A Gesture Based Interface for Human-Robot Interaction

Service robotics is currently a highly active research area in robotics, with enormous societal potential. Since service robots directly interact with people, finding natural and easy-to-use user interfaces is of fundamental importance. While past work has predominately focussed on issues such as navigation and manipulation, relatively few robotic systems are equipped with flexible user interfaces that permit controlling the robot by natural means. This paper describes a gesture interface for the control of a mobile robot equipped with a manipulator. The interface uses a camera to track a person and recognize gestures involving arm motion. A fast, adaptive tracking algorithm enables the robot to track and follow a person reliably through office environments with changing lighting conditions. Two alternative methods for gesture recognition are compared: a template based approach and a neural network approach. Both are combined with the Viterbi algorithm for the recognition of gestures defined through arm motion (in addition to static arm poses). Results are reported in the context of an interactive clean-up task, where a person guides the robot to specific locations that need to be cleaned and instructs the robot to pick up trash.     

A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots

This paper addresses the problem of building large-scale geometric maps of indoor environments with mobile robots. It poses the map building problem as a constrained, probabilistic maximum-likelihood estimation problem. It then devises a practical algorithm for generating the most likely map from data, along with the most likely path taken by the robot. Experimental results in cyclic environments of size up to 80 by 25 meter illustrate the appropriateness of the approach.     

Bayesian Landmark Learning for Mobile Robot Localization

To operate successfully in indoor environments, mobile robots must be able to localize themselves. Most current localization algorithms lack flexibility, autonomy, and often optimality, since they rely on a human to determine what aspects of the sensor data to use in localization (e.g., what landmarks to use). This paper describes a learning algorithm, called BaLL, that enables mobile robots to learn what features/landmarks are best suited for localization, and also to train artificial neural networks for extracting them from the sensor data. A rigorous Bayesian analysis of probabilistic localization is presented, which produces a rational argument for evaluating features, for selecting them optimally, and for training the networks that approximate the optimal solution. In a systematic experimental study, BaLL outperforms two other recent approaches to mobile robot localization.     

A Probabilistic Approach to Concurrent Mapping and Localization for Mobile Robots

This paper addresses the problem of building large-scale geometric maps of indoor environments with mobile robots. It poses the map building problem as a constrained, probabilistic maximum-likelihood estimation problem. It then devises a practical algorithm for generating the most likely map from data, along with the most likely path taken by the robot. Experimental results in cyclic environments of size up to 80×25 m illustrate the appropriateness of the approach.     

Importance of the gonadotropin-releasing hormone (GnRH) surge for induction of the preovulatory luteinizing hormone surge of the ewe: dose-response relationship and excess of GnRH

The preovulatory LH surge in the ewe is stimulated by a large sustained surge of GnRH. We have previously demonstrated that the duration of this GnRH signal exceeds that necessary to initiate and sustain the LH surge. The objective of the present study was to determine whether a similar excess exists for amplitude of the GnRH surge. Experiments were performed using an animal model in which GnRH secretion was blocked by progesterone, which in itself does not block the pituitary response to GnRH. To assess the amplitude of the GnRH surge needed to induce the LH surge, we introduced artificial GnRH surges of normal contour and duration but varying amplitudes. Twelve ewes were run through 3 successive artificial follicular phases (total of 36). Six of these artificial follicular phases were positive controls, in which progesterone was removed, the estradiol stimulus was provided, and vehicle was infused. In these control cycles, animals generated endogenous LH surges. In the remaining artificial follicular phases, progesterone was not withdrawn, the estradiol stimulus was provided, and either vehicle (negative control) or GnRH solutions of varying concentrations (experimental) were infused. The circulating GnRH concentrations achieved by infusion were monitored. No LH surges were observed in negative controls, whereas LH surges were induced in experimental cycles provided a sufficient dose of GnRH was infused. A highly significant dose-response relationship was observed between the amplitude of the GnRH surge and both the amplitude of the LH surge and the area under the curve describing the LH response, but no such relationship existed between the amplitude of the GnRH surge and the duration of the LH response. In numerous cases, LH surges similar to those in the positive control animals resulted from infusion of amounts of GnRH estimated to be considerably less than those delivered to the pituitary during the endogenously generated GnRH/LH surge. These findings indicate that, in the ewe, increased GnRH secretion drives the preovulatory LH surge in a dose-dependent fashion, and they provide evidence that the amplitude of the GnRH surge may exceed that needed to generate the LH surge.     

Teaching Challenge

This paper reflects on the author's experience with the course "CS294: Projects in Artificial Intelligence," at Stanford University during the fall quarter of 2004. To gain a better understanding of artificial intelligence through collaborative project work, he and his students participated at the 2004 DARPA Grand Challenge. Although they failed to finish the course, their robot named Stanley was able to go further than any other robot had gone in the Grand Challenge. The experience taught his students some valuable new lessons about working in large teams that are focused on true challenge problems     

Anytime search in dynamic graphs

Agents operating in the real world often have limited time available for planning their next actions. Producing optimal plans is infeasible in these scenarios. Instead, agents must be satisfied with the best plans they can generate within the time available. One class of planners well-suited to this task are anytime planners, which quickly find an initial, highly suboptimal plan, and then improve this plan until time runs out.A second challenge associated with planning in the real world is that models are usually imperfect and environments are often dynamic. Thus, agents need to update their models and consequently plans over time. Incremental planners, which make use of the results of previous planning efforts to generate a new plan, can substantially speed up each planning episode in such cases.In this paper, we present an A^∗-based anytime search algorithm that produces significantly better solutions than current approaches, while also providing suboptimality bounds on the quality of the solution at any point in time. We also present an extension of this algorithm that is both anytime and incremental. This extension improves its current solution while deliberation time allows and is able to incrementally repair its solution when changes to the world model occur. We provide a number of theoretical and experimental results and demonstrate the effectiveness of the approaches in a robot navigation domain involving two physical systems. We believe that the simplicity, theoretical properties, and generality of the presented methods make them well suited to a range of search problems involving dynamic graphs.     

Web interfaces for mobile robots in public places

The growth of the World Wide Web provides unique opportunities to bring robots closer to people. The vision behind such endeavors ranges from relatively simple web-based inspections and surveillance applications to highly versatile applications that use robots connected to the web to establish a remote telepresence in dynamic and populated environments. In the latter scenario, robots play the role of a physical mediator, enabling remote people to acquire information, explore, manipulate, communicate, and interact physically with people far away. The article describes a series of web interfaces designed to remotely operate mobile robots in public places through the web. The design of these interfaces specifically addresses issues such as low bandwidth of interconnections, control brokering, and shared control as well as interaction with people in the robot's environment, which arise naturally in applications with web-based robot control. The interfaces have been tested extensively using two deployed service robots, which were installed as interactive tour guides in two museums. The article also discusses trade-offs and limitations of web-based robots that interact with people in populated public places     

In vivo micro-image mosaicing

Recent advances in optical imaging have led to the development of miniature microscopes that can be brought to the patient for visualizing tissue structures in vivo. These devices have the potential to revolutionize health care by replacing tissue biopsy with in vivo pathology. One of the primary limitations of these microscopes, however, is that the constrained field of view can make image interpretation and navigation difficult. In this paper, we show that image mosaicing can be a powerful tool for widening the field of view and creating image maps of microanatomical structures. First, we present an efficient algorithm for pairwise image mosaicing that can be implemented in real time. Then, we address two of the main challenges associated with image mosaicing in medical applications: cumulative image registration errors and scene deformation. To deal with cumulative errors, we present a global alignment algorithm that draws upon techniques commonly used in probabilistic robotics. To accommodate scene deformation, we present a local alignment algorithm that incorporates deformable surface models into the mosaicing framework. These algorithms are demonstrated on image sequences acquired in vivo with various imaging devices including a hand-held dual-axes confocal microscope, a miniature two-photon microscope, and a commercially available confocal microendoscope.     

The dynamic window approach to collision avoidance

This approach, designed for mobile robots equipped with synchro-drives, is derived directly from the motion dynamics of the robot. In experiments, the dynamic window approach safely controlled the mobile robot RHINO at speeds of up to 95 cm/sec, in populated and dynamic environments