We report on a reformulated general Ethics and Robotics course, in which we aim to address the twin curricular challenges of exposing computer science students to ethics discourse and establishing a pathway for ethics-oriented modules to be designed into numerous computer science courses across an institution. Given computer science instructors' lack of time and expertise to build ethics modules themselves, we tasked our students with creating ethics modules for instructors of 11 computer science courses at our university. Our course participants represented a diverse range of backgrounds and perspectives that catalyzed lively discussions and creative ideas for ethics pedagogy innovation. We report on course details, including in-class activities, assignments, and the project. We discuss our findings, including reception from students and computer science instructors and planned updates for the next course iteration. Given the course's overall success, we share with the hope that others may learn from or adopt our course approach. Materials are available on our website: https://vdean.github.io/16-735-ethics-robotics.html.

Industrial smoke emissions pose a significant concern to human health. Prior works have shown that using Computer Vision (CV) techniques to identify smoke as visual evidence can influence the attitude of regulators and empower citizens to pursue environmental justice. However, existing datasets are not of sufficient quality nor quantity to train the robust CV models needed to support air quality advocacy. We introduce RISE, the first large-scale video dataset for Recognizing Industrial Smoke Emissions. We adopted a citizen science approach to collaborate with local community members to annotate whether a video clip has smoke emissions. Our dataset contains 12,567 clips from 19 distinct views from cameras that monitored three industrial facilities. These daytime clips span 30 days over two years, including all four seasons. We ran experiments using deep neural networks to establish a strong performance baseline and reveal smoke recognition challenges. Our survey study discussed community feedback, and our data analysis displayed opportunities for integrating citizen scientists and crowd workers into the application of Artificial Intelligence for Social Impact.

Urban air pollution has been linked to various human health concerns, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developedSmell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. We also applied regression analysis to identify statistically significant effects of push notifications on user engagement. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns and can empower communities to advocate for better air quality. All citizen-contributed smell data are publicly accessible and can be downloaded fromhttps://smellpgh.org.

Urban air pollution has been linked to various human health considerations, including cardiopulmonary diseases. Communities who suffer from poor air quality often rely on experts to identify pollution sources due to the lack of accessible tools. Taking this into account, we developed Smell Pittsburgh, a system that enables community members to report odors and track where these odors are frequently concentrated. All smell report data are publicly accessible online. These reports are also sent to the local health department and visualized on a map along with air quality data from monitoring stations. This visualization provides a comprehensive overview of the local pollution landscape. Additionally, with these reports and air quality data, we developed a model to predict upcoming smell events and send push notifications to inform communities. Our evaluation of this system demonstrates that engaging residents in documenting their experiences with pollution odors can help identify local air pollution patterns, and can empower communities to advocate for better air quality.

Developing information technology to democratize scientific knowledge and support citizen empowerment is a challenging task. In our case, a local community suffered from air pollution caused by industrial activity. The residents lacked the technological fluency to gather and curate diverse scientific data to advocate for regulatory change. We collaborated with the community in developing an air quality monitoring system which integrated heterogeneous data over a large spatial and temporal scale. The system afforded strong scientific evidence by using animated smoke images, air quality data, crowdsourced smell reports, and wind data. In our evaluation, we report patterns of sharing smoke images among stakeholders. Our survey study shows that the scientific knowledge provided by the system encourages agonistic discussions with regulators, empowers the community to support policy making, and rebalances the power relationship between stakeholders.

Robotics activities allow students to gain confidence in their abilities to use technology creatively, express themselves, and solve problems of interest. However, many traditional robotics elective programs suffer from self-selection and reach only a subset of students. Arts & Bots is a middle school robotics program which integrates robotics into non-technology classes to engage a more diverse population of students. In this paper, we present the collected student outcomes from our program evaluation study which ran from 2013 until 2017. During this time, Arts & Bots was implemented by 24 teachers in 66 classes, reaching 727 middle school students. Program evaluation data included pre- and post-surveys, daily reflection sheets, project presentation videos, and classroom observations. Between pre- and post-tests, we recorded better student understanding of what engineering careers entail, and found that female students caught up to their male peers in their understanding. Our analysis also shows pre/post improvement in student technical knowledge. Quantitative survey results are complemented by our coding and analysis of qualitative student short answers. We found that female students were significantly more likely than male peers to mention increases in confidence on the post-survey. This paper concludes with a discussion of trends in the evaluation results.

This paper describes the development of Flutter, a new sensor-driven, robotics technology kit for in-school use with elementary-age students. Our development began by conducting focus groups with teachers (N=6) in which we guided a participatory design process. Through affinity diagramming, we identified science and math as areas of focus for the program; we also brainstormed project-topics with the teachers. The Flutter Kit is controlled by an app that allows for touch based interactions and enables the kits to be programmable by tablets. The app interface, developed with teachers through the use of paper and digital prototypes, builds on the concept of data flow from an input to an output and emphasizes the use of sensor data for creating interactive devices. The central element of the Flutter hardware is a custom microcontroller board that connects to the tablet app via bluetooth; permits students to log sensor data; and controls a buzzer, three sensor ports, three tricolor LEDs, and three servo ports. From observations of four pilot classes (N=84) and student interviews, we generated ideas for future improvements to the system, such as: hardware changes for ease of use and changes to the curriculum to support students' data analysis skills.

In this paper we describe our process for synthesizing frameworks for recognizing student talents in the areas of Computational Thinking (CT) and Engineering Design (ED) from prior research. Computer science education research has resulted in multiple, overlapping definitions of CT as an approach towards solving problems using methods and tools that are derived from computer science. Our development of operationalized definitions of CT talent for middle school educators is focused on uniting models for CT in a simplified structure. Our ED definition framework builds on multiple distinct models of the engineering design process along with concepts from systems engineering models and the design thinking process. We operationalize these frameworks to provide teachers with metrics and examples for recognizing and assessing the CT and ED skills of their students in non-technical classes. By training teachers to evaluate students' processes from the perspective of an engineer and computer scientist, teachers are more able to help their STEM-inclined students recognize the alignments between their own talents and possible careers. Through the analysis of teacher surveys and interviews from 19 classroom implementations, we evaluated the changes that the Arts & Bots program has had on teacher perceptions of student CT and ED skills and talents.

The next generation of world citizens must be technologically fluent members of society. By technological fluency we mean the ability to manipulate technology creatively and for one's own use. This fluency is composed of knowledge and skills utilizing materials and tools, as well as attitudes, (e.g. confidence), with respect to technology. Numerous interventions exist to support middle school students' technological fluency, and robotics activities are popular. It is critical that instruments assessing student attitudes towards robotics are available for the development and evaluation of these interventions. We present an instrument for assessing middle school students' technological fluency attitudes specifically tailored for robotics activities. Survey subscales were developed from existing science motivation research, and individual measurement items were generated and adapted within those subscales. The robotics activity attitudes scale (RAAS) was revised through three rounds of pilot testing in 2010, 2012 and 2015. The final RAAS in 2015 consisted of 50 items with an overall Cronbach's alpha of .972 (N=236) organized in four dimensions of Curiosity, Interest, Expectancy Value, and Confidence and Identity.

With increasing numbers of electric and hybrid vehicles on the road, transportation presents a unique opportunity to leverage data-driven intelligence to realize large scale impact in energy use and emissions. Energy management in these vehicles is highly sensitive to upcoming power load on the vehicle, which is not considered in conventional reactive policies calculated at design time. Advancements in cheap sensing and computation have enabled on-board upcoming load predictions which can be used to optimize energy management. In this work, we propose and evaluate a novel, real-time optimization strategy that leverages predictions from prior data in a simulated hybrid battery-supercapacitor energy management task. We demonstrate a complete adaptive system that improves over the lifetime of the vehicle as more data is collected and prediction accuracy improves. Using thousands of miles of real-world data collected from both petrol and electric vehicles, we evaluate the performance of our optimization strategy with respect to our cost function. The system achieves performance within 10% of the optimal upper bound calculated using a priori knowledge of the upcoming loads. This performance implies improved battery thermal stability, efficiency, and longevity. Our strategy can be applied to optimize energy use in gas-electric hybrids, battery cooling in electric vehicles, and many other load-sensitive tasks in transportation.

Arts & Bots combines intrinsically creative craft materials, common robotics components, a custom programming environment and teacher professional development to create a flexible robotics intervention for secondary school classrooms. In order to engage students underserved by other robotics programs, Arts & Bots is oriented to support the creation of collaborative expression-focused robots, as opposed to more commonly implemented competitive task-focused robot activities. Specifically, Arts & Bots targets integration into traditional nontechnical classes, such as literature and history, to reach a broader base of students than would be enrolled in elective technology programs. This paper describes three classroom implementations, including a secondary school poetry project. By including Arts & Bots in these core courses, we expose diverse students to engineering education activities such as hands-on experiences with computer programming, prototyping, and the engineering design process. We present our outcomes grouped within two primary themes: first, in Technological Fluency, we present students' self-reporting of concepts learned, confidence with technology, and breaking of technology stereotypes; second, in Complementary Non-Technical Skills, we present other skills students learned by participating in the Arts & Bots program.

Human driven systems present a unique optimization challenge for robot control. Generally, operators of these systems behave rationally given environmental factors and desired goals. However, information available to subsystem controllers is often incomplete, and the operator becomes more difficult to model without this input information. In this work we present a data-driven, nonparametric model to capture both expectation and uncertainty of the upcoming duty for a subsystem controller. This model is a modified k-nearest neighbor regressor used to generate weighted samples from a distribution of upcoming duty, which are then exploited to generate an optimal control. We test the model on a simulated heterogeneous energy pack manager in an Electric Vehicle operated by a human driver. For this domain, upcoming load on the energy pack strongly affects the optimal use and charging strategy of the pack. Given incomplete information, there is a natural uncertainty in upcoming duty due to traffic, destination, signage, and other factors. We test against a dataset of real driving data gathered from volunteers, and compare the results other models and the optimal upper bound.

Arts & Bots is an educational program that aims to broaden diversity and participation in technology by integrating arts and crafts with robotics. Arts & Bots is a flexible program that can be integrated into in-school and out-of-school programs in many subject areas. This paper describes the visual programming environment developed for Arts & Bots and its goals of low barriers to entry, classroom compatibility, supporting student acquisition of computational thinking skills, and enabling complex robot behaviors. The authors also compare and contrast the programming environment with other popular visual programming environments, namely Scratch, Alice and LEGO NXT-G.

In this paper, a modelling approach is described that represents human-robot social interactions as partially observable Markov decision processes (POMDPs). In these POMDPs, the intention of the human is represented as an unobservable part of the state space, and the robot's own intentions are expressed through the rewards. The state transition structure for the models is created using action rules that capture the effects of the robot's actions, relate the human's behavior to their intentions, and describe the changing state of the environment. State transitions are modified using data from humans interacting with other humans. The policies obtained by solving these models are used to control a robot in a socially situated task with a human partner. These interactions are compared to those of human pairs performing the same task, demonstrating that this approach produces policies that exhibit natural and socially appropriate behavior.

At the 2008 ACM/IEEE Conference on Human-Robot Interaction, a provocative panel was held to discuss the complicated ethical issues that abound in the field of human-robot interaction. The panel members and the audience participation made it clear that the HRI community desires - indeed, is in need of - an ongoing discussion on the nature of social responsibility in the field of human-robot interaction. At the 2010 Conference, we will hold a panel on the issues of social responsibility in HRI, focusing on the unique features of robotic interaction that call for responsible action (e.g., value-specific domains such as autonomy, accountability, trust, and/or human dignity; and application areas such as military applications, domestic care, entertainment, and/or communication). As a young and rapidly growing field, we have a responsibility to conduct our research in such a way that it leads to human-robot interaction outcomes that promote rather than hinder the flourishing of humans across society. What does social responsibility within the HRI field look like, and how do we conduct our work while adhering to such an obligation? The panelists will be asked to address this and related questions as a means of continuing an ongoing conversation on social responsibility in human-robot interaction.

Many efforts are being made to improve computer science education in order to address the retention and motivation of students. These efforts rely on the development of educational tools and environments, tools that, when successful, require many years to integrate into the computer science education community. We introduce a strategy that both speeds uptake in the community and improves the chances of the project creating an educationally successful tool. The strategy hinges on creating an initial community of educators before an educational tool is fully mature but at the point at which it becomes usable by teachers. While this is somewhat analogous to the beta-testing communities in software development, our aim is for the community to drive the underlying design in significant ways. Our context is CSbots, a project to develop a robot, software environment, and associated curricula for introductory computer science education. We detail our collaborative outreach effort, which resulted in the concurrent creation of a community of 30 invested educators and a well aligned educational tool ready for broad dissemination.

We present CSbots, an ongoing program to use robots as educational tools in the Introduction to Computer Science CS1) course. We aim to use robotics to improve learning and retention by altering course work so that it is more relevant to students.

In this paper, we present a user study of a new collaborative communication method between a user and remotely-located robot performing an exploration task. In the studied scenario, our user possesses scientific expertise but not necessarily detailed knowledge of the robot's capabilities, resulting in very little common ground

In this paper, we explore how dynamic visual cues can be used to create accessible and meaningful social interfaces without raising expectations beyond what is achievable with current technology. Our approach is inspired by research in perceptual causality, which suggests that simple displays in motion can evoke high-level social and emotional content. For our exploration, we iteratively designed and implemented a public social interface using abstraction and motion as design elements. Our interface communicated simple social and emotional content such as displaying happiness when there is high social interaction in the environment. Our qualitative evaluations showed that people frequently and repeatedly interacted with the interface while they tried to make sense of the underlying social content. They also shared their models with others, which led to more social interaction in the environment.

The dangerous and time sensitive nature of a disaster area makes it an ideal application for robotic exploration. Our long term goal is to enable humans, software agents, and autonomous robots to work together to save lives. Existing work in coordination for search and rescue does not address the variety of constraints that apply to the problem. This paper provides an expressive language for specifying system constraints. We also describe a coordination architecture capable of quickly finding an optimal or near optimal solution to the combined problems of task allocation, scheduling, and path planning subject to system constraints. We address a perceived lack of benchmarks for this research area by establishing a repository open to the research community which includes a set of benchmarks we designed to illustrate some of the complexities of the problem space. Finally, we evaluate various algorithms on these benchmarks

The mobile robot programming laboratory course has been taught at Carnegie Mellon University for the past twelve years. It is a problem-driven class designed for students with little or no experience with robots. In this paper, we first present the current status of the class, and show how it improves the education and training of students in a robotics curriculum by giving them a hands-on experience with a real robot. We show that, in addition to core subjects such as perception, action and cognition, students also have the opportunity to learn advanced topics such as reinforcement learning and multi-robot coordination. We then discuss the evolution of the class under general categories: hardware and programming environment, team experiments, and assignments. We present important lessons learned in each category, and how they affect the learning experience of participating students. We conclude by discussing future opportunities

Current technology literacy trends in the United States show declining interest and engagement in technological fields of study. We propose a roadmap by which robotics applications can enliven technology education and capture the interest of new students. We also describe our current efforts to design appropriate technologies and apply them at the middle school, high school, and college levels

To help answer questions about the behavior of participants in human-robot systems, we propose the cognitive evaluation of human-robot systems (CEHRS) method based on our work with the personal exploration rover (PER). The CEHRS method consists of six steps: (1) identify all system participants, (2) collect data from all participant groups, including the system's creators, (3) analyze participant data in light of system-wide goals, (4) answer targeted questions about each participant group to determine the flow of knowledge, information, and influence throughout the system, (5) look for inconsistencies in the knowledge and beliefs of different participant groups, and (6) make recommendations for improvement. We offer this comprehensive, human-centered evaluation method as a starting point for future work in understanding cognitive change in human-robot interactions

The Peer-To-Peer Human-Robot Interaction (P2P-HRI) project is developing techniques to improve task coordination and collaboration between human and robot partners. Our work is motivated by the need to develop effective human-robot teams for space mission operations. A central element of our approach is creating dialogue and interaction tools that enable humans and robots to flexibly support one another. In order to understand how this approach can influence task performance, we recently conducted a series of tests simulating a lunar construction task with a human-robot team. In this paper, we describe the tests performed, discuss our initial results, and analyze the effect of intervention on task performance.

We describe a monocular robot vision system which accomplishes accurate 3-DOF dead-reckoning, closed loop motion control, and precipice and obstacle detection, all in dynamic environments, using a single, consumer-grade web cam and typical laptop computer hardware. Simultaneous translation and rotation are accurately measured, and the camera need not be placed at the robot’s center of rotation. The algorithm is straightforward to implement and robust to noisy measurements. The software is based on open source computer vision libraries and is itself open source. It has been tested in a wide variety of real-world environments and on several different mobile robot platforms.

The Personal Rover Project produces technology, curriculum and evaluation techniques for robotic educational use in formal and informal (after-school, out-of-school) learning environments. Our specific aim for this phase of the project is to create and evaluate human-robot interactions that educate members of the general public in an informal learning environment, specifically museums. Our educational goals are to further an appreciation and understanding of NASA's Mars Exploration Rovers (MERs), to illustrate the role of robotic rovers in scientific exploration, and to provide hands-on learning experiences that demonstrate robot autonomy. We have designed a new robot, the Personal Exploration Rover (PER) and the related interactive components of a museum exhibit to achieve these goals. Here we describe the exhibits developed and the formal evaluation results of the exhibits' educational impact and efficacy. These results suggest techniques by which learning can be measured and used as an indicator of successful human-robot interaction.

Installation of a robot system in a publicly accessible technical museum poses nontrivial problems along three axes. First, the robot must be reliable, both by failing rarely in spite of continuous, daily use and by allowing museum staff to easily return the robot to service. Second, the robot must perform without the need for staff intervention, from system autonomy to energetics enabling full-day operation without battery replacement. Third, the user-end interaction software must be self-explanatory as well as instructional and engaging in order to effectively communicate the learning goals of the exhibit. In this paper we describe the design of such a robot system and share early results regarding its successful deployment at five museums across the United States.

Despite the growing number of multi-agent software systems, relatively few physical systems have adopted multi-agent systems technology. Agents that interact with a dynamic physical environment have requirements not shared by virtual agents, including the need to transfer information about the world and their interaction with it. The agent communication languages proven successful in software based multi-agent systems incur overheads that make them impractical or infeasible for the transfer of low-level data. Instead, real world systems typically employ application specific protocols to transfer video, audio, sensory, or telemetry data. These protocols lack the transparency and portability of formal agent communication languages and consequently are limited in their scalability. We propose augmenting the capabilities of current multi-agent systems to provide for the efficient transfer of low-level information, by allowing backchannels of communication between agents with flexible protocols in a carefully principled way. We show that this extension can yield significant performance increases in communication efficiency and discuss the benefits of incorporating backchannels into a search a rescue robot system.

During the summer of 2002, Robotic Autonomy was taught to thirty students at Carnegie Mellon West in cooperation with NASA/Ames (Moffett Field, CA). The authors at Carnegie Mellon University's Robotics Institute and at the University of Pittsburgh's Learning Research and Development Center planned a methodology for formally evaluating the educational efficacy of Robotic Autonomy. This article describes the educational analysis methodology and the statistically significant results of our analysis, demonstrating the positive impact of Robotic Autonomy on student learning beyond the boundaries of specific technical concepts in robotics. Educational robotics is gaining traction at all levels of the educational system, however formal analysis of its effectiveness has been lacking. This research project seeks to address this weakness by presenting statistically significant evidence of broad learning.

The robotic manipulation of flexible materials such as paper remains a challenging area of research. Our previous work has focused on the nondestructive manipulation of bound paper as found in books. This article describes a new approach to the one-sided, nonprehensile paper manipulation problem in which we use the polymer polydimethylsiloxane (PDMS) to create a mechanical bond between the paper and robot manipulator. We have fabricated and tested several complete page-flipping robots that make use of this technique. The current robot has manipulated 10,720 bound pages with an error rate of 0.056%. Future research would focus on refining the design for use in industry.

Motion vision (visual odometry, the estimation of camera egomotion) is a well researched field, yet has seen relatively limited use despite strong evidence from biological systems that vision can be extremely valuable for navigation. The limited use of such vision techniques has been attributed to a lack of good algorithms and insufficient computer power, but both of those problems were resolved as long as a decade ago. A gap presently yawns between theory and practice, perhaps due to perceptions of robot vision as less reliable and more complex than other types of sensing. We present an experimental methodology for assessing the real world precision and reliability of visual odometry techniques in both normal and extreme terrain. This paper evaluates the performance of a mobile robot equipped with a simple vision system in common outdoor and indoor environments, including grass, pavement, ice, and carpet. Our results show that motion vision algorithms can be robust and effective, and suggest a number of directions for further development.

The Trikebot is the result of a ground-up design effort chartered to develop an effective and low-cost educational robot for secondary level education and home use. This paper describes all aspects of the Trikebot, including chassis and mechanism; control electronics; communication architecture; robot control server and student programming environment. Notable innovations include a fast-build construction kit, indoor/outdoor terrainability, CMOS vision-centered sensing, back-EMF motor speed control and a Java programming interface.

This paper summarizes a long-term project to install and maintain socially interactive, autonomous mobile robots in public spaces. We have deployed four robots over the past five years, accumulating a total operational time exceeding seven years. This document introduces the robots, then focuses on lessons learned from each deployment. Finally, this paper describes how this entire project came to a close, offering a cautionary tale for those who wish to embark on such an effort in the future.

This paper presents the results of an experiment in human-robot social interaction. Its purpose was to measure the impact of certain features and behaviors on people's willingness to engage in a short interaction with a robot. The behaviors tested were the ability to convey expression with a humanoid face and the ability to indicate attention by turning towards the person that the robot is addressing. We hypothesized that these features were minimal requirements for effective social interaction between a human and a robot. We will discuss the results of the experiment and their implications for the design of socially interactive robots.

In this paper simultaneous localization and map building is performed with a hybrid, metric-topological,approach. A global topological map connects local metric maps, allowing a compact environment model, which does not require global metric consistency and permits both precision and robustness. However, the most important innovation of the approach is the way how loops in the environment are handled by map building using the information of the multi hypotheses topological localization. The method uses data from a 360/spl deg/ laser scanner to extract comers and openings for the topological approach and infinite lines for the metric method. This hybrid approach has been tested in a 50 /spl times/ 25 m/sup 2/ portion of the institute building with a fully autonomous robot. The performances of the whole system are proven empirically by comparing maps generated by independent explorations, testing the localization capabilities, making relocation experiments and showing how the technique for closing the loop works.

We propose a learning algorithm for acquiring a stochastic model of the behavior of a mobile robot, which allows the robot to localize itself along the outer boundary of its environment while traversing it. Compared to previously suggested solutions based on learning self-organizing neural nets, our approach achieves much higher spatial resolution which is limited only by the control time-step of the robot. We demonstrate the successful work of the algorithm on a small robot with only three infrared range sensors and a digital compass, and suggest how this algorithm can be extended to learn probabilistic models for full decision-theoretic reasoning and planning.

We present an experiment in sequential visual servo control of a dynamic manipulation task with unknown equations of motion and feedback from an uncalibrated camera. Our algorithm constructs a model of a Markov decision process (MDP) by means of grounding states in observed trajectories, and uses the model to find a control policy based on visual input, which maximizes a prespecified optimal control criterion balancing performance and control effort.

In this paper we describe a functioning low cost embedded vision system which can perform basic color blob tracking at 16.7 frames per second. This system utilizes a low cost CMOS color camera module and all image data is processed by a high speed, low cost microcontroller. This eliminates the need for a separate frame grabber and high speed host computer typically found in traditional vision systems. The resulting embedded system makes it possible to utilize simple color vision algorithms in applications like small mobile robotics where a traditional vision system would not be practical.

Proposes a method for creating unique identifiers, called fingerprint sequences, for visually distinct locations by recovering statistically significant features in panoramic color images. Fingerprint sequences are expressive enough for mobile robot localization, as demonstrated using a minimum energy sequence-matching algorithm that is described. Empirical results in two different places demonstrate the reliability of the system for global localization on a Nomad Scout mobile robot.

In this paper a new localization approach combining the metric and topological paradigm is presented. The main idea is to connect local metric maps by means of a global topological map. This allows a compact environment model which does not require global metric consistency and permits both precision and robustness. The method uses a 360 degree laser scanner in order to extract lines for the metric localization and doors, discontinuities and hallways for the topological approach. The approach has been widely tested in a 50/spl times/25 m portion of the institute building with the new fully autonomous robot Donald Duck. 25 randomly generated test missions were performed with a success ratio of 96% and a mean error at the goal point of 9 mm for an overall trajectory length of 1.15 km.

Compelling human-robot interaction demands high level perception of human behavior by the robot. In this paper we describe a visual perception system that provides high-level, narrative interpretation of human behavior in relation to the robot. The vision system has been implemented using Firewire digital camera technology and has been tested in public venues at The Robotics Institute.

An approach combining the metric and topological paradigm for simultaneous localization and map building is presented The main idea is to connect local metric maps by means of a global topological map. This allows a compact environment model which does not require global metric consistency and permits both precision and robustness. The method uses a 360 degree laser scanner in order to extract corners and openings for the topological approach and lines for the metric localization. The approach has been tested in a 30 /spl times/ 25 m portion of the institute building with the fully autonomous robot Donald Duck An experiment consists of a complete exploration and a set of test missions. Three experiments have been performed for a total of 15 test missions, which have been randomly defined and completed with a success ratio of 87%.

Believable agents usually depend upon explicit, model-based simulations of human emotions. This work appeals instead to the sensibilities of dramatic acting to create agents that are believable. The chosen task is that of comedy improvisation as it provides a solid demonstration of the agents' believability in the context of a high-level deliberative goal. Furthermore, this work employs physical robots as the actors, employing the real-time sensor values from the robots as inputs into the acting process. This paper describes the dramatic approach to acting that we used and describes the Java-based implementation on two Nomad Scout robots. Actual, improvised scripts created by the robots are included and analyzed.

This paper presents a new appearance-based place recognition system for topological localization. The method uses a panoramic vision system to sense the environment. Color images are classified in real-time based on nearest-neighbor learning, image histogram matching, and a simple voting scheme. The system has been evaluated with eight cross-sequence tests in four unmodified environments, three indoors and one outdoors. In all eight cases, the system successfully tracked the mobile robot's position. The system correctly classified between 87% and 98% of the input color images. For the remaining images, the system was either momentarily confused or uncertain, but never classified an image incorrectly.

We describe the Cye personal robot, concentrating on its path planning and navigation. We start out with a brief description of the general problem, followed by more detail on the Cye robot. After that, we concentrate on the path planner, which uses a global potential field approach, combined with a novel optimization criterion. This ensures that the robot maintains adequate distance from obstacles, while finding an optimal path which incorporates partial terrain knowledge. This system has been in use for over five months, with approximately 200 installations. As we empirically show, it is robust and can handle dynamic obstacles and imperfect maps.

This paper presents a mobile robot localizer that detects topological transitions using a color vision-based classification system. After a two-step training process, the localization system is shown to achieve sufficient reliability to track the position of a mobile robot across two floors of an office building using purely discrete (non-probabilistic) update. Experimental results are based on an off-the-shelf electric wheelchair fitted with a parabolic color camera.

We present a robot, called InductoBeast, that greets a new office building by learning the floorplan automatically, with minimal human intervention and a priori knowledge. Our robot architecture is unique because it combines both abductive and inductive mapping methods to solve this problem. We present experimental results spanning three office environments. We hope the breadth of these results helps to establish a performance benchmark against which robust and adaptive navigator robots of the future may be measured.