Zachary Dodds

Evaluating the Roomba: A low-cost, ubiquitous platform for robotics research and education

This paper presents the iRobot corporations Roomba vacuum as a low-cost resource for robotics research and education. Sensor and actuation models for unmodified Roombas are presented in the context of both special- and general-purpose spatial-reasoning algorithms, including Monte Carlo Localization and FastSLAM. Further tests probe the feasibility of sensor extensions to the platform. Results demonstrate that, with some caveats, the Roomba is a viable foundation for both classroom and laboratory use, especially for work seeking to leverage robots to other ends, as well as robotics per se with a computational focus.

Women in CS: an evaluation of three promising practices

Historically, Harvey Mudd College (HMC) has had very little success attracting women to the study of computer science: women have chosen CS less than any other field of study. In 2006 HMC began three practices in order to increase the number of women studying and majoring in CS; these practices have now been in place for 3 years. With this paper we describe these practices and present a thorough evaluation of the quantitative and qualitative differences that have accompanied them. In sum, these efforts have rebalanced our department by significantly increasing womens participation in our computer science program.

Components, Curriculum, and Community: Robots and Robotics in Undergraduate AI Education

This editorial introduction presents an overview of the robotic resources available to AI educators and provides context for the articles in this special issue. We set the stage by addressing the trade-offs among a number of established and emerging hardware and software platforms, curricular topics, and robot contests used to motivate and teach undergraduate AI.

Recent methods for image-based modeling and rendering

A long-standing goal in image-based modeling and rendering is to capture a scene from camera images and construct a sufficient model to allow photo-realistic rendering of new views. With the confluence of computer graphics and vision, the combination of research on recovering geometric structure from un-calibrated cameras with modeling and rendering has yielded numerous new methods. Yet, many challenging issues remain to be addressed before a sufficiently general and robust system could be built to (for instance) allow an average user to model their home and garden from camcorder video. This tutorial aims to give researchers and students in computer graphics a working knowledge of relevant theory and techniques covering the steps from real-time vision for tracking and the capture of scene geometry and appearance, to the efficient representation and real-time rendering of image-based models. It also includes hands-on demos of real-time visual tracking, modeling and rendering systems.

The evolution of a computational outreach program to secondary school students

This paper tracks the five-year growth and current trajectory of a computational outreach program at a small, liberal-arts college. The program has enhanced opportunities for talented high-school students to experience computation more deeply than their HS curriculum currently offers. This outreach evolved from a naive initial premise into a mutually beneficial interaction between an undergraduate computer science department and a local secondary school. The most important factor in the programs sustainability is a supportive liaison within the high schools administration. We hope the lessons we have learned will help other CS departments develop sustainable outreach programs.

When CS 1 is biology 1: crossdisciplinary collaboration as CS context

We present the curriculum, deployment, and initial evaluation of a course, BioCS1, designed to serve as CS1 and Biology1 for majors of either (or both) disciplines. Cotaught by professors in both fields, BioCS1 interweaves fundamental biology and computational topics in a manner similar to contextual approaches to CS1. In contrast to other contextual approaches, however, BioCS1 emphasizes both CS and its context equally. The results suggest that cross-disciplinary collaborations can succeed at the introductory level, as they have at later stages of the curriculum.

Bio1 as CS1: evaluating a crossdisciplinary CS context

We present the curriculum, deployment, and initial evaluation of a course, BioCS1, designed to serve as an introductory course in both biology and CS. Co-taught by professors in both fields, BioCS1 interweaves fundamental biology and computational topics in a manner similar to contextual approaches to CS1. In contrast to other contextual approaches, however, BioCS1 emphasizes both CS and its context equally. The results suggest that such cross-disciplinary collaborations can thrive at the introductory level, just as they have later in the curriculum.

Accessible aerial autonomy

This work presents a combination of software and hardware that makes aerial autonomy substantially more accessible both in terms of programmatic complexity and in terms of cost. We use the ARDrone quadrotor helicopter and Willow Garages Robot Operating System software infrastructure to demonstrate several autonomous tasks. Using vision as the sole aerial sensor, we demonstrate point-to-point navigation, aerial support of a ground robots, and robot localization within image-based maps. In contrasting several variations of SURFfeature matching, we demonstrate that low-cost aerial platforms can support robust, landmark-free visual spatial reasoning. This evaluation shows that aerial platforms can be practical, cost- and time-effective components of task-performing systems. We argue that aerial autonomy should be considered a broadly accessible resource, within reach of any investigator or educator of AI robotics.

Educational advances in artificial intelligence

In 2010 a new annual symposium on Educational Advances in Artificial Intelligence (EAAI) was launched as part of the AAAI annual meeting. The event was held in cooperation with ACM SIGCSE and has many similar goals related to broadening and disseminating work in computer science education. EAAI has a particular focus, however, as the event is specific to educational work in Artificial Intelligence and collocated with a major research conference (AAAI) to promote more interaction between researchers and educators in that domain. This panel seeks to introduce participants to EAAI as a way of fostering more interaction between educational communities in computing. Specifically, the panel will discuss the goals of EAAI, provide an overview of the kinds of work presented at the symposium, and identify potential synergies between that EAAI and SIGCSE as a way of better linking the two communities going forward.

Visual loop-closing with image profiles

This paper investigates the ability of image profiles, pixel-intensity sums across subsets of a video stream, to support the crucial robotic skill of place recognition through visual information alone. Building from work in which image profiles are the fundamental image representation for a model of biological neural processing [3, 4, 5], this paper offers a conceptually simpler approach to simultaneous localization and mapping via a single camera (monocular SLAM). In contrast to feature-based approaches in which extraction and statistical post-processing dominate the computation, this work uses a representation suitable even for very simple autonomous platforms. Experiments demonstrate the ability of our profile-based path segments to compensate for the inevitable inaccuracies in odometry when creating consistent world maps.