are provided for the necessity of developing such a system at this time, as well as arguments for and against its creation.

This paper reports the methods and results of an on-line survey addressing the issues surrounding lethality and autonomous systems that was conducted as part of a research project for the U.S. Army Research Office. The robotics researcher demographic, one of several targeted in this survey that includes policymakers, the military, and the general public, provides the data for this report. The design and administration of this survey and an analysis and discussion of the survey results are provided.

As the capabilities, range of missions, and the size of robot teams increase, the ability for a human operator to account for all the factors in these complex scenarios can become exceedingly difficult. Our previous research has studied the use of case-based reasoning (CBR) tools to assist a user in the generation of multi-robot missions. These tools, however, typically assume that the robots available for the mission are of the same type (i.e., homogeneous). We loosen this assumption through the integration of contract-net protocol (CNP) based task allocation coupled with a CBR-based mission specification wizard. Two alternative designs are explored for combining case-based mission specification and CNP-based team allocation as well as the tradeoffs that result from the selection of one of these approaches over the other.

This paper addresses a difficult issue confronting the designers of intelligent robotic systems: their potential use of lethality in warfare. As part of an ARO-funded study, we are currently investigating the points of view of various demographic groups, including researchers, regarding this issue, as well as developing methods to engineer ethical safeguards into their use in the battlefield.

This paper describes a usability study designed to assess ease of use, user satisfaction, and performance of a mobile robot mission specification system. The software under consideration, MissionLab, allows users to specify a robot mission as well as compile it, execute it, and control the robot in real-time. In this work, a new automated mission repair mechanism that aids users in correcting faulty missions was added to the system. This mechanism was compared to an older version in order to better inform the development process, and set a direction for future improvements in usability.

This paper presents a theoretical framework for computationally representing social situations in a robot. This work is based on interdependence theory, a social psychological theory of interaction and social situation analysis. We use interdependence theory to garner information about the social situations involving a human and a robot. We also quantify the gain in outcome resulting from situation analysis. Experiments demonstrate the utility of social situation information and of our situation-based framework as a method for guiding robot interaction. We conclude that this framework offers a principled, general approach for studying interactive robotics problems

Autonomous outdoor navigation requires the ability to discriminate among different types of terrain. A non-trivial problem is to manage the robot’s speed based on terrain roughness. This paper presents a speed control system for a robotic platform traveling over natural terrain. This system is based on the view of a line-scanning laser of the area just in front of the platform. Analysis of range data for roughness produced by the laser over different terrains is examined. An algorithm for managing speed through different terrain has been tested on real outdoor surfaces producing excellent performance.

Humans are inherently social creatures, and affect plays no small role in their social nature. We use our emotional expressions to communicate our internal state, our moods assist or hinder our interactions on a daily basis, we constantly form lasting attitudes towards others, and our personalities make us uniquely predisposed to perform certain tasks. In this paper, we present a framework under development that combines these four areas of affect to influence robotic behavior, and describe initial results of a longitudinal human-robot interaction study. The study was designed to inform the development of the framework in order to increase ease and pleasantness of human-robot interaction.

It is important to be able to guarantee the safety and effectiveness of robot behavior in applications where robots must operate alongside people or in hazardous situations. A modeling framework based on port automata and asynchronous communication is introduced in this paper. By looking at the internal transitions between port communications, an analysis approach is developed that removes the combinatoric issues of looking at an asynchronous combination of robot and environment. An example application of the approach to wheel slippage in a mobile robot is presented.

Ad-hoc networks among groups of autonomous mobile robots are becoming a common occurrence as teams of robots take on increasingly complicated missions over wider areas. Research has often focused on proactive means in which the individual robots of the team may prevent communication failures between nodes in this network. This is not always possible especially in unknown or hostile environments. This research addresses reactive aspects of communication recovery. How should the members of the team react in the event of unseen communication failures between some or all of the nodes in the network? We present a number of behaviors to be utilized in the event of communications failure as well as a behavioral sequencer to further enhance the effectiveness of these recovery behaviors. The performance of the communication recovery behavior is analyzed in simulation and their application on hardware platforms is discussed.

This paper presents a method for multi-robot communication sensitive reconnaissance. This approach utilizes collections of precompiled vector fields in parallel to coordinate a team of robots in a manner that is responsive to communication failures. Collections of vector fields are organized at the task level for reusability and generality. Different team sizes, scenarios, and task management strategies are investigated. Results indicate an acceptable reduction in communication attenuation when compared to other related methods of navigation. Online management of tasks and potential scalability are discussed.

In this paper, we present successful strategies for forgetting cases in a case-based reasoning (CBR) system applied to autonomous robot navigation. This extends previous work that involved a CBR architecture, which indexes cases by the spatio-temporal characteristics of the sensor data, and outputs or selects parameters of behaviors in a behavior-based robot architecture. In such a system, the removal of cases can be applied when a new situation unlike any current case in the library is encountered, but the library is full. Various strategies of determining which cases to remove are proposed, including metrics such as how frequently a case is used and a novel spreading activation mechanism. Experimental results show that such mechanisms can increase the performance of the system significantly and allow it to essentially forget old environments in which it was trained in favor of new environments it is currently encountering. The performance of this new system is better than both a purely reactive behavior-based system as well as the CBR module that did not forget cases. Furthermore, such forgetting mechanisms can be useful even when there is no major environmental shift during training, since some cases can potentially be harmful or rarely used. The relationship between the forgetting mechanism and the case library size is also discussed.

MissionLab is a mission specification system that implements a hybrid deliberative and reactive control architecture for autonomous mobile robots. The user creates and executes the robot mission plans through its graphical user interface. As robot deployments become more common in highly stressful situations, such as in dealing with explosives or biohazards, the usability of their mission specification system becomes critical. To address this need, a mission-planning "wizard" has been recently integrated into MissionLab. By retrieving and adapting past successful mission plans stored in its database, this new feature is designed to simplify the user's planning process. The latest formal usability experiments, reported in this paper, testing for usability improvements in terms of speed of the mission planning process, accuracy of the produced mission plans, and ease of use is conducted. This paper introduces the mission-planning wizard, describes the usability experiments (including design), and discusses the results in detail.

We present an approach that uses Q-learning on individual robotic agents, for coordinating a mission-tasked team of robots in a complex scenario. To reduce the size of the state space, actions are grouped into sets of related behaviors called roles and represented as behavioral assemblages. A role is a finite state automata such as Forager, where the behaviors and their sequencing for finding objects, collecting them, and returning them are already encoded and do not have to be re-learned. Each robot starts out with the same set of possible roles to play, the same perceptual hardware for coordination, and no contact other than perception regarding other members of the team. Over the course of training, a team of Q-learning robots will converge to solutions that best the performance of a well-designed handcrafted homogeneous team.

In this paper we describe a software system built to coordinate an autonomous vehicle with variable configuration ability operating in rough terrain conditions. The paper describes the system architecture, with an emphasis on the action planning function. This is intended to work with a proprioceptive algorithm that continuously coordinates wheel torques and suspension forces and positions to achieve optimal terrain crossing performance.

This paper presents a method for a mobile robot to construct and localize relative to a "cognitive map", where the cognitive map is assumed to be a representational structure that encodes both spatial and behavioral information. The localization is performed by applying a generic Bayes filter. The cognitive map was implemented within a behavior-based robotic system, providing a new behavior that allows the robot to anticipate future events using the cognitive map. One of the prominent advantages of this approach is elimination of the pose sensor usage (e.g., shaft encoder, compass, GPS, etc.), which is known for its limitations and proneness to various errors. A preliminary experiment was conducted in simulation and its promising results are discussed.

A new interfacing method is presented to control mobile robot(s) in a supervised manner. Mobile robots often provide global position information to an operator. This research describes a method whereby the operator controls a mobile robot(s) using his finger or stylus via a touchpad or touch screen interface. Using a mapping between the robot's operational site and the input device, a human user can provide routing information for the mobile robot. Two algorithms have been developed to create the robot trajectory from the operator's input. Information regarding numerous path points is generated when the operator moves his finger/stylus. To prune away meaningless point information, a simple but powerful significant points extracting algorithm is developed. The resulting significant points are used as waypoints. An on-line piecewise cubic Bezier curves (PCBC) trajectory generation algorithm is presented to create a smooth trajectory for these significant points. As the method is based on distance and not on time, the velocity of mobile robot can be controlled easily within its allowable dynamic range. The PCBC trajectory can also be modified on the fly. Simulation results are presented to verify these newly developed methods.

In this paper, the effects of adaptive robotic behavior via learning momentum in the context of a robotic team are studied. Learning momentum is a variation on parametric adjustment methods that has previously been successfully applied to enhance individual robot performance. In particular, we now assess, via simulation, the potential advantages of a team of robots using this capability to alter behavioral parameters when compared to a similar team of robots with static parameters.

Autonomous teams of robots operating in a dynamic, adversarial environment stand to benefit from using all available resources. But how can knowledge be used to construct a plan that does not interfere with the robots ability to react to its environment? In this research we distill abstract representation into a plan usable by a reactive behavior-based architecture. This plan is then exploited to enhance the performance of a team of robots tasked with maintaining communications while performing reconnaissance. Utilizing multiple plans in serial and in parallel is shown via simulation to be a promising method for increasing mission performance. We conclude that the utility of these internalized plans warrants further investigation as a method for imbuing reactive agents with a priori knowledge.

This paper presents a framework for affective robotic behavior (TAME) and describes an exploratory experimental study to identify relevant affective phenomena to include into the framework in order to increase ease and pleasantness of human-robot interaction.

This paper studies the effects of the integration of two learning algorithms, case-base reasoning (CBR) and learning momentum (LM), for the selection of behavioral parameters in real-time for robotic navigational tasks. Use of CBR methodology in the selection of behavioral parameters has already shown significant improvement in robot performance as measured by mission completion time and success rate. It has also made unnecessary the manual configuration of behavioral parameters from a user. However, the choice of the library of CBR cases does affect the robot performance, and choosing the right library sometimes is a difficult task especially when working with a real robot. In contrast, learning momentum does not depend on any prior information such as cases and searches for the "right" parameters in real-time. This results in high mission success rates and requires no manual configuration of parameters, but it shows no improvement in mission completion time. This work combines the two approaches so that CBR discontinuously switches behavioral parameters based on given cases whereas LM uses these parameters as a starting point for the real-time search for the "right" parameters. The integrated system was extensively evaluated on both simulated and physical robots. The tests showed that on simulated robots the integrated system performed as well as the CBR only system and outperformed the LM only system, whereas on real robots it significantly outperformed both CBR only and LM only systems.

This paper presents an approach to learning an optimal behavioral parameterization in the framework of a case-based reasoning methodology for autonomous navigation tasks. It is based on our previous work on a behavior-based robotic system that also employed spatio-temporal case-based reasoning in the selection of behavioral parameters but was not capable of learning new parameterizations. The present method extends the case-based reasoning module by making it capable of learning new and optimizing the existing cases where each case is a set of behavioral parameters. The learning process can either be a separate training process or be part of the mission execution. In either case, the robot learns an optimal parameterization of its behavior for different environments it encounters. The goal of this research is not only to automatically optimize the performance of the robot but also to avoid the manual configuration of behavioral parameters and the initial configuration of a case library, both of which require the user to possess good knowledge of robot behavior and the performance of numerous experiments. The presented method was integrated within a hybrid robot architecture and evaluated in extensive computer simulations, showing a significant increase in the performance over a nonadaptive system and a performance comparable to a non-learning CBR system that uses a hand-coded case library.

Q-learning has often been used to learn primitive behaviors, or to coordinate a limited set of motor skills. However, the complexity of the algorithm increases exponentially with the number of states the robot can be in and the number of actions that it can take. Therefore, it is natural to try to reduce the number of states and actions in order to improve the efficiency of the algorithm. Robot behaviors and behavioral assemblages provide a good level of abstraction which could be used to speed up robot learning. Instead of coordinating a set of primitives, we use Q-learning to coordinate a set of well tested behavioral assemblages to accomplish a robot mission. The domain for our experiments is a simple intercept mission. This paper also explores the effects of imperfect perceptual algorithms on learning when this approach is used.

Presents a method for creating high-fidelity models of animal behavior for use in robotic systems based on a behavioral systems approach, and describes in particular how an ethological model of a domestic dog can be implemented with AIBO, the Sony entertainment robot.

This paper re-introduces and evaluates the schematic sowbug proposed by Tolman (1939). The schematic sowbug is based on Tolman's purposive behaviorism, and it is believed to be the first prototype in history that actually implemented a behavior-based architecture suitable for robotics. The schematic sowbug navigates the environment based on two types of vectors, orientation and progression, that are computed from the values of sensors perceiving stimuli. Our experiments on both simulation and real robot proved the legitimacy of Tolman's assumptions, and the potential of applying the schematic sowbug model and principles within modern robotics is recognized.

We further study the effects of learning momentum as defined by Arkin, Clark and Ram (1992) on robots, both simulated and real, attempting to traverse obstacle fields in order to reach a goal. Integration of these results into a large-scale software architecture, MissionLab, provides the ability to exercise these algorithms in novel ways. Insight is also sought in reference to when different learning momentum strategies should be used.

Presents the application of a case-based reasoning approach to the selection and modification of behavioral assemblage parameters. The goal of this research is to achieve an optimal parameterization of robotic behaviors in run-time. This increases robot performance and makes a manual configuration of parameters unnecessary. The case-based reasoning module selects a set of parameters for an active behavioral assemblage in real-time. This set of parameters fits the environment better than hand-coded ones, and its performance is monitored providing feedback for a possible reselection of the parameters. The paper places a significant emphasis on the technical details of the case-based reasoning module and how it is integrated within a schema-based reactive navigation system. The paper also presents the results and evaluation of the system in both in simulation and real world robotic experiments.

New reactive behaviors that implement formations in multirobot teams are presented and evaluated. The formation behaviors are integrated with other navigational behaviors to enable a robotic team to reach navigational goals, avoid hazards and simultaneously remain in formation. The behaviors are implemented in simulation, on robots in the laboratory and aboard DARPA's HMMWV-based unmanned ground vehicles. The technique has been integrated with the autonomous robot architecture (AuRA) and the UGV Demo II architecture. The results demonstrate the value of various types of formations in autonomous, human-led and communications-restricted applications, and their appropriateness in different types of task environments.

This paper reviews key concepts of the Autonomous Robot Architecture (AuRA). Its structure, strengths, and roots in biology are presented. AuRA is a hybrid deliberative/ reactive robotic architecture that has been developed and refined over the past decade. In this article, particular focus is placed on the reactive behavioural component of this hybrid architecture. Various real world robots that have been implemented using this architectural paradigm are discussed, including a case study of a multiagent robotic team that competed and won the 1994 AAAI Mobile Robot Competition.

We present a new line of research investigating on-line adaptive reactive control mechanisms for autonomous intelligent agents. We discuss a case-based method for dynamic selection and modification of behavior assemblages for a navigational system. The case-based reasoning module is designed as an addition to a traditional reactive control system, and provides more flexible performance in novel environments without extensive high level reasoning that would otherwise slow the system down. The method is implemented in the ACBARR (case-based reactive robotic) system and evaluated through empirical simulation of the system on several different environments, including "box canyon" environments known to be problematic for reactive control systems in general.

This paper describes an implementation of a behavior-based mobile manipulator capable of autonomously transferring a sample from one drum to a second in unstructured environments. A major contribution of the project was the coherent integration of the arm and base as a cohesive unit, and not just a mobile base with an arm attached. The support for smooth simultaneous operation of all joints on the vehicle facilitated biologically plausible motions, such as arm preshaping. The behavior-based controller used a pseudo-force model, where behaviors add forces and torques to joints and limbs resulting in coordinated motion. The vehicle Jacobian is used to convert the pseudo-forces into joint torques and a pseudo-damping model converts the joint torques into joint velocities. This process allows rapid control of the manipulator without the use of inverse kinematics. A drum sampling task is presented where the vehicle demonstrates how a sample of material could be moved from one drum to another, illustrating the efficacy of the solution.

Specifying a multiagent behavioral configuration requires both a careful choice of the behavior set and creation of a temporal chain executing the mission using those behaviors. This difficult task is simplified by applying an object-oriented approach to the design using a methodology called temporal sequencing to partition the mission into discrete operating states and enumerate the perceptual triggers causing transitions between those states. Several smaller independent configurations (assemblages) can then be created, each implementing one distinct operating state. Each assemblage consists of a collection of behaviors and a suitable coordination mechanism which causes the group to act as a single, coherent, behavior. The missions are specified in a structured user-friendly language targeted for military-style scout missions. Various multiagent missions have been demonstrated in simulation and results are shown using our Denning mobile robots.

This paper presents an algorithm that can recognize and localize objects given a model of their contours using only ultrasonic range data. The algorithm exploits a physical model of the ultrasonic beam and combines several readings to extract outline object segments from the environment. It then detects patterns of outline segments that correspond to predefined models of object contours, performing both object recognition and localization. The algorithm is robust since it can account for noise and inaccurate readings as well as efficient since it uses a relaxation technique that can incorporate new data incrementally without recalculating from scratch.>

A methodology for integrating multiple perceptual algorithms within a reactive robotic control system is presented. A model using finite state accepters is developed as a means for expressing perceptual processing over space and time in the context of a particular motor behavior. This model can be utilized for a wide range of perceptual sequencing problems. The feasibility of this method is demonstrated in two separate implementations. The first is in the context of mobile robot docking where the mobile robot uses four different vision and ultrasonic algorithms to position itself relative to a docking workstation over a long-range course. The second uses vision, IR beacon, and ultrasonic algorithms to park the robot next to a desired plastic pole randomly placed within an arena.>

New methods for producing avoidance behavior among moving obstacles within the context of reactive robotic control are described. These specifically include escape and dodging behaviors. Dodging is concerned with the avoidance of a ballistic projectile while escape is more useful within the context of chase. The motivation and formulation of these new reactive behaviors are presented. Both simulation and experimental results using a robot in a cluttered and moving world are provided.

The authors describe a reactive robotic control system which incorporates aspects of machine learning to improve the system's ability to navigate successfully in unfamiliar environments. This system overcomes limitations of completely reactive systems by exercising online performance enhancement without the need for high-level planning. The goal of the learning system is to give the autonomous robot the ability to adjust the scheme control parameters in an unstructured dynamic environment. The results of a successful implementation that learns to navigate out of a box canyon are presented. This system never resorts to a high-level planner, but instead learns continuously by adjusting gains based on the progress made so far. The system is successful because it is able to improve its performance in reaching a goal in a previously unfamiliar and dynamic world.>

Sensor fusion has an important role in the navigation of autonomous mobile robots. Our research has generated a generic and robust pro- cess model based on the action-oriented percep- tion paradigm. The autonomous execution and ex- ception handling abilities of this model have been implemented as the Sensor Fusion Effects (SFX) architecture. The key aspects of this implemen- tation are the sensing plan, the uncertainty man- agement mechanism, the application of feedback from the sensing process to individual sensors, the detection of exceptions to the sensing plan, and handling of those exceptions. This paper gives an overview of the SFX architecture, concentrating on the sensing plan as the central control struc- ture guiding autonomous execution. This paper also reports on experiments using sensor data col- lected from our mobile robot which demonstrate the use of the sensing plan representation, the ex- ecution sequence, the application of feedback, and how feedback improves the overall sensing capa- bilities of the robot.

This paper explores the application of genetic algorithms to the learning of local robot navigation behaviors for reactive control systems. Our approach is to train a reactive control system in various types of environments, thus creating a set of "ecological niches" that can be used in similar environments. The use of genetic algorithms as an unsupervised learning method for a reactive control architecture greatly reduces the effort required to configure a navigation system. Findings from computer simulations of robot navigation through various types of environments are presented. I. Introduction A common robot task is to navigate through an environment to a goal position, without hitting any obstacles that may be present. Navigation through a cluttered environment is an extremely complex and underconstrained task. Apart from the computational constraints placed on the design of a navigation system, it is desirable that the system be robust enough to navigate through a large number ...

The concept of visual interaction is introduced as the process which links perception and problem solving such that problem solving is affected by what is seen, and conversely, what is seen and perceived is affected by the current state of the problem-solving process. The development of a cognitively based model of the visual interaction process in diagnostic radiology is described. It is shown how aspects of this model are being incorporated into the design and implementation of an intelligent computer-based radiological assistant. In order to achieve this, it is necessary to extract information about the nature and type of knowledge involved in this process, and then to determine how the knowledge is used to accomplish the task of radiological diagnosis. This work may provide new directions for clinically useful interactive radiological systems. It is also seen as a useful radiological teaching tool, providing hands-on experience with a clinical aid, and further, it may prove to be effective tool for studying the radiological process.>

The authors have developed reactive motor behaviors (schemas) which exploit inclinometer data. Using this information, they have implemented artificial intelligence hill-climbing techniques as well as valley finding and isocontour following. All of these schemas are integrated with the other schemas present in the system AuRA (autonomous robot architecture) and can be used concurrently with obstacle avoidance, goal seeking, and other motor behaviors. Simulation studies illustrate the utility of these methods using actual terrain data.>

Current approaches towards achieving mobility in the workplace are reviewed. The role of automatic guided vehicles (AGVs) and some of the preliminary work of other groups in autonomous vehicles are described. An overview is presented of the autonomous robot architecture (AuRA), a general-purpose system designed for experimentation in the domain of intelligent mobility. The means by which navigation is accomplished within this framework is specifically addressed. A description is given of the changes made to AuRA to adapt it to a flexible manufacturing environment, the types of knowledge that need to be incorporated, and the new motor behaviors required for this domain. Simulations of both navigational planning and reactive/reflexive motor schema-based navigation in a flexible manufacturing systems environment, followed by actual navigational experiments using the mobile vehicle, are presented.>

The design of an autonomous robot architecture is analyzed in light of the cognitive psychological, neuroscientific, and ethological studies that influenced its development. Motor schema-based navigation and its relationship to models of detour behavior in amphibians is described. Application of the action-perception cycle in the context of action-oriented perception is discussed, with particular emphasis on the role of expectations as focus-of-attention mechanisms. The process of homeostatic control as a means of dynamically modifying motor behavior based on internal sensing is also described. These approaches are substantiated throughout with simulation studies and actual mobile robot experiments.>

Schema-based navigational techniques are used to introduce dynamic path replanning for a mobile robot, based on internal sensor information. This mode of operation, termed homeostatic control, forms an integral part of the autonomous robot architecture. A model that is analogous to the mammalian endocrine system serves as the basis for this mode. Simulation results verify the viability of this concept. It is found that dynamic replanning can be carried out using internal monitoring of the robot's state, and not solely based on environmental perception. The robot can be shown to be responsive to changes in fuel, temperature, and other conditions as it navigates through the world.>

Motor schemas are proposed as a basic unit of behavior specification for the navigation of a mobile robot. These are multiple concurrent processes which operate in conjunction with associated perceptual schemas and contribute independently to the overall concerted action of the vehicle. The motivation behind the use of schemas for this domain is drawn from neuroscientific, psychological and robotic sources. A variant of the potential field method is used to produce the appropriate velocity and steering commands for the robot. An implementation strategy based on available tools at UMASS is described. Simulation results show the feasibility of this approach.