48 results for MacDonald, Bruce, Conference item

  • Improving The 2.5D STAGE Robotic simulator

    Wong, N; Peng Hsu, JC; Collett, Toby; MacDonald, Bruce (2008)

    Conference item
    The University of Auckland Library

    The open source Stage simulator is a plug-in for the Player robotic software system, that enables the user to test robotic devices in a simulated environment. While designing and building the hardware for a new robotic system might consume numerous months, the Stage simulator provides for building a simulation world with different robotic devices, and for the execution of different tasks, in a time frame of less than a week. Recent additions to Stage include a 2.5D version for simulating objects with simple height properties. However, the 2.5D version of Stage is incomplete. This project aims to provide a complete working solution for 2.5D. Several changes to Stage 2.5D are reported, including improvements to the collision detection and the addition of a gripper device that moves in the z direction. The solution for the collision detection issue provides full 2.5D collision detection functionality and the gripper model is used to allow the robot to complete simple 2.5D tasks such as stacking an object on top of another.

    View record details
  • Integration of a 3D-TOF camera into an autonomous, mobile robot system

    Hussmann, S; Schauer, D; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    3D imaging systems can provide valuable information for autonomous robot navigation. Still the most significant challenge in robot navigation is to have knowledge of 3D dynamic information about the object of interest in the environment. Time-of-Flight (TOF) sensors have recently become available at reasonable prices and offer the possibility to deliver the dynamic object information required for robot navigation. In comparison to stereo vision systems and laser range scanners they combine the advantages of active sensors providing accurate distance measurements and camera-based systems recording a 2D matrix at a high frame rate. This paper focuses on the integration of a TOF sensor into an autonomous, mobile robot system. Experimental results show that the TOF sensor is more suited for robot navigation than the existing laser range system.

    View record details
  • Markerless Augmented Reality for Robots in Unprepared Environments

    Chen, Ian; MacDonald, Bruce; Wuensche, Burkhard (2008)

    Conference item
    The University of Auckland Library

    Augmented Reality (AR) can assist humans in understanding complex robot information, and improve Human and Robot Interaction (HRI). However, many restrictions are imposed by the underlying technology used and thus have lim- ited current AR systems to operate in con- trolled or modi ed robot environments. This hinders the wide spread use of AR for di er- ent robot applications. This paper presents a markerless AR system that combines recent tracking and detection techniques for AR vi- sualisation of robot task relevant information. We employ natural feature tracking techniques to compute the camera pose for accurate reg- istration of virtual objects. Automatic relocal- isation of the camera pose is achieved using a planar object detection algorithm which recov- ers from tracking failures. Experiments using a camera mounted on a mobile ground robot demonstrated accurate tracking and successful recovery of planar features in an unprepared indoor environment.

    View record details
  • Measuring and improving the accuracy of ARDev using a square grid

    Fung, Kathy; MacDonald, Bruce; Collett, Toby (2006)

    Conference item
    The University of Auckland Library

    Augmented reality (AR) systems superimpose 3D virtual objects on top of a real scene. Most applications require the AR system to maintain an accurate registration between the virtual objects and the real scene. Many AR systems use parameters obtained from the camera calibration to set up a virtual camera that models the real camera. Thus, inaccuracy in camera calibration can adversely affect the registration of an AR system. This paper proposes a calibration improvement algorithm which measures and improves accuracy of a robotics AR system that is currently used in our lab. The algorithm uses a square grid pattern as a calibration device. The vertices of the grid are defined as calibration points. The image coordinates of the calibration points are extracted using image processing technique. By comparing the difference between these image coordinates and those that are calculated using the camera parameters, the accuracy of the system can be measured. The registration error found can be used to adjust the camera parameters accordingly and thereby improves the accuracy of the system. Experiments have shown that the calibration improvement algorithm is feasible and it can be used to measure and minimise the registration error of the AR system.

    View record details
  • Real Time Simultaneous Localisation and Mapping for the Player Project

    Yang, Yung-Hsun; MacDonald, Bruce; Stol, Karl (2008)

    Conference item
    The University of Auckland Library

    This paper presents the development of a real time Simultaneous Localisation and Mapping (SLAM) application for generic robot plat- forms using Player, called the Real Time SLAM Proxy (RSP). The Extended Kalman Filter (EKF) and Multiple Particle Filter (MPF) SLAM algorithms are implemented in RSP, and experimental results are provided. RSP is in- tended for nonholonomic robots that operate in 2-D outdoor environments where landmarks can be modelled by cylindrical features and de- tected using laser range nders.

    View record details
  • Realtime Debugging for Robotics Software

    Gumbley, Luke; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    Conventional software debugging constructs are insu cient for debugging robotic software due primarily to the assumption of a deter- ministic, suspendable environment. What is needed is a method to extract and report infor- mation about robotic software execution while continuing execution in the real world environ- ment. A previously theorized debugging con- struct called a tracepoint has been implemented within both a C and a Python debugger. The NetBeans IDE was modi ed to provide an ex- tensible user interface. A plugin-based visu- alisation system for rendering trace data has also been implemented. Presently, plugins for the visualisation system have been created for rendering laser and ultrasonic range nder data from the Player robot library. Benchmark tests show that although there is still signi cant room for improvement, in one typical use case the system adds less than 1% overhead.

    View record details
  • Retirement home staff and residents' preferences for healthcare robots

    Broadbent, Elizabeth; Tamagawa, Rie; Kerse, Ngaire; Knock, Brett; Patience, Anna; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    As the proportion of people in the older age groups grows, demands on care providers increase. The ability of robotic technology to meet these demands is limited by a lack of acceptance by older people. This study investigates which tasks staff and residents in a retirement village would like a robot to assist with, as well as their attitudes towards robots and preferences for their appearance. Findings show that residents are more positive about robots than staff, and participants prefer a silver robot of 1.25 m height, with wheels and a screen on the body. Residents would most like the robot to assist with detecting falls, turning on and off appliances, lifting, cleaning, medication reminding, making phone calls and monitoring location. Making robots that fit these preferences may increase the acceptance of robotic assistants by older people.

    View record details
  • Robust trajectory segmentation for programming by demonstration

    Abbas, Tanveer; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    A novel trajectory segmentation and modeling approach is presented. Trajectory segmentation and matching is an important step in the programming by demonstration (PbD) process to extract the user's intentions from multiple trajectories. To match multiple trajectories, the segmentation and modeling approach must be consistent and robust to disparities caused by robot dynamics and human imperfections. Several curve segmentation approaches have demonstrated substantial potential in the field of image processing and gesture recognition. They emphasize reduction of the degree of mismatch between given and model curves. However they fail to reduce mismatch between models of multiple trajectories recorded to demonstrate the same intention.We propose an M-estimator for trajectory modeling and set up a new segmentation criterion to address the issue. The proposed approach is better suited for PbD of mobile robots. The approach is evaluated for real robot trajectories.

    View record details
  • Specifying robot reactivity in procedural languages

    Biggs, Geoffrey; MacDonald, Bruce (2006)

    Conference item
    The University of Auckland Library

    A key part of programming a robotic system is specifying the responses to events that the robot may encounter. Existing methods of programming responses include event loops, reactive languages and hybrid architectures, none of which meet the specific needs of mobile robot programming. This work presents a design for new semantics for specifying reactivity in mobile robot programs, one that allows for effective specification of reactive behaviour within procedural robot programs. An initial evaluation version is implemented in Python. Events and responses are supported as program objects, and are connected together by new statements. Programmers specify connections between events and responses anywhere within the program code, so connections can easily be changed in response to changes in program and robot state

    View record details
  • Towards a flexible platform for voice accent and expression selection on a Healthcare Robot

    Igic, Aleksandar; Watson, Catherine; Teutenberg, Jonathan; Tamagawa, Rie; MacDonald, Bruce; Broadbent, Elizabeth (2009)

    Conference item
    The University of Auckland Library

    In the application of robots in healthcare, where there is a requirement to communicate vocally with non-expert users, a capacity to generate intelligible and expressive speech is needed. The Festival Speech Synthesis System is used as a framework for speech generation on our healthcare robot. Expression is added to speech by modifying mean pitch and pitch range parameters of a statistical model distributed with Festival. US and UK English diphone voices are evaluated alongside a newly made New Zealand English accented diphone voice by human judges. Results show judges can discern different accents and correctly identify the nationality of the voice.

    View record details
  • Towards Expressive Speech Synthesis in English on a Robotic Platform

    Roehling, Sigrid; MacDonald, Bruce; Watson, Catherine (2006)

    Conference item
    The University of Auckland Library

    Affect in???uences speech, not only in the words we choose, but in the way we say them. This paper reviews the research on vocal correlates in the expression of affect and examines the ability of currently available major text-to-speech (TTS) systems to synthesize expressive speech for an emotional robot guide. Speech features discussed include pitch, duration, loudness, spectral structure, and voice quality. TTS systems are examined as to their ability to control the features needed for synthesizing expressive speech: pitch, duration, loudness, and voice quality. The OpenMARY system is recommended since it provides the highest amount of control over speech production as well as the ability to work with a sophisticated intonation model. OpenMARY is being actively developed, is supported on our current Linux platform, and provides timing information for talking heads such as our current robot face.

    View record details
  • On internal knowledge representation for programming mobile robots by demonstration

    Abbas, T; MacDonald, Bruce (2010)

    Conference item
    The University of Auckland Library

    Intuitive learning of new behaviours is one of the important aspects of social robotics. Among various robot learning approaches, recently Programming by Demonstration (PbD) has gained signi???cant recognition with a lot of potential. Internal representation of the knowledge is a key design choice in the learning process. Using machine learning techniques such as ANNs, HMMs and NARMAX models, simple skills can be encoded from raw sensory data. However, the abstract symbolic representations have demonstrated greater potential for learning complicated tasks but with less details and require a piece of prior knowledge as well. For a particular application, appropriate choice of the symbols is a key design issue. This paper discusses the choice of the symbols to build a PbD process for typical indoor navigation. The learning results are presented for a few tasks to demonstrate the potential of the proposed approach.

    View record details
  • A comparison between extended kalman filtering and sequential monte carlo technique for simultaneous localisation and map-building.

    Yuen, David; MacDonald, Bruce (2002)

    Conference item
    The University of Auckland Library

    Monte Carlo Localisation has been applied to solve many di erent classes of localisation problems. In this paper, we present a possible Simultaneous Localisation and Map-building implementation using the Sequential Monte Carlo technique. Multiple particle lters are created to estimate both the robot and land- mark positions simultaneously. The proposed technique shows promising results when com- pared with those obtained with the Extended Kalman lter.

    View record details
  • An Intuitive Interface for a Cognitive Programming By Demonstration System

    Brageul, David; Vukanovic, Slobodan; MacDonald, Bruce (2008)

    Conference item
    The University of Auckland Library

    A significant challenge in programming robots by demonstration is to accurately capture the user's intentions, so that sensor differences can be managed during playback. Sensor difference can be caused by: natural sensory data variations, minor variations in the task conditions, significant changes in the task scenario, or because the task requires a new set of actions to be executed. This paper presents a design for a programming by demonstration system that focuses on the important goal of capturing the intentions of the user during the demonstration. A gesture interface for a large touch screen is used during demonstration, to capture more clearly the user's intentions for robot movements, and also during a pre- playback session to capture the user's intentions regarding sensor data.

    View record details
  • Attitudes of retirement home residents, relatives and staff towards healthcare robots.

    Broadbent, Elizabeth; Tamagawa, Rie; Kerse, Ngaire; Day, Karen; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    View record details
  • Augmented Reality Visualisation for Player

    Collett, Toby; MacDonald, Bruce (2006)

    Conference item
    The University of Auckland Library

    One of the greatest challenges when debugging a robot application is understanding what is going wrong. Robots are embodied in a complex, changing and unpredictable real world, using sensors and actuators that are different from humans???. As a result humans may ???nd the development of robotic software to be dif???cult and time consuming. We present an augmented reality visualisation tool for the popular open source Player system, that enhances the developers understanding of the robots world view and thus improves the robot development process.

    View record details
  • Covariance Visualisations for Simultaneous Localisation and Mapping

    Kozlov, Alexei; MacDonald, Bruce; Wuensche, Burkhard (2009)

    Conference item
    The University of Auckland Library

    Simultaneous Localisation and Mapping (SLAM) is a method of environment mapping in mobile robotics. One of the most popular classes of this algorithm is the Extended- Kalman Filter (EKF) SLAM, which maps the environment by estimating similarities between currently registered scene objects and newly perceived ones. More advanced versions of this algorithm are necessary, e.g. for multiple robots or outdoor environments. However, development is di cult because of the complex interaction between the internal robot state, the perceived scene and the actual scene. New visualisation methods are hence required to enable developers to debug and evaluate EKF-SLAM algorithms. We present novel Augmented Reality based visualisation techniques which display the algorithm's progress by visualising feature and robot pose estimates, as well as correlations between fea- tures and clusters of features. The techniques allow a qualitative estimate of the algorithm's mapping compared with the ground truth and indicate the correctness and convergence properties of the SLAM system.

    View record details
  • Developer Oriented Visualisation of a Robot Program

    Collett, Toby; MacDonald, Bruce (2006)

    Conference item
    The University of Auckland Library

    Robot programmers are faced with the challenging problem of understanding the robot's view of its world, both when creating and when debugging robot software. As a result tools are created as needed in different laboratories for different robots and different applications. We discuss the requirements for effective interaction under these conditions, and propose an augmented reality approach to visualising robot input, output and state information, including geometric data such as laser range scans, temporal data such as the past robot path, conditional data such as possible future robot paths, and statistical data such as localisation distributions. The visualisation techniques must scale appropriately as robot data and complexity increases. Our current progress in developing a robot visualisation toolkit is presented.

    View record details
  • Distance indexed trajectory generation for a helicopter robot for programming by demonstration

    Abbas, Tanveer; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    A trajectory generator is presented. While the generator is generic we focus on its application for a programming by demonstration (PbD) system. Using stored task knowledge, our PbD system generates position targets at runtime to guide the robot to achieve specified task goals. This paper addresses the problem of trajectory generation (as a sequence of waypoints) to move from one position target to another. Most existing trajectory generation algorithms produce time indexed trajectories. The traversability of time indexed trajectories can be ensured only if an accurate dynamic model is considered for trajectory generation. However, if the true dynamics are not known, the robot may fail to follow the trajectory. A novel distance indexed trajectory generation method is presented to resolve these issues for a helicopter robot. The approach is evaluated using a helicopter simulator.

    View record details
  • Expressive Speech for a Virtual Talking Head

    Li, Xingyan; Watson, Catherine; Igic, Aleksandar; MacDonald, Bruce (2009)

    Conference item
    The University of Auckland Library

    This paper presents our work on building an expressive facial speech synthesis system Eface, which can be used on a social or service robot. Eface aims at enabling a robot to deliver infor- mation clearly with empathetic speech and an expressive virtual face. The system is built on two open source software packages: the Festival speech synthesis system, which provides robots the capability to speak with di erent voices and emotions, and Xface{a 3D talking head, which enables the robot to display various human fa- cial expressions. This paper addresses how to express di erent speech emotions with Festi- val and how to integrate the synthesized speech with Xface. We have also implemented Eface on a physical robot and tested it with some ser- vice scenarios.

    View record details