As autonomous social robots become more prevalent in home environments, they must decide where to position themselves within many different types of rooms or spaces, balancing accessibility with staying out of the way. This paper presents a machine learning approach to modeling user preferences for robot parking spots in the home using standard 2D occupancy maps. Our method learns spatial patterns from the information available in the occupancy maps and user-annotated floorplans without requiring specialized inputs. We evaluate the approach using floorplan data from 84 users who provided parking spot preferences after living with and evaluating a social robot in their homes for at least two weeks. Our method significantly outperforms a state-of-the-art baseline focused exclusively on avoiding walking paths. We demonstrate how the approach extends to additional map features and share insights about the types of preference patterns learned by the model. This contribution provides a framework that can incorporate new environmental inputs as robot perception capabilities evolve.

As robots enter our homes and workplaces, they will have more direct access to us, our information, and our daily lives. The more a robot knows about us, the more helpful it can be, at least in theory. Where is the balance between privacy and utility? How might the robot communicate the tradeoffs between privacy and utility in a nuanced but clear manner? How can we ensure that the perception of privacy-protection offered by the robot accurately reflects how much the robot is actually preserving our privacy? How can a robot learn information that it can use to better help us without being intrusive? What behaviors should the robot have (or not have) to not only ensure that it protects our privacy, but also is perceived as protecting our privacy? How can we measure the effectiveness of these behaviors, so that we can track our progress towards more useful, less invasive robot companions? This workshop is the the third in a series at HRI, and will bring together researchers from a wide variety of intellectual communities to look at these questions, identify promising research directions, and set an agenda for how to start making progress. We are particularly interested in expanding the core of researchers interested in privacy-related issues in HRI, and in those “privacy-curious” researchers who want to find out more about he intersection of privacy and their own research.

Privacy is an important yet understudied focus in consideration of successful human-robot interaction (HRI). In this paper, we present a thematic analysis of the topics discussed in the Privacy-Aware Robotics Workshop held at the HRI Conference in 2024. The analysis points across the perspectives of User, Engineering, and Society with particular identification of open “interdisciplinary zones” at the intersections of these perspectives. Based on that, we formulate and present three main themes for future research directions: the tension between robot functioning and effectiveness of privacy implementations in real-world contexts; the need to involve and empower target user communities in the co-design of privacy-aware robots, and the consideration of regulatory frameworks that extend across jurisdictions in robot design.

In the wake of the global health crisis caused by the COVID-19 pandemic, there is a pressing need for innovative disinfection methods that are both effective and user-friendly to a broad user base. This paper introduces an approach that allows a user to instruct tasks to an ultraviolet (UV) disinfection robot via speech. The implementation of a voice interface offers a hands-free operation and caters to non-technical users who require a simple and effective way to command the robot. Through a combination of object recognition, natural language processing using a large language model (LLM), and task planning, our system can execute tasks more effectively since it is more aware of the context of its sanitizing duties.

For social robots operating in home environments, identifying appropriate parking locations which are "out of the way" is a challenging and multi-faceted problem. This paper proposes a solution to one core aspect of that problem, specifically a model for estimating locations where the robot may block walking paths through narrow spaces. For generality, this model assumes no a priori knowledge about user behaviors or semantic features in the space, and is derived purely from spatial geometry based on a standard 2D occupancy map. An experimental validation based on self-reported parking spot preferences from long-term robot users demonstrates that the proposed model captures 74% of user preferences, outperforming a naive baseline condition in selecting user-preferred parking spots. The proposed method provides a basis for estimating socially-appropriate parking locations for robots operating in the home or other unstructured social spaces and serves as a foundation for developing more sophisticated parking spot preference models in the future.

Ultraviolet-C (UV-C) robot irradiation is a promising approach for disinfecting surfaces contaminated by pathogens in healthcare settings. However, limitations exist with current UV disinfection robots, including coverage for complex surface geometries. This research presents a system for human-guided robotic UV disinfection that uses empirical sensor measurements rather than relying on high-accurate models for UV map coverage. Human guidance is integrated into the methodology to enhance disinfection, aiding in addressing complex shaped objects and topologies. Further, a validation test confirmed that our estimation approach reliably underestimates the UV exposure, which is beneficial for ensuring thorough disinfection. Initial user studies demonstrated that while autonomous disinfection was effective for simple objects like tabletops, human-guided disinfection, especially with feedback, improved coverage and speed for complex shapes like mugs. Combining human intuition with autonomy shows potential for enhancing robotic disinfection effectiveness.

Many critical robot environments, such as healthcare and security, require robots to account for contextdependent criteria when performing their functions (e.g., navigation). Such domains require decisions that balance multiple factors, making it difficult for robots to make contextually appropriate decisions. Multi-Objective Optimization (MOO) methods offer a potential solution by trading off between objectives; however concepts like Pareto fronts are not only expensive to compute but struggle with differentiating among solutions on the Pareto front. This work introduces the Contextual Multi-Objective Path Planning (CMOPP) algorithm, which enables the robot to trade off different complex costs dependent on context. The key insight of this work is to separate the path planning and path cost estimation into two independent steps, thus significantly reducing computation cost without impacting the quality of the resulting path. As a result, CMOPP is able to accurately model path costs, which provide meaningful trade-offs when choosing a path that best fits the context. We show the benefits of CMOPP on case studies that demonstrate its contextual path planning capabilities. CMOPP finds contextually appropriate paths by first reducing the search space up to 99.9% to a near-optimal set of paths. This reduction enables the generation of accurate path cost models, using up to 90% less computation than similar methods.

For social robots to successfully integrate into daily life in home environments, they will need reliable models of the way people perceive and use space in the home. This paper explores the problem of obtaining annotated training data at scale for subjective judgments about spatial locations. Focusing on the use case of identifying good and bad parking spots for a social robot operating in a home environment, two experiments are presented. The first study shows that the presentation of context-rich 3D images to human annotators yields notably different outcomes from those obtained when using 2D robot navigation maps. We attribute the source of these differences to a set of features visible only in the 3D views and introduce a technique for labeling these features on the 2D maps. The second study reveals that using labeled 2D maps produces annotation data very similar to that obtained using 3D images. Since a labeled 2D map can be generated at a fraction of the cost of a full set of 3D views, we recommend this method as a scalable approach to collecting subjective spatial data annotations in everyday environments.

Most people do not have direct access to knowledge about the inner workings of robots. Instead, they must develop mental models of the robot, a process that is not well understood. This article presents findings from a long-term, in-the-wild, qualitative, hypothesis-generating study of the mental model formation process. The focus was on how (qualitatively) users form mental models of the robot—specifically its perceptual capabilities, rules of behavior, and communication with other humans. Participants of diverse ages had multiple interactions with the robot over six weeks in a non-laboratory setting. The robot’s rules of behavior were changed every two weeks. A novel, non-anthropomorphic robot was created for the study with a realistic use case: storing people’s shoes during a yoga class. This article reports findings from a case study analysis of 28 interviews conducted over six weeks with six participants. These findings are organized into six topics: (1) variability in the rate at which mental models are updated to be more predictive, (2) types of reasoning and hypothesizing about the robot, (3) borrowing from existing mental models and use of imagination, (4) attributing sensing capabilities where there are no visible sensors, (5) judgments about whether the robot is autonomous or teleoperated, and (6) experimenting with the robot. Specific suggestions for future research are given throughout, culminating in a set of study design recommendations. This work demonstrates the fruitfulness of long-term, in-the-wild studies of human-robot interaction, of which mental model formation is a foundational aspect.

In this paper we propose a framework for conceptualizing and demonstrating a good-faith effort when developing autonomous systems. The framework addresses two fundamental problems facing autonomous systems: (1) the disconnect between human-mental models and machine-based sensors and algorithms; and (2) unpredictability in complex systems. We address these problems using a mix of education - explicitly delineating the mapping between human concepts and their machine equivalents in a structured manner - and data sampling with expected ranges as a testing mechanism.

The Robotics Program at Oregon State University has beenrunning an NSF-funded summer Research Experiences forUndergraduates (REU) site since 2014. Over twenty studentsper year (on average) have participated in the site, spendingten weeks embedded in the OSU Robotics Program. Our mainfocus with this REU Site is to give the participants a com-plete research experience, from problem definition to the fi-nal presentation of results, "in miniature". Our secondary ed-ucational objectives are: 1) Teach basic non-technical skillsneeded for graduate work, such as time management and lit-erature review, 2) Provide details on how to apply to gradu-ate school and for funding, 3) Clarify what we look for in agraduate student, and 4) Detail what to expect from the grad-uate student experience. In this paper, we describe the over-all structure of the participants’ summer experience, outlinesome of the training materials that we use, describe the moti-vations for our approach, and discuss the lessons that we havelearned after running the program for a number of years.

Privacy-sensitive robotics is an emerging area of HRI research. Judgments about privacy would seem to be context-dependent, but none of the promising work on contextual "frames" has focused on privacy concerns. This work studies the impact of contextual "frames" on local users' privacy judgments in a home telepresence setting. Our methodology consists of using an online questionnaire to collect responses to animated videos of a telepresence robot after framing people with an introductory paragraph. The results of four studies indicate a large effect of manipulating the robot operator's identity between a stranger and a close confidante. It also appears that this framing effect persists throughout several videos. These findings serve to caution HRI researchers that a change in frame could cause their results to fail to replicate or generalize. We also recommend that robots be designed to encourage or discourage certain frames.

State-of-the-art personal robots must perform complex manipulation tasks to be viable in assistive scenarios. However, many of these robots, like the PR2, use manipulators with high degrees-of-freedom. The complexity of these robots lead to large dimensional state spaces, which are difficult to fully explore. Our previous work introduced the IDRRL algorithm, which compresses the learning space by transforming a high-dimensional learning space onto a lower-dimensional manifold while preserving expressivity. In this work we formally prove that IDRRL maintains PAC-MDP guarantees. We then improve upon our previous formulation of IDRRL by introducing cascading autoencoders (CAE) for dimensionality reduction, producing the new algorithm IDRRL-CAE. We demonstrate the improvement of this extension over our previous formulation, IDRRL-PCA, in the Mountain Car and Swimmers domains.

The advent of robotics technology raises new privacy concerns, but preliminary research in this area has not included members of the general public in the conversation. This study used three focus groups to see what types of privacy concerns would be mentioned by typical users and to see what other topics were deemed important by the participants. The conversations were based around three concrete scenarios involving telepresence robots: an in-home tele-maid, a boss attending a meeting via telepresence, and a medical robo-ceptionist. Codings of our transcripts yielded privacy-relevant concerns not yet categorized by the literature such as hacking, theft, embarrassment, and marketing. These findings will give privacy-sensitive robotics researchers (1) a more complete list of privacy categories to measure, (2) new research questions to pursue, and (3) privacy-enhancing design suggestions to test.

Teleoperated robots can be used to provide medical care to patients in infectious disease outbreaks, alleviating workers from being in dangerous infectious zones longer than absolutely needed. Nevertheless, patients' reactions to this technology have not been tested. We test three hypotheses related to patients' comfort and trust of the operator and robot in a simulated Ebola Treatment Unit. Our findings suggest patients trust the robot teleoperator more when they can see the teleoperator.

We present a study that examines the efficiency and usability of three different interfaces for specifying which objects should be kept private (i.e., not visible) in an office environment. Our study context is a robot “janitor” system that has the ability to blur out specified objects from its video feed. One interface is a traditional point-and-click GUI on a computer monitor, while the other two operate in the real, physical space: users either place markers on the objects to indicate privacy or use a wand tool to point at them. This late-breaking report presents qualitative feedback from users for improving the interfaces.

Real-time contamination monitoring in health care facilities would allow medical teams to take appropriate actions to carefully enter, avoid, or decontaminate contaminated areas, reducing infection risk for themselves and their patients. In this paper, we demonstrate and evaluate the first end-to-end, real-time contamination tracking system for robotic health care support. The system models contamination of the environment and people, directs decontamination efforts of a simulated scrubber robot, and alerts users when nearing contaminated areas. We outline our transmission model design choices, as based on Ebola virus disease, and evaluate the system against the spread of a physical substance.

We present a study that examines the efficiency and usability of three different interfaces for specifying which objects should be kept private (i.e., not visible) in an office environment. Our study context is a robot “janitor” system that has the ability to blur out specified objects from its video feed. One interface is a traditional point-and-click GUI on a computer monitor, while the other two operate in the real, physical space: users either place markers on the objects to indicate privacy or use a wand tool to point at them. We compare the interfaces using both self-report (e.g., surveys) and behavioral measures. Our results showed that (1) the graphical interface performed better both in terms of time and usability, and (2) using persistent markers increased the participants' ability to recall what they tagged. Choosing the right interface appears to depend on the application scenario. We also summarize feedback from the participants for improving interfaces that specify visual privacy preferences.

The ROS ecosystem is an interconnected web of packages, nodes and people with no efficient means to compare, assess or visualize them. We develop a set of tools consisting of various metrics, a data visualization web app, and an active monitoring system. With these tools, we measure the current state of the ecosystem as well as determine where the community should direct their efforts. We also encourage the community to provide input on potential applications, additional metrics, and further improvements to address the needs of the ROS ecosystem. We incentivize this input by gamifying community contributions to the infrastructure. Encouraging user-driven improvements to the ROS infrastructure through the use of a leaderboard and friendly competition will advance ROS development and community support far into the future.

Many navigation systems, including the ubiquitous ROS navigation stack, perform path-planning on a single costmap, in which the majority of information is stored in a single grid. This approach is quite successful at generating collision-free paths of minimal length, but it can struggle in dynamic, people-filled environments when the values in the costmap expand beyond occupied or free space. We have created and implemented a new method called layered costmaps, which work by separating the processing of costmap data into semantically-separated layers. Each layer tracks one type of obstacle or constraint, and then modifies a master costmap which is used for the path planning. We show how the algorithm can be integrated with the open-source ROS navigation stack, and how our approach is easier to fine-tune to specific environmental contexts than the existing monolithic one. Our design also results in faster path planning in practical use, and exhibits a cleaner separation of concerns that the original architecture. The new algorithm also makes it possible to represent complex cost values in order to create navigation behavior for a wide range of contexts.

High-level control of mobile robots currently requires use of a personal computer and traditional graphical user interface in the vast majority of cases. Such interfaces are not natural and frequently poorly suited to interacting with robots when tasking the robot to perform very short interactions requiring only brief commands. This is a problem that is especially acute for persons with disabilities. New technologies, such as Google Glass provide a variety of high quality sensors and an unobtrusive display which allows users to have a powerful robot control interface with them at all times. In this paper we present a system which provides the basic elements required in order for a user to interact with a robot using Glass. We also informally evaluate Glass as an input device, and present several examples of applications that this interface enables.

Currently, high-level task control of robots is generally performed by using a graphical interface on a desktop or laptop computer. This type of mediated interaction is not natural, and can be problematic and cumbersome for persons with certain types of motor disabilities, and for people interacting with the robot when there are no computer displays present. In this work, we present a framework which enables the removal of such obvious intermediary devices and allows users to assign tasks to robots using interfaces embedded directly in the world, by projecting these interfaces directly onto surfaces and objects. We describe the implementation of the projected interface framework, and give several examples of tasks which can be performed with such an interface.

Modern societies depend on complex and critical infrastructures for energy, transportation, sustenance, medical care, emergency response, communications security. As computers, automation, and information technology (IT) have advanced, these technologies have been exploited to enhance the efficiency of operating the processes that make up these infrastructures. Where commonalities exist between different infrastructures or elements of a common infrastructure, such as in the electric power grid, the potential for even greater efficiencies has fueled the desire to integrate intelligent sensing and control architectures and methods over a large region. The results of this integration are the highly interconnected and interdependent control systems of today. However, as we have observed over recent decades, natural disasters, and terrorist attacks can produce failures in complex systems such as utility and transportation infrastructure the consequences of which resulting enormous losses to economy and security. To minimize the impact of these crippling events, society requires control system architectures and methods that maximize the resilience of the complex systems upon which society depends. By “resilience” we mean the capacity of a control system to maintain state awareness and to proactively maintain a safe level of operational normalcy in response to anomalies, including threats of a malicious and unexpected nature[1]. Threats are those elements that counter normalcy and destabilize control system networks, including human error and malicious human attacks, complex latencies and interdependencies.

Effective robot navigation in the presence of humans is hard. Not only do human obstacles move, they react to the movements of the robot according to instinct and social rules. In order to efficiently navigate around each other, both the robot and the human must move in a way that takes the other into account. Failure to do so can lead to a lowering of the perceived quality of the interaction and, more importantly, it can also delay one or both parties, causing them to be less efficient in whatever task they are trying to achieve. In this paper, we present a system capable of creating more efficient corridor navigation behaviors by manipulating existing navigation algorithms and introducing social cues from the robot to the human. We give the results of a user study, demonstrating the effectiveness of our system, and discuss how it can be applied more generally to a wide variety of situations.

After many years, the robotics research community has settled on standard middleware: the Robot Operating System (ROS). This standard presents a great opportunity for educational robotics. This hands-on workshop will engage participants in ROS-based curricula for CS 02 and advanced undergraduates. The workshop will highlight how ROS has simplified, enabled, and expanded flipped robotics curricula in CS 02. Our advanced materials show how ROS enables easy access to the robotics research community, permitting larger and more research-representative projects. This workshop is two long hands-on sessions punctuated with short reports from the presenters' experience. Participants will implement the first two assignments of our CS 2 curriculum. http://www.cs.hmc.edu/dodds/ROSatSIGCSE2013.

The Robots for Humanity project aims to enable people with severe motor impairments to interact with their own bodies and their environment through the use of an assistive mobile manipulator, thereby improving their quality of life. Assistive mobile manipulators (AMMs) are mobile robots that physically manipulate the world in order to provide assistance to people with disabilities. They present an exciting frontier for assistive technology, as they can operate away from the user, have a large dexterous workspace (due to their mobility), and not directly encumber their users. The cornerstone of this project is an ongoing, interactive design process with a quadriplegic user, Henry Evans, and his wife and primary caregiver, Jane Evans. Henry has been enabled, through the use of a PR2 robot, to scratch his own face, shave, fetch a towel from his kitchen, and hand out Halloween candy to trick-ortreating children at a local mall.

We present an interface that allows users to direct a mobile manipulation robot in tabletop pick-and-place tasks using only their head motions and a single button. The system uses an estimate of the user's head pose and a 3d world model maintained by the robot to determine where the user is pointing their head. We give the results of some preliminary evaluations of our system, which suggest that it is both intuitive and effective. We also describe an example trash-sorting application where the user directs a PR2 robot sort objects in to “trash” and “recycle” piles.

This paper presents a generative model of eye-hand coordination. We use numerical optimization to solve for the joint behavior of an eye and two hands, deriving a predicted motion pattern from first principles, without imposing heuristics. We model the planar scene as a POMDP with 17 continuous state dimensions. Belief-space optimization is facilitated by using a nominal-belief heuristic, whereby we assume (during planning) that the maximum likelihood observation is always obtained. Since a globally-optimal solution for such a high-dimensional domain is computationally intractable, we employ local optimization in the belief domain. By solving for a locally-optimal plan through belief space, we generate a motion pattern of mutual coordination between hands and eye: the eye's saccades disambiguate the scene in a task-relevant manner, and the hands' motions anticipate the eye's saccades. Finally, the model is validated through a behavioral experiment, in which human subjects perform the same eye-hand coordination task. We show how simulation is congruent with the experimental results.

Time utility functions can describe the complex timing constraints of real-time and cyber-physical systems. However, utility aware scheduling policy design is an open research problem. Previously we solved a Markov Decision Process formulation of the scheduling problem to derive value-optimal scheduling policies for systems with periodic real-time task sets and stochastic non-preemptive execution intervals. However, the complexity of computing solutions and their policy storage requirements necessitate the exploration of scalable solutions. In this paper we generalize the Utility Accrual Packet Scheduling Algorithm. We compare several heuristics to Markov Decision Process policy evaluation under soft and hard real-time conditions, different load conditions, and different classes of time utility functions. Based on these evaluations we present guidelines for which heuristics are best suited to particular scheduling criteria.

No abstract available.

No abstract available.

Telepresence robots are becoming increasingly popular and are increasingly ready to enter use in the real world as stand-ins for remote humans. It is useful, but currently uncommon, to provide the human operator with an approximation of peripheral vision and the ability to saccade around the scene. We have developed an interface which provides peripheral vision to a remote operator by using a motorized pan-tilt camera to create a panorama, and enables the operator to move the camera's gaze within that panorama.

Polonius is a robot control interface designed for running Wizard of Oz style experiments. It is designed to be easy enough to be used by the non-programmer collaborators of roboticists. The program acts as an intermediary between the robot and a wizard interacting with a GUI based on a pre-defined script. Polonius also eliminates the need for coding the video after experiments by integrating a robust logging system.

Most commercially-available robots are either aimed at the research community, or are designed with a single purpose in mind. The extensive hobbyist community has tended to focus on the hardware and the low-level software aspects. We claim that there is a need for a low-cost, general-purpose robot, accessible to the hobbyist community, with sufficient computation and sensing to run “research-grade” software. In this paper, we describe the design and implementation of such a robot. We explicitly outline our design goals, and show how a capable robot can be assembled from off-the-shelf parts, for a modest cost, by a single person with only a few tools. We also show how the robot can be used as a low-cost telepresence platform, giving the system a concrete purpose beyond being a low-cost development platform.

Operating robots across networks with unknown, bandwidth, latency and other conditions presents difficulty when the operation depends on real-time feedback and control. Standard video compression methods do a good job compressing arbitrary video, but do not take domain knowledge into account when more information about the video is known beforehand. We have incorporated robot odometry into the video pipeline, allowing video quality to be selectively reduced at times when odometry suggests that such a reduction will not adversely affect task performance of human operators. We found that selectively reducing video quality significantly reduced bandwidth usage, increasing the robot's responsiveness and controllability, while having no measurable effect on task performance.

Given the difficulty of social human-robot interaction (HRI), finding an appropriate conceptual model, as well as a useful venue to test the model, is key. While most work in social HRI draws insight and inspiration from the field of social psychology, this paper explores the philosophical backing and benefits of using ideas from theatre to frame social interactions. We present an analogy to Searle's Chinese Room argument to motivate the expressive challenges faced by human actors and by robots in social situations. We then compare the elements of theatre with the elements of HRI, and discuss techniques that we believe will lead to improved interactions.

Human-Robot Interaction researchers are beginning to reach out to fields not traditionally associated with interaction research, such as the performing arts, cartooning, and animation. These collaborations offer the potential for novel insights about how to get robots and people to interact more effectively, but they also involve a number of unique challenges. This full-day workshop will offer a venue for HRI researchers and their collaborators from these diverse fields to report on their work, share insights about the collaboration process, and to help begin to define an exciting new area in HRI.

The robust operation of many sensor network applications depends on deploying relays to ensure wireless coverage. Radio mapping aims to predict network coverage based on a small number of link measurements. This problem is particularly challenging in complex indoor environments where walls significantly affect radio signal propagation. Nevertheless, we show that it is feasible to accurately predict coverage through a two-step process: a propagation model is used to predict signal strength at a recipient node, which is then mapped to a coverage prediction. Through an in-depth empirical study, we show that complex models do not necessarily produce accurate estimates of signal strength: there is an important tradeoff between model accuracy and the number of parameters that must be estimated from limited training data. We find that the best performance is achieved by a family of models which classify walls based on their attenuation into a small number of classes and develop an algorithm to perform this classification automatically. Based on these insights, we build a novel Radio Mapping Tool (RMT) for predicting radio converge in indoor environments. Experimental results demonstrate RMT's effectiveness in two buildings: RMT reduces the number of locations where coverage is erroneously predicted to exist by as much as 39% and 54% compared to the classic log-normal radio propagation model.

Open soft real-time systems, such as mobile robots, must respond adaptively to varying operating conditions, while balancing the need to perform multiple mission specific tasks against the requirement that those tasks complete in a timely manner. Setting and enforcing a utilization target for shared resources is a key mechanism for achieving this behavior. However, because of the uncertainty and non-preempt ability of some tasks, key assumptions of classical scheduling approaches do not hold. In previous work we presented foundational methods for generating task scheduling policies to enforce proportional resource utilization for open soft real-time systems with these properties. However, these methods scale exponentially in the number of tasks, limiting their practical applicability.In this paper, we present a novel parameterized scheduling policy that scales our technique to a much wider range of systems. These policies can represent geometric features of the scheduling policies produced by our earlier methods, but only require a number of parameters that is quadratic in the number of tasks. We provide empirical evidence that the best of these policies are competitive with exact solution methods in small problems, and significantly outperform heuristic methods in larger ones.

Abstract—Classical scheduling abstractions such as deadlines and priorities do not readily capture the complex timing semantics found in many real-time cyber-physical systems. Time utility functions provide a necessarily richer description of timing semantics, but designing utility-aware scheduling policies using them is an open research problem. In particular, scheduling design that optimizes expected utility accrual is needed for realtime cyber-physical domains. In this paper we design scheduling policies that optimize expected utility accrual for cyber-physical systems with periodic, non-preemptable tasks that run with stochastic duration. These policies are derived by solving a Markov Decision Process formulation of the scheduling problem. We use this formulation to demonstrate that our technique improves on existing heuristic utility accrual scheduling policies. I.

This paper proposes a novel approach for coupling perception and action through minimax dynamic programming. We tackle domains where the agent has some control over the observation process (e.g. via the manipulation of some sensors), and show how to transform the system so that an optimal control solution can be sought with standard algorithms. We demonstrate our method in a toy domain, where an agent guides two point masses (ldquohandsrdquo) to a target in a 2D scene with obstacles. The agent can direct the gaze of a virtual ldquoeyerdquo to different parts of the scene, thereby reducing the observation noise for elements of the scene in that vicinity and improving the quality of feedback control. In this manner, motor control of the eye allots attentional resources. We propose a unified framework that treats both perception and action as interdependent components of the same optimal control task. The implications of uncertainty on task performance are uncovered by deploying an adversary whose strength to do harm is proportional to the instantaneous level of state uncertainty. We transform the partially-observable system to a fully-observable by coupling the state dynamics with a state-estimation filter, and so augment the state space to include an explicit representation of the instantaneous state uncertainty. The augmented system is high-dimensional, but through minimax differential dynamic programming, a local method that is less susceptible to the curse of dimensionality, we are able to solve for the optimal control of the hands and the eye at the same time, allowing for the emergence of interesting phenomena such as hand-eye coordination, saccades and smooth pursuit.

Plenteous research studies schemata in Genetic Programming (GP), though little of it is been empirical, due to the vast numbers of typical schemata in even small populations. In this research, we define maximal schemata, and extend our TRIPS algorithm to the more general Max-Schema-Growth (MSG) algorithm, applicable to a wider range of schema forms (TRIPS only handles standard fragment schemata). We present MSG specialized to work with unordered-fragments schemata (tree-fragments with unordered functions), and compare the number of maximal schemata found of these two forms. For most maximal fragments, another maximal fragment was also found that differed only by the orders of function node arguments. We conclude that maximal unordered-fragments may represent a greater range of common patterns between programs than standard maximal fragments, though the greater reach comes at a price with a severe increase in the time taken by the algorithm.

Open soft real-time systems, such as mobile robots, experience unpredictable interactions with their environments and yet must respond both adaptively and with reasonable temporal predictability. New scheduling approaches are needed to address the demands of such systems, in which many of the assumptions made by traditional real-time scheduling theory do not hold. In previous work we established foundations for a scheduling policy design and verification approach for open soft real-time systems, that can use different decision models, e.g., a Markov decision process (MDP), to capture the nuances of their scheduling semantics.However, several important refinements to the preliminary techniques developed in that work are needed to make the approach applicable in practice. This paper makes three main contributions to the state of the art in scheduling open soft real-time systems: (1) it defines a novel representation of the scheduling state space that is both more compact and more expressive than the model defined in our previous work; (2) it exploits regular structure of that representation to allow efficient verification of properties involving both discrete and continuous system state variables under specific scheduling policies; and (3) it removes the unnecessary use of a time horizon in our previous approach, thus allowing the more precise specification and enforcement of a wider range of scheduling policies for open soft real-time systems.

We develop a framework to allow generic object detection algorithms to exploit geometric information commonly available to robot vision systems. Robot systems take pictures with calibrated cameras from known positions and may simultaneously capture depth measurements in the scene. This allows known constraints on the 3D size and position of objects to be translated into constraints on potential locations and scales of objects in the image, eliminating potentially expensive image operations for geometrically infeasible object locations. We show this integration to be very natural in the context of face detection and find that the computational effort of the standard Viola Jones face detector (as implemented in OpenCV) can be reduced by 85 percent with three times fewer false positives.

This paper presents an algorithm for adapting periodic behavior to gradual shifts in task parameters. Since learning optimal control in high dimensional domains is subject to the 'curse of dimensionality', we parametrize the policy only along the limit cycle traversed by the gait, and thus focus the computational effort on a closed one-dimensional manifold, embedded in the high-dimensional state space. We take an initial gait as a departure point, and iterate between modifying the task slightly, and adapting the gait to this modification. This creates a sequence of gaits, each optimized for a different variant of the task. Since every two gaits in this sequence are very similar, the whole sequence spans a two-dimensional manifold, and combining all policies in this 2-manifold provides additional robustness to the system. We demonstrate our approach on two simulations of bipedal robots - the compass gait walker, which is a four-dimensional system, and RABBIT, which is ten-dimensional. The walkers' gaits are adapted to a sequence of changes in the ground slope, and when all policies in the sequence are combined, the walkers can safely traverse a rough terrain, where the incline changes at every step.

The control of high-dimensional, continuous, non-linear systems is a key problem in reinforcement learning and control. Local, trajectory-based methods, using techniques such as Differential Dynamic Programming (DDP) are not directly subject to the curse of dimensionality, but generate only local controllers. In this paper, we introduce Receding Horizon DDP (RH-DDP), an extension to the classic DDP algorithm, which allows us to construct stable and robust controllers based on a library of local-control trajectories. We demonstrate the effectiveness of our approach on a series of high-dimensional control problems using a simulated multi-link swimming robot. These experiments show that our approach effectively circumvents dimensionality issues, and is capable of dealing effectively with problems with (at least) 34 state and 14 action dimensions.

This paper introduces a methodology for human-robot interaction (HRI) experiments that involves soliciting the general public for participation. In particular, it reviews a series of HRI usability experiments with visitors to the Saint Louis Science Center and the Museum of Idaho's annual Science and Engineering Expo between the years 2003 and 2006. During these events visitors to the museums evaluated the usability of various levels of robot autonomy, teamed with fellow humans to evaluate distributing control of an individual robot, and provided data for a comparative analysis of a variety of data representation schemes.

Simulation is becoming an increasingly important aspect of mobile robots. As we are better able to simulate the real world, we can usefully perform more research in simulated environments. The key aspects of a good simulator, an accurate physics simulation and realistic graphical rendering system, are also central to modern computer games. In this paper, we describe a robot simulation environment built from technologies typically used in computer video games. The simulator is capable of simulating multiple robots, with realistic physics and rendering. It can also support human-controlled avatars using a traditional first-person interface. This allows us to perform robot-human interaction and collaboration studies in the simulated environment. The distributed nature of the simulation allows us to perform large-scale experiments, with users participating from geographically remote locations

We consider a variant of Q-learning in continuous state spaces under the total expected discounted cost criterion combined with local function approximation methods. Provided that the function approximator satisfies certain interpolation properties, the resulting algorithm is shown to converge with probability one. The limit function is shown to satisfy a fixed point equation of the Bellman type, where the fixed point operator depends on the stationary distribution of the exploration policy and the function approximation method. The basic algorithm is extended in several ways. In particular, a variant of the algorithm is obtained that is shown to converge in probability to the optimal Q function. Preliminary computer simulations are presented that confirm the validity of the approach.

High-school robotics competitions of all sorts are hugely popular. Robotics courses are now being widely taught in colleges and universities. Commercial applications of robotics are growing, as it becomes practical to deploy autonomous systems in the real world. Despite the activity in each of these areas, there is a lack of continuity between them. In this paper, we describe our plans for a novel outreach and education program that attempts to bridge between the worlds of high-school, university, and research laboratory robotics.

We describe a complete, end-to-end system for taking well-composed photographs using a mobile robot. The general scenario is a reception, or other event, where people are roaming around talking to each other. The robot serves as an "event photographer", roaming around the same space as the participants, periodically taking photographs. These images are then sent to a workstation where participants can print the photographs out, or email them.

Programming mobile robots can be a long, time-consuming process. Specifying the low-level mapping from sensors to actuators is prone to programmer misconceptions, and debugging such a mapping can be tedious. The idea of having a robot learn how to accomplish a task, rather than being told explicitly, is an appealing one. It seems easier and much more intuitive for the programmer to specify what the robot should be doing, and to let it learn the fine details of how to do it. In this paper, we introduce a framework for reinforcement learning on mobile robots and describe our experiments using it to learn simple tasks.

Design and test engineers in some companies have resisted the use of circuit simulation programs because of the necessity of learning a special language for circuit input and of the necessity of becoming too involved in computer operations. To overcome these objections the Circuit Analysis and Simulation Group at AE Labs has designed graphics processor programs to interface between the designer and the simulation programs. This paper provides a description of the current generation of these programs.