Publications


Online Indices: [ Google Scholar (H-Index: 10) ]     |     [ DBLP ]     |     [ UQ reSEARCHers ]     |     [ BibBase ]


Journal and Conference Papers (in Year of Publication):

QuickSearch:   Number of matching entries: 0.


Abstract: This paper presents a novel approach for constructing light-weight, low-cost sensor modules and miniature unmanned aerial vehicles which consist of printed circuit boards as integrated electronic, structural and aerodynamic lift-producing devices. In this way, each aircraft can be a single-piece, single-manufacturing step assembly, reducing materials, processing and labour costs. This approach allows the fabrication of devices that are sufficiently inexpensive so as to be economic for single-use or disposable applications, such as long-range sensor deployment for environmental monitoring. We present two example low-cost, proof-of-concept aircraft employing electro-aeromechanical structures --- rotary-wing and fixed-wing --- and demonstrate their flight performance.
BibTeX:
@inproceedings{eams.icra.2013,
  author = {P. E. I. Pounds and S. P. N. Singh},
  title = {Integrated Electro-Aeromechanical Structures for Low-Cost, Self-Deploying Environment Sensors and Disposable UAVs},
  booktitle = {International Conference on Robotics and Automation (ICRA)},
  year = {2013},
  pages = {4444-4451},
  note = {Accepted}
}
Review: va2
BibTeX:
@conference{singh2012iball,
  author = {Singh, S. and Pounds, P. and Kurniawati, H.},
  title = {I-Ball: A Programmable Sporting Aid for Children with a Visual Impairment to Play Soccer},
  booktitle = {HCI International Conference},
  year = {2013}
}
Abstract: This paper describes a model reduction strategy for obtaining a computationally efficient prediction of a fixed-wing UAV performing waypoint navigation under steady wind conditions. The strategy relies on the off-line generation of time parametrized trajectory libraries for a set of flight conditions and reduced order basis functions functions for determining intermediate locations. It is assumed that the UAV has independent bounded control over the airspeed and altitude, and consider a 2D slice of the operating environment. We found that the reduced-order model finds intermediate positions within 10% and at speeds of 10x faster than clock-time (even in wind conditions in excess of 50% of the UAV's forward airspeed) when compared against simulation results using a medium-fidelity flight dynamics model. The potential of this strategy for online planning operations is highlighted.
BibTeX:
@inproceedings{acra.windgustuav.2012,
  author = {A. Doshi and S. P. N. Singh and A. Postula},
  title = {An Online Feedback Motion Planning and Control Strategy for UAVs in Wind},
  booktitle = {Australian Conference on Robotics and Automation},
  year = {2012},
  url = {http://www.araa.asn.au/acra/acra2012/papers/pap147.pdf}
}
Abstract: This paper introduces a Cartesian impedance control framework in which reaction forces exceeding control authority directly reshape bucket motion during successive excavation passes. This novel approach to excavation results in an iterative process that does not require explicit prediction of terrain forces. This is in contrast to most excavation control approaches that are based on the generation, tracking and re-planning of single-pass tasks where the performance is limited by the accuracy of the prediction. In this view, a final trench profile is achieved iteratively, provided that the forces generated by the excavator are capable of removing some minimum amount of soil, maintaining convergence towards the goal. Field experiments show that a disturbance compensated controller is able to maintain convergence, and that a 2-DOF feedforward controller based on free motion inverse dynamics may not converge due to limited feedback gains.
BibTeX:
@inproceedings{fsr2012.excavator,
  author = {Guilherme J. Maeda and David C. Rye and Surya P. N. Singh},
  title = {Iterative Autonomous Excavation},
  booktitle = {Field and Service Robotics},
  year = {2012},
  url = {http://www.astro.mech.tohoku.ac.jp/FSR2011/}
}
Abstract: Disturbances that arise in material removal by repeated attempts to track the same path have the particular characteristics of non-repetitive magnitudes, but nearly-repetitive or gradual gradient transitions. This paper proposes and validates Iterative Learning Control (ILC) with a PD-type learning function for this class of disturbance as a predictive controller for autonomous excavation. However, parameters of the PD learning function may require different tunings for different excavation conditions, and convergence can be slow when compared to changes in excavation dynamics. In order to improve convergence, a plant inversion learning function is reinterpreted as a disturbance observer in the iteration domain, effectively rendering a disturbance learning controller (DLC). A hydraulic mini-excavator was used to evaluate experimentally the performance of the conventional ILC and the DLC against a robust controller. ILC achieved a desired cut profile with non-monotonic transients and DLC converged faster by learning disturbances directly from command discrepancies.
Review: http://db.acfr.usyd.edu.au/download.php/Maeda2012_IROS_LearningDisturbances.pdf?id=2571
BibTeX:
@inproceedings{gjm.iros2012.draft,
  author = {Guilherme J. Maeda and David C. Rye and Surya P. N. Singh},
  title = {Learning Disturbances in Autonomous Excavation},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  year = {2012},
  note = {Submitted},
  doi = {10.1109/IROS.2012.6385566}
}
Abstract: In this paper we develop an algorithmic framework allowing for fast and elegant path correction exploiting Lie group
symmetries and operating without the need for explicit control strategies such as cross-track regulation. These systems
occur across the gamut of robotics, notably in locomotion, be it ground, underwater, airborne, or surgical domains. Instead
of reintegrating an entire trajectory, the method selectively alters small key segments of an initial trajectory in a consistent
way so as to transform it via symmetry operations. The algorithm is formulated for arbitrary Lie groups and applied in
the context of the special Euclidean group and subgroups thereof. A sampling-based motion planner is developed that
uses this method to create paths for underactuated systems with differential constraints. It is also shown how the path
correction method acts as a controller within a feedback control loop for real-time path correction. These approaches are
demonstrated for ground vehicles in the plane and for flexible bevel tip needle steering in space. The results show that
using symmetry-based path correction for motion planning provides a prudent and simple, yet computationally tractable,
integrated planning and control strategy.
BibTeX:
@article{ijrr.fmc.2012,
  author = {Konstantin Seiler and Surya P. N. Singh and and Salah Sukkarieh and Hugh Durrant-Whyte},
  title = {Using Lie Group Symmetries of Fast Corrective Motion Planning},
  journal = {The International Journal of Robotics Research},
  year = {2012},
  volume = {31},
  number = {2},
  pages = {151-166},
  doi = {10.1177/0278364911429977}
}
Review: robotica.inpress
BibTeX:
@article{robotica.2012,
  author = {S. P. N. Singh and K. J. Waldron},
  title = {A Stance Period Approach for Simplified Observation of Galloping as Applied to Canines},
  month = {July},
  journal = {Robotica},
  year = {2012},
  volume = {30},
  number = {4},
  pages = {627-633},
  doi = {10.1017/S0263574711000488}
}
Abstract: Lizards are one of the few animal groups that readily switch between quadrupedal (4-legged) and bipedal (2-legged)
locomotion. Previous studies on bipedal locomotion in lizards suggest that bipedalism does not confer any locomotory
advantage for increasing speed or endurance but instead may have evolved as a simple consequence of acceleration
generating torque around the hip joint.
BibTeX:
@inproceedings{rss.lizard.2012,
  author = {Christofer J. Clemente and Surya P. N. Singh},
  title = {Obstacle Negotiation for High Speed Legged-Robots. Inspiration from Bipedal Lizards},
  booktitle = {Robotics: Science and Systems (RSS) Workshop on Bio-inspired Robotics},
  year = {2012},
  url = {https://wiki.cites.uiuc.edu/wiki/display/wkshplocomotion/Home}
}
Abstract: Distributed sensing offers a variety of benefits for environmental monitoring applications such as bushfire fighting. The cost and delay in distributing sensors over a large geographic area makes ad hoc aerial deployment via air-drop a compelling technology. However, the need to ruggardise sensors to survive free-fall impact, or the cost of including aerodynamic arrest devices such as parachutes for soft-landing, makes aerial deployment less viable. We present a method for constructing low-cost light-weight sensor modules that incorporate a mono-wing into the structure of the sensor PCB. This allows the sensors to autorotate to a soft-landing after release from the air, without additional processing or fabrication steps.
BibTeX:
@inproceedings{rss.samara.2012,
  author = {Samuel Valdes and Ignacio Urza and Paul E. I. Pounds and Surya P. N. Singh},
  title = {Samara: Low-cost Deployment for Environmental Sensing Using Passive Autorotation},
  booktitle = {Robotics: Science and Systems (RSS) Workshop on Bio-inspired Robotics},
  year = {2012},
  url = {https://wiki.cites.uiuc.edu/wiki/display/wkshplocomotion/Home}
}
Abstract: Model uncertainty complicates most kinodynamic motion planning and control approaches due to their reliance on accurate forward prediction. If the model uncertainty is significant, a generated path or control strategy based on forward simulation of this model is potentially invalid and expensive to track (if possible). This paper explores the use of system identification/estimation to tune model parameters. Framed as an extension to rapidly exploring random tree (RRT) methods, it updates the model so that reachable actions added to the tree have more fidelity. This can be viewed as a mixture of a model predictive control (MPC) for local planning with an approximate-model global planner providing sub-goals and thus overcoming the limited lookahead caused by model uncertainty. The benefits of this approach are illustrated for a 3 DOF serial manipulator controlled by computed torque control operating under large external disturbances. In this case, the approach provides operation under intermittent feedback and disturbance observation. Tracking and actuator utilization are also improved over solutions found via conventional methods.
BibTeX:
@conference{icra11.gjm,
  author = {Guilherme J. Maeda and Surya P. N. Singh and Hugh Durrant-Whyte},
  title = {A Tuned Approach to Feedback Motion Planning with RRTs under Model Uncertainty},
  booktitle = {International Conference on Robotics and Automation},
  year = {2011},
  pages = {2288-2294},
  doi = {10.1109/ICRA.2011.5979834}
}
Abstract: Observing human motion patterns is informative for social robots that share the environment with people. This paper presents a methodology to allow a robot to navigate in a complex environment by observing pedestrian positional traces. A continuous probabilistic function is determined using Gaussian process learning and used to infer the direction a robot should take in different parts of the environment. The approach learns and filters noise in the data producing a smooth underlying function that yields more natural movements. Our method combines prior conventional planning strategies with most probable trajectories followed by people in a principled statistical manner, and adapts itself online as more observations become available. The use of learning methods are automatic and require minimal tuning as compared to potential fields or spline function regression. This approach is demonstrated testing in cluttered office and open forum environments using laser and vision sensing modalities. It yields paths that are similar to the expected human behaviour without any a priori knowledge of the environment or explicit programming.
BibTeX:
@conference{icra11.simon,
  author = {S. T. O'Callaghan and S. P. N. Singh and A. Alempijevic and F. Ramos},
  title = {Learning Navigational Maps by Observing Human Motion Patterns},
  booktitle = {International Conference on Robotics and Automation},
  year = {2011},
  pages = {4333-4340},
  doi = {10.1109/ICRA.2011.5980478}
}
Abstract: Disturbances that arise in material removal by repeated attempts to track the same path have the particular characteristics of non-repetitive magnitudes, but nearlyrepetitive or gradual gradient transitions. This paper proposes and validates Iterative Learning Control (ILC) with a PD-type learning function for this class of disturbance as a predictive controller for autonomous excavation. However, parameters of the PD learning function may require different tunings for different excavation conditions, and convergence can be slow when compared to changes in excavation dynamics. In order to improve convergence, a plant inversion learning function is reinterpreted as a disturbance observer in the iteration domain, effectively rendering a disturbance learning controller (DLC). A hydraulic mini-excavator was used to evaluate experimentally the performance of the conventional ILC and the DLC against a robust controller. ILC achieved a desired cut profile with nonmonotonic transients and DLC converged faster by learning disturbances directly from command discrepancies.
Review: Disturbances that arise in material removal by repeated attempts to track the same path have the particular characteristics of non-repetitive magnitudes, but nearly-repetitive or gradual gradient transitions. This paper proposes and validates Iterative Learning Control (ILC) for this class of disturbance as a low-level control strategy in autonomous excavation. Parameters of the ILC learning rule may require different tunings for different excavation conditions, and convergence can be slow when compared to changes in excavation dynamics. An iterative Disturbance Learning Controller (DLC) based on inverse dynamics is presented as a solution to those problems. The DLC learning rule is independent of the excavation condition and the use of an inverse arm dynamics accelerates convergence. A hydraulic mini-excavator was used to evaluate experimentally the performance of the ILC and the DLC against a robust controller. ILC achieved a desired cut profile with non-monotonic transients and DLC converged faster by learning disturbances directly from command discrepancies.
BibTeX:
@inproceedings{maeda2011improving,
  author = {Maeda, G.J. and Singh, S.P.N. and Rye, D.C.},
  title = {Improving operational space control of heavy manipulators via open-loop compensation},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  year = {2011},
  pages = {725--731},
  doi = {10.1109/IROS.2011.6094437}
}
BibTeX:
@electronic{rss11.ipc,
  author = {S. P. N. Singh and R. Tedrake and P. Corke},
  title = {Integrated Planning and Control Workshop},
  year = {2011},
  note = {(also http://bit.ly/ipc2011)},
  url = {http://www.roboticsconference.org/workshops.html}
}
Abstract: This paper presents RobotAssist, a robotic platform designed for use in human robot interaction research and for entry into Robocup@Home competition. The core autonomy of the system is implemented as a component based software framework that allows for integration of operating system independent components, is designed to be expandable and integrates several layers of reasoning. The approaches taken to develop the core capabilities of the platform are described, namely: path planning in a social context, Simultaneous Localisation and Mapping (SLAM), human cue sensing and perception, manipulatable object detection and manipulation.
BibTeX:
@conference{acra2010.athome,
  author = {Nathan Kirchner and Alen Alempijevic and Sonja Caraian and Robert Fitch and Daniel Hordern and Gibson Hu and Gavin Paul and David Richards and Surya P. N. Singh and Stephen Webb},
  title = {RobotAssist - a Platform for Human Robot Interaction Research},
  booktitle = {Australian Conference on Robotics and Automation},
  year = {2010},
  url = {https://wiki.qut.edu.au/display/cyphy/Program+Timetable}
}
Abstract: Pan-tilt-zoom (PTZ) cameras complement many robotic applications. A coordinated camera steering method is presented to orient a set of commodity cameras to gaze at the same object or area of interest in the workspace. This method solves for a relevant camera model (intrinsics and extrinsics) and uses this to compute the geometry required for motion relative to a tracking signal.

This paper modifies auto-calibration of intrinsics and self-surveying methods of extrinsics for on-line gaze control operations over off-line reconstruction. To this feature tracking is added for feedback to compensate for servo imprecision and asynchrony. The performance of the approach is validated through a cooperative steering task on an array of PTZ cameras. Results show successful automatic steering and mean calibrations within 5% of estimates generated using reference calibration techniques.

BibTeX:
@conference{acra2010.camerasteering,
  author = {S. P. N. Singh and Kit Axelrod},
  title = {Coordinated Steering for an Uncalibrated Pan-Tilt-Zoom Camera Array},
  booktitle = {Australian Conference on Robotics and Automation},
  year = {2010},
  url = {https://wiki.qut.edu.au/display/cyphy/Program+Timetable}
}
Abstract: In this paper, the accuracy of non-linear finite element computations in application to surgical simulation was evaluated by comparing the experiment and modelling of indentation of the human brain phantom. The evaluation was realised by comparing forces acting on the indenter and the deformation of the brain phantom. The deformation of the brain phantom was measured by tracking 3D motions of X-ray opaque markers, placed within the brain phantom using a custom-built bi-plane X-ray image intensifier system. The model was implemented using the ABAQUS finite element solver. Realistic geometry obtained from magnetic resonance images and specific constitutive properties determined through compression tests were used in the model. The model accurately predicted the indentation force-displacement relations and marker displacements. Good agreement between modelling and experimental results verifies the reliability of the finite element modelling techniques used in this study and confirms the predictive power of these techniques in surgical simulation.
BibTeX:
@article{CMBE.2010.xraycalibration,
  author = {Jiajie Ma and Adam Wittek and Surya P. N. Singh and Grand Joldes and T. Washio and K. Chinzei and K. Miller},
  title = {Evaluation of accuracy of non-linear finite element computations for surgical simulation: study using brain phantom},
  month = {December},
  journal = {Computer Methods in Biomechanics and Biomedical Engineering},
  year = {2010},
  volume = {13},
  number = {6},
  pages = {783--794},
  url = {http://www.ingentaconnect.com/content/tandf/gcmb/2010/00000013/00000006/art00017},
  doi = {10.1080/10255841003628995}
}
Abstract: Operations with flexible, compliant manipulators over large workspaces relative to the manipulator are complicated by noise, vibration, and measurement bias. These difficulties are compounded in unstructured environments, such as those encountered in humanitarian demining. By taking advantage of the static structure of the terrain and the manipulatorӳ fundamental mechanical characteristics, a series of adaptive corrections and filters refine noisy topographical measurements. These filters along with a shaped actuation scheme can generate smooth and well-controlled trajectories that allow for terrain surface following. Experimental testing was performed on a field robot with a compliant, 3 m long hybrid manipulator and a stereo vision system. The proposed method provides a vertical tracking precision of ѵ mm on a variety of ground clearings, with tip scanning speeds of up to 0.5 m/s. As such, it can agilely move the attached sensor(s) through precise scanning trajectories that are very close to the ground. This method improves overall detection and generation of precise maps of suspected mine locations.
BibTeX:
@inproceedings{demining.fsr,
  author = {M. Freese and S. P. N. Singh and W. Singhose and E. Fukushima and S. Hirose},
  title = {Terrain Modeling and Following Using a Compliant Manipulator for Humanitarian Demining Applications},
  booktitle = {Field and Service Robotics},
  publisher = {Springer},
  year = {2010},
  series = {Springer Tracts in Advanced Robotics},
  volume = {62},
  pages = {3-12},
  url = {http://dx.doi.org/10.1007/978-3-642-13408-1_1},
  doi = {10.1007/978-3-642-13408-1_1}
}
Abstract: This paper presents an algorithm for segmenting 3D point clouds. It extends terrain elevation models by incorporating two types of representations: (1) ground representations based on averaging the height in the point cloud, (2) object models based on a voxelisation of the point cloud. The approach is deployed on Riegl data (dense 3D laser data) acquired in a campus type of environment and compared against six other terrain models. Amongst elevation models, it is shown to provide the best fit to the data as well as being unique in the sense that it jointly performs ground extraction, overhang representation and 3D segmentation. We experimentally demonstrate that the resulting model is also applicable to path planning.
BibTeX:
@conference{IROS2010.Douillard,
  author = {B. Douillard and J. Underwood and N. Melkumyan and S. Singh and S. Vasudevan and C. Brunner},
  title = {{Hybrid Elevation Maps}: {3D} Surface Models for Segmentation},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  year = {2010},
  doi = {10.1109/IROS.2010.5650541}
}
Abstract: This paper presents algorithms for fast segmentation of 3D point clouds and subsequent classification of the obtained 3D segments. The method jointly determines the ground surface and segments individual objects in 3D, including overhanging structures. When compared to six other terrain modelling techniques, this approach has minimal error between the sensed data and the representation; and is fast (processing a Velodyne scan in approximately 2 seconds). Applications include improved alignment of successive scans by enabling operations in sections (Velodyne scans are aligned 7% sharper compared to an approach using raw points) and more informed decision-making (paths move around overhangs). The use of segmentation to aid classification through 3D features, such as the Spin Image or the Spherical Harmonic Descriptor, is discussed and experimentally compared. Moreover, the segmentation facilitates a novel approach to 3D classification that bypasses feature extraction and directly compares 3D shapes via the ICP algorithm. This technique is shown to achieve accuracy on par with the best feature based classifier (92.1%) while being significantly faster and allowing a clearer understanding of the classifier's behaviour.
BibTeX:
@incollection{iser.2010.3dclassification,
  author = {B. Douillard and J. Underwood and V. Vlaskine and A. Quadros and S. P. N. Singh},
  title = {A Pipeline for the Segmentation and Classification of {3D} Point Clouds},
  booktitle = {Experimental Robotics: The 12th International Symposium on Experimental Robotics},
  publisher = {Springer},
  year = {2010},
  url = {http://iser2010.grasp.upenn.edu/sites/iser2010/files/papers/ISER2010_0055_1987d92478e380a648d2ffe1090dc390.pdf}
}
Abstract: A new control strategy based on feedback motion planning is presented for solving nonlinear control problems in constrained environments. The algorithm explores the state-space using a bi-directional rapidly exploring random tree (biRRT) in order to find a feasible trajectory between an initial and goal state. By incrementally scheduling LQR controllers, it attempts to connect states so as to link the two trees. These attempts are evaluated by verifying that the connected state is inside the controllable area of an infinite time horizon controller at the goal. This allows for a rapid delineation of equivalent neighborhoods in the state-space. As a result, random exploration is terminated as soon as a feasible solution is made possible by feedback means, avoiding oversampling and partially introducing optimal actions at the neighborhood of the connection. The algorithm is demonstrated and compared against a biRRT using single-link pendulum and cart-pole swing-up tasks amongst obstacles, the latter showing a nearly order of magnitude more efficient search.
BibTeX:
@conference{Maeda2010,
  author = {Guilherme J. Maeda and Surya P. N. Singh and Hugh Durrant-Whyte},
  title = {Feedback Motion Planning Approach for Nonlinear Control using Gain Scheduled RRTs},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  year = {2010},
  pages = {119--126},
  doi = {10.1109/IROS.2010.5650634}
}
Abstract: From exploring planets to cleaning homes, the reach and versatility of robotics is vast. The integration of actuation, sensing and control makes robotics systems powerful, but complicates their simulation. This paper introduces a modular and decentralized architecture for robotics simulation. In contrast to centralized approaches, this balances functionality, provides more diversity, and simplifies connectivity between (independent) calculation modules. As the Virtual Robot Experimentation Platform (V-REP) demonstrates, this gives a small-footprint 3D robot simulator that concurrently simulates control, actuation, sensing and monitoring. Its distributed and modular approach are ideal for complex scenarios in which a diversity of sensors and actuators operate asynchronously with various rates and characteristics. This allows for versatile prototyping applications including systems verification, safety/remote monitoring, rapid algorithm development, and factory automation simulation.
BibTeX:
@conference{simpar.2010.vrep,
  author = {Marc Freese and Surya P. N. Singh and Fumio Ozaki and Nobuto Matsuhira},
  title = {Virtual Robot Experimentation Platform {V-REP}: A Versatile {3D} Robot Simulator},
  booktitle = {{SIMPAR} 2010},
  year = {2010},
  series = {Lecture Notes in Computer Science},
  url = {http://www.sim.informatik.tu-darmstadt.de/simpar2010/index.php/program/schedule.html}
}
Abstract: Trajectory generation and control of large equipment in open field environments involves systematically and robustly operating in uncertain and dynamic terrain. This paper presents an integrated motion planning and control system for tracked vehicles. Flexible path-end adjustments and adaptive look-ahead are introduced to a state lattice planning approach with waypoint control. For a given processing horizon, this increases search coverage and reduces planning error. This tramming approach has been successfully fielded on a 98-ton autonomous blast hole drill rig used in iron ore mining in Western Australia. The system has undergone extensive testing and is now integrated into a production environment. This work is a key element in a larger program aimed at developing a fully autonomous, remotely operated mine.
BibTeX:
@inproceedings{spns.icra2010.ipc,
  author = {X. Fan and S. P. N. Singh and F. Oppolzer and E. Nettleton and R. Hennessy and A. Lowe and H. Durrant-Whyte},
  title = {Integrated Planning and Control of Large Tracked Vehicles in Open Terrain},
  booktitle = {International Conference on Robotics and Automation},
  month = {May},
  year = {2010},
  pages = {4424 -4430},
  doi = {10.1109/ROBOT.2010.5509392}
}
Abstract: Robotics is a rapidly-progressing and applied subject. This paper advocates for a research-driven model for modern robotics course design that, based on a principled approach, prepares students to consider and adopt recent results in their mechatronics applications. This view pro-vides a rubric for defining a sufficient set of top-ics that give a broad overview of robotic tech-nologies and provides a foundation for later (undergraduate) research experience. To address the inherently multidisciplinary nature of robot-ics, a modular co-teaching model is adopted in which separate sections are taught by different lecturers, who potentially span various academic departments. Evidence supporting this approach is illustrated from case studies of student pro-jects in The University of Sydneyӳ Experimen-tal Robotics course, MTRX 4700. By providing an engaging topic, a research approach, exten-sive mentorship, and an open-ended problem, the course not only meets learning objectives, but also promotes a research foundation sup-porting later undergraduate research opportuni-ties.
BibTeX:
@article{spns.mtrx4700,
  author = {S. P. N. Singh and R. Fitch and S. Williams},
  title = {A Research-Driven Approach to Undergraduate Robotics Education},
  journal = {Computers in Education Journal},
  year = {2010},
  volume = {1},
  number = {4},
  pages = {21--27}
}
Abstract: For a mechanical system it often arises that its planned motion will need to be corrected either to refine an approximate plan or to deal with disturbances. This paper develops an algorithmic framework allowing for fast and elegant path correction for nonholonomic underactuated systems with Lie group symmetries, which operates without the explicit need for control strategies. These systems occur frequently in robotics, particularly in locomotion, be it ground, underwater, airborne, or surgical needle steering. Instead of re-integrating an entire trajectory, the method alters small segments of an initial trajectory in a consistent way so as to transform it via symmetry operations. This approach is demonstrated for the cases of a kinematic car and for flexible bevel tip needle steering, showing a prudent and simple, yet computationally tractable, trajectory correction.
BibTeX:
@incollection{wafr2010.pathcorrection,
  author = {Konstantin Seiler and Surya P. N. Singh and Hugh Durrant-Whyte},
  title = {Using Lie Group Symmetries for Fast Corrective Motion Planning},
  booktitle = {Algorithmic Foundations of Robotics {IX}},
  publisher = {Springer},
  year = {2010},
  series = {Springer Tracts in Advanced Robotics},
  volume = {68},
  pages = {37-52},
  url = {http://bigbird.comp.nus.edu.sg/pmwiki/farm/wafr/uploads/Main/wafr2010_submission_30.pdf},
  doi = {10.1007/978-3-642-17452-0_3}
}
Abstract: The gallop is the preferred gait by mammals for agile traversal through terrain. This motion is intrinsically complex as the feet are used individually and asymmetrically. Experimental data for the gallop are limited due the large workspace needed because of the gait's speed and long traversal. A generalized motion measurement strategy is adopted based on high-speed, motion capture with a reduced marker set and an emphasis on body and leg kinematics and with limited ground reaction force measurement. This allows for an extension of the workspace and allows for markers to be placed in locations with reduced tissue compliance. This is sufficient for capturing the principal motion and for making kinematic comparisons to a previously developed approximating impulse model framework. A series of gallops were measured in a large gait laboratory (18 m2 principal working area) from three canine subjects (ranging from 8 to 24 kg) galloping down a 15 m runway. Normalized results show a correlation with motions suggested by the impulse model and are in keeping with insights from previous animal and legged robot studies.
BibTeX:
@conference{clawar.2009.dogmotion,
  author = {S. P. N. Singh and K. J. Waldron},
  title = {Generalized Dog Motion Measurements to Support a Simple Model of Rotary Galloping Locomotion},
  booktitle = {Mobile Robotics: Solutions and Challenges},
  year = {2009},
  pages = {741-748},
  url = {http://www.worldscientific.com/doi/abs/10.1142/9789814291279_0091},
  doi = {10.1142/9789814291279_0091}
}
BibTeX:
@unpublished{rtcma.fsrdraft,
  author = {X. Fan and S. P. N. Singh},
  title = {System Design for Autonomous Vehicle Tramming in Open-Pit Mining},
  month = {February},
  year = {2009},
  note = {RTCMA Internal Document}
}
BibTeX:
@techreport{rtcma.mcs.jan,
  author = {Singh, S. P. N.},
  title = {Mine Control System: Control Architecture Overview},
  month = {January},
  year = {2009},
  number = {CMA0004.100}
}
BibTeX:
@techreport{rtcma.xic.july,
  author = {Singh, S. P. N.},
  title = {Mine Control System: Local Controller Design Report},
  month = {July},
  year = {2009},
  number = {CMA0004.101}
}
Abstract: This paper focuses on modeling the gait characteristics of a quadrupedal gallop. There have been a number of studies of the mechanics of the stance phase in which a foot is in contact with the ground. We seek to put these studies in the context of the stride, or overall motion cycle. The model used is theoretical, and is kept simple in the interest of transparency. It is compared to empirical data from observations of animals, and to data from experiments with robots such as our KOLT machine, and results from sophisticated simulation studies. Modeling of the energy loss inherent in the interaction between the system and the environment plays a key role in the study. Results include the discovery of a hidden symmetry in the gait pattern, usually regarded as being completely asymmetrical. Another result demonstrates that the velocities with which the two front feet impact and leave the ground are different, and similarly for the rear feet. The velocities of the foot pairs mirror each other. This is consistent with empirical observation, but is at variance with the assumption used almost universally when modeling stance. A further result elicits the importance of the pitch moment of inertia and other effects that make the mammalian architecture, in which the center of mass is closer to the shoulders than to the hips, beneficial.
BibTeX:
@article{spns.jmr.09,
  author = {K. J. Waldron and J. Estremera and P. Csonka and S. P. N. Singh},
  title = {Analyzing Bounding and Galloping Using Simple Models},
  month = {February},
  journal = {Journal of Mechanisms and Robotics},
  year = {2009},
  volume = {1},
  number = {011002},
  pages = {1-11},
  doi = {10.1115/1.2959095}
}
BibTeX:
@unpublished{tmp.mp.url,
  author = {S. P. N. Singh},
  title = {Motion Planning Terminology List},
  year = {2009},
  note = {http://www-personal.acfr.usyd.edu.au/spns/motion/TerminologyList.pdf}
}
BibTeX:
@techreport{rtcma.arch.rpt,
  author = {A. H. G\"{o}kto\u{g}an and E. Nettleton and R. Hennessy and D. C. Bandara and S. P. N. Singh and H. Durrant-Whyte},
  title = {Mine System Architecture},
  month = {July},
  year = {2008},
  number = {Document CMA0001.100}
}
BibTeX:
@techreport{rtcma.rpt.req,
  author = {S. P. N. Singh},
  title = {Travel Summary Memo: West Angelas and Tom Price Mine Needfinding / Assessment Visit},
  month = {September},
  year = {2008}
}
BibTeX:
@conference{spns.biorob.2008,
  author = {S. P. N. Singh},
  title = {Comparison of Field Quadruped Motion Tracking},
  booktitle = {Biorobotics 2008 Workshop at the International Conference on Robotics and Automation},
  year = {2008}
}
Abstract: Effcient motion estimation is central to observing and controlling dynamic legged locomotion. This paper considers a screw-theoretic (line-oriented) representation for this context and illustrates this on the attitude estimation subproblem. This is presented as part of an Extended Kalman Filter (EKF) based on inertial (gyroscopic) sensing in which each measurement axis is treated as an zero pitch, instantaneous screw axis. The implemented solution integrates this to tracks both the orientation and the body screw-axis. In comparison to point-oriented (quaternion) representations, this method is more general, computationally efficient, and provides a more intuitive mechanism for specifying motion constraints, especially for rotary joint motion(s) such as those that at the foot. This technique is demonstrated on a trotting quadrupedal robot at a 250 Hz rate and with drift errors limited to a 5deg bound.
BibTeX:
@conference{spns.romansy.sekf,
  author = {S. P. N. Singh and S. Trujillo and K. J. Waldron},
  title = {A Screw Representation for Aiding State Estimation with Application to Dynamic Quadrupedal Locomotion},
  booktitle = {Proceedings of {ROMANSY} 17: Robot Design, Dynamics, and Control},
  year = {2008}
}
BibTeX:
@inproceedings{icra.2007,
  author = {Singh, S. P. N. and Waldron, K. J.},
  title = {{A Hybrid Motion Model for Aiding State Estimation in Dynamic Quadrupedal Locomotion}},
  booktitle = {International Conference on Robotics and Automation},
  year = {2007},
  pages = {4337-4342},
  doi = {10.1109/ROBOT.2007.364147}
}
BibTeX:
@conference{icra.dem.2007,
  author = {Singh, S. P. N. and M. Freese and J. Trevelyan},
  title = {{Contributions on a Design Direction for Future Humanitarian Demining Robots}},
  booktitle = {Proceedings of the {ICRA 2007} Workshop on Robotics in Challenging and Hazardous Environments},
  month = {April},
  year = {2007}
}
Abstract: A Self-Surveying Camera Array (SSCA) is a vision based local-area positioning system consisting of multiple ground-deployed cameras that are capable of self-surveying their extrinsic parameters while tracking and localizing a moving target. This paper presents the array self-surveying algorithm that involves tracking a target helicopter in each camera frame and localizing the helicopter in an array-fixed frame. Three cameras are deployed independently in an arbitrary arrangement that allows each camera to view the helicopter's flight volume. The helicopter then flies an unplanned path that allows the camera array to calibrate their relative locations and orientations by utilizing self-surveying algorithms extended from the well known structure from motion algorithm and the bundle adjustment technique. This yields the cameras' extrinsic parameters enabling real-time helicopter positioning via triangulation relative to the calibrated camera array. This paper also presents results from field trials, which verify the feasibility of the SSCA as a readily deployable system applicable to helicopter tracking and localization. The results demonstrate that, as compared to differential GPS solution as true reference, the SSCA is capable of positioning the helicopter with meter-level accuracy. The SSCA has been integrated with onboard inertia sensors providing a reliable positioning system to enable successful autonomous hovering.
BibTeX:
@article{ijrr.heli,
  author = {M. Matsuoka and A. Chen and S. P. N. Singh and A. Coates and A. Y. Ng and S. Thrun},
  title = {Autonomous Helicopter Tracking and Localization Using a Self-Surveying Camera Array},
  month = {February},
  journal = {The International Journal of Robotics Research},
  year = {2007},
  volume = {26},
  number = {2},
  pages = {205-215},
  doi = {10.1177/0278364906074898}
}
BibTeX:
@conference{kw.clawar07,
  author = {K. J. Waldron and J. Estremera and P. J. Csonka and S. P. N. Singh},
  title = {Thinking About Bounding and Galloping Using Simple Models},
  booktitle = {Advances and Techniques in Climbing and Walking Robots ({CLAWAR 2007})},
  year = {2007},
  note = {Chapter 22}
}
Abstract: An important tool in clarifying various theories governing the dynamics of rapid quadrupedal gaits, such as the trot and gallop, is the measurement of body attitude. Such measurements are complicated in open field environments because of the large ranges and high data rates needed due to the speeds (7 m/s) and rapid shifts in dynamics present. To address this a lightweight inertial sensing harness is introduced with sensing design based on the KOLT robot. Its mass center is collocated with the subject so as to reduce dynamic bias. This work combines dynamic gait system identification and motion estimation and is demonstrated on a Labrador retriever (Canis lupus familiaris) through measurements of the gallop over long spans (20 m) and at data rates comparable with gait laboratories (400 Hz). The results are consistent with laboratory measurements, but seem to suggest a roll and yaw cross-coupling during gallop.
BibTeX:
@conference{spns.iros07,
  author = {S. P. N. Singh and P. J. Csonka and K. J. Waldron},
  title = {{Robotic Harness for the Field Assessment of Galloping Gaits}},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  month = {Oct},
  year = {2007},
  pages = {4247-4252},
  doi = {10.1109/IROS.2007.4399637}
}
BibTeX:
@article{hd.ambi,
  author = {S. P. N. Singh},
  title = {{Functional Dissection: Beware of Landmines}},
  journal = {Ambidextrous Magazine},
  year = {2006},
  volume = {4},
  pages = {24-25},
  url = {http://ambidextrousmag.org/issues/04/}
}
Abstract: Manipulator operations are complicated by sensor noise, mechanical compliance, and system bias. These uncertainties are compounded in field environments, such as those encountered in humanitarian demining. By taking advantage of the generally flat and static structure of the terrain, a series of adaptive corrections and filters refine a sensed topographical model and generate a trajectory that is robust to inherent inaccuracies and modeling errors. Experimental testing on a mobile robot using stereo-vision as modeling sensor indicates that this method provides a tracking precision of ѵ mm on relatively flat ground. As such, it will keep the attached mine sensors close to the ground, improving effectiveness.
BibTeX:
@conference{icra.2006,
  author = {M. Freese and S. P. N. Singh and E. Fukushima and S. Hirose},
  title = {{Bias-Tolerant Terrain Following Method for a Field Deployed Manipulator}},
  booktitle = {International Conference on Robotics and Automation},
  month = {May},
  year = {2006},
  pages = {175-180},
  url = {http://ieeexplore.ieee.org/iel5/10932/34383/01641180.pdf?tp=&arnumber=1641180&isnumber=34383}
}
Abstract: Legged robots display a characteristically periodic motion. Measuring and tracking this motion has traditionally been performed using general inertial measurement techniques. While widely applied in robotics, this approach is limited in dynamic legged locomotion due to the excessive accumulation of drift from severe impact shocks (nearly 9 g in single leg experiments). This paper introduces the attitude estimation problem for legged locomotion and shows preliminary results from a more powerful combined range and inertial sensing approach. Based on a modified Extended Kalman Filter the method uses ground-directed range sensors, the stride period, and other periodic features of legged locomotion in order to address inertial drift. Together this provides rapid, robust estimates of flight phases and attitude necessary for extended dynamic legged operations.
BibTeX:
@inproceedings{iser04,
  author = {Singh, S. P. N. and Waldron, K. J.},
  title = {Towards High-Fidelity on Board Attitude Estimation for Legged Locomotion via a Hybrid Range and Inertial Approach},
  booktitle = {{Experimental Robotics {IX}}},
  year = {2006},
  series = {{Springer Tracts in Advanced Robotics}},
  volume = {21},
  pages = {589-598},
  doi = {10.1007/11552246_56}
}
Abstract: Dynamic legged locomotion entails navigating terrain at high speed. The impact shocks from rapid footfalls, pivotal for such mobility, introduce large impulses that saturate motion measurement. A biomimetic approach is presented in which visual information, in the form of optical flow, complements information from inertial sensors. The motion is then determined using a two-phase hybrid extended Kalman filter. Experimentation in determining attitudes on a robotic leg platform shows a reduction in drift over inertial approaches and in delay over visual approaches. In tests with 6g impulses, pose was recovered within 5 deg rms with angular rate errors limited to 10 deg/sec at frequencies up to 250 Hz.
BibTeX:
@inproceedings{spns.iros06,
  author = {S. P. N. Singh and P. J. Csonka and K. J. Waldron},
  title = {{Optical Flow Aided Motion Estimation for Legged Locomotion}},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  month = {Oct},
  year = {2006},
  pages = {1738--1743},
  doi = {10.1109/IROS.2006.282134}
}
BibTeX:
@phdthesis{thesis.spns,
  author = {S. P. N. Singh},
  title = {{Self-contained Measurement of Dynamic Legged Locomotion: Design for Robot and Field Environments}},
  school = {Stanford University},
  year = {2006},
  url = {http://www-personal.acfr.usyd.edu.au/spns/thesis.html}
}
Abstract: This paper describes an algorithm that tracks and localizes a helicopter using a ground-based trinocular camera array. The three cameras are placed independently in an arbitrary arrangement that allows each camera to view the helicopterӳ flight volume. The helicopter then flies an unplanned path that allows the cameras to self-survey utilizing an algorithm based on structure from motion and bundle adjustment. This yields the cameraӳ extrinsic parameters allowing for real-time positioning of the helicopterӳ position in a camera array based coordinate frame. In fielded experiments, there is less than a 2m RMS tracking error and the update rate of 20Hz is comparable to DGPS update rates. This system has successfully been integrated with an IMU to provide a positioning system for autonomous
BibTeX:
@inproceedings{3cam.fsr,
  author = {M. Matsuoka and A. Chen and S. P. N. Singh},
  title = {{Autonomous Helicopter Tracking and Localization Using a Self-Calibrating Camera Array}},
  booktitle = {Proceedings of the International Conference on Field and Service Robotics ({FSR} 2005)},
  month = {July},
  year = {2005},
  pages = {19-30},
  doi = {10.1007/11736592_3}
}
Abstract: Legged robots offer exceptional mobility in uncharted terrains. Their dynamic nature yields unrivaled mobility, but serves to destabilize the motion estimation process that underlies legged operations. In particular, the discontinuous foot fall patterns and flight phases result in severe impulses, which, in turn, result in excessive accumulation of drift by inertial sensors. Ground range measurements, amongst several others, are robust to this drift yet are limited in application due to their low-bandwidth and sensitivity to ground conditions. In considering the attitude estimation problem for this dynamic legged locomotion, this paper develops a pose calculation method based on ground range measurements. This is used in conjunction with a hybrid Extended Kalman Filter that takes advantage of the ballistic nature of the flight phases. Results indicate that this combination provides rapid, robust estimates of attitude necessary for extended dynamic legged operations. In single leg experiments, which were conducted using low-cost sensing hardware, this method had an RMS error of < 1 Ь half that of a non-hybrid EKF approach.
BibTeX:
@inproceedings{icra05,
  author = {S. P. N. Singh and K. J. Waldron},
  title = {Attitude Estimation for Dynamic Legged Locomotion Using Range and Inertial Sensors},
  booktitle = {International Conference on Robotics and Automation},
  month = {April},
  year = {2005},
  pages = {1675-1680},
  doi = {10.1109/ROBOT.2005.1570352}
}
BibTeX:
@manual{slasr,
  author = {P. J. Csonka and S. P. N. Singh},
  title = {An Overview of the Stanford SLASR Sensor},
  year = {2005},
  url = {http://www-locolab.stanford.edu/Publications/SLASR_Overview.pdf}
}
BibTeX:
@inproceedings{icra04,
  author = {S. P. N. Singh and K. J. Waldron},
  title = {Design and Evaluation of an Integrated Planar Localization Method for Desktop Robotics},
  booktitle = {International Conference on Robotics and Automation},
  month = {April},
  year = {2004},
  volume = {2},
  pages = {1109-1114},
  doi = {10.1109/ROBOT.2004.1307973}
}
Abstract: In this paper we present the system design of a machine that we have constructed to study a quadrupedal gallop gait. The gallop gait is the preferred high-speed gait of most cursorial quadrupeds. To gallop, an animal must generate ballistic trajectories with characteristic strong impacts, coordinate leg movements with asymmetric footfall phasing, and effectively use compliant members, all the while maintaining dynamic stability. In this paper we seek to further understand the primary biological features necessary for galloping by building and testing a robotic quadruped similar in size to a large goat or antelope. These features include high-speed actuation, energy storage, on-line learning control, and high-performance attitude sensing. Because body dynamics are primarily influenced by the impulses delivered by the legs, the successful design and control of single leg energetics is a major focus of this work. The leg stores energy during flight by adding tension to a spring acting across an articulated knee. During stance, the spring energy is quickly released using a novel capstan design. As a precursor to quadruped control, two intelligent strategies have been developed for verification on a one-legged system. The Levenberg-Marquardt on-line learning method is applied to a simple heuristic controller and provides good control over height and forward velocity. Direct adaptive fuzzy control, which requires no system modeling but is more computationally expensive, exhibits better response. Using these techniques we have been successful in operating one leg at speeds necessary for a dynamic gallop of a machine of this scale. Another necessary component of quadruped locomotion is high-resolution and high-bandwidth attitude sensing. The large ground impact accelerations, which cause problems for any single traditional sensor, are overcome through the use of an inertial sensing approach using updates from optical sensors and vehicle kinematics.
BibTeX:
@article{ijrr,
  author = {J. G. Nichol and S. P. N. Singh and K. J. Waldron and L. R. Palmer and D. E. Orin},
  title = {System Design of a Quadrupedal Galloping Machine},
  journal = {The International Journal of Robotics Research},
  year = {2004},
  volume = {23},
  number = {10-11},
  pages = {1013-1027},
  url = {http://ijr.sagepub.com/cgi/content/abstract/23/10-11/1013},
  doi = {10.1177/0278364904047391}
}
Abstract: A new concept for coordinating large-scale autonomous robot exploration teams having populations in the thousands is introduced along with several illustrative scenarios. Inspired by constructs found within the human immune system, the Immunology-derived Distributed Autonomous Robotics Architecture (IDARA) was developed so that exploratory actions are refined and followed by specific and mediated responses. The foundations of the IDARA model are derived from the immune network model; in particular, interactions derived from the innate immune system are integrated to yield a stronger first-order, all-purpose search strategy. Using this architecture as a foundation, the work develops methods for kilorobotic exploration in dynamic environments. As characterized via computer simulations with robot populations of up to 1,500 robots, IDARA-based exploration proved to be a robust and compact method for largescale multirobot coordination that combines reflexive and deliberative control methods in an opportunistic fashion, mimicking the human immune system
BibTeX:
@conference{cec02,
  author = {Singh, S.P.N. and Thayer, S.M. and Thayer, W.P.},
  title = {A Foundation for Kilorobotic Exploration},
  booktitle = {Proceedings of the 2002 Congress on Evolutionary Computation ({CEC 2002})},
  year = {2002},
  volume = {2},
  pages = {1033-1038},
  doi = {10.1109/CEC.2002.1004385}
}
Abstract: This paper presents a new concept and simulated results for the distributed
coordination of autonomous robot teams via the Immunology-derived Distributed
Autonomous Robotics Architecture (IDARA) to perform select search
and rescue (SAR) operations autonomously. Primarily designed for the coordination
and control of ԫilorobotԠcolonies, this architecture incorporates the immune
systemӳ stochastic learning and reaction mechanisms to yield astute and adaptive
responses to dynamic environmental conditions. This allows the architecture to
vary actions from reactive to deliberative to result in a guided, yet stochastic,
method that is ideal for dynamic operations such as terrain searching. IDARA
was evaluated in a variety of SAR problem domains via computer simulations.
These tests show that the IDARA framework is robust to noise and does not degrade
when coordinating large colonies of robots consisting of up to 1,500 robots.
By providing new levels of scalability in noisy environments, IDARA enables the
full potential of micro-scale robotic for intelligent exploration, mapping, and SAR
operations in a manner not afforded by traditional methods.
BibTeX:
@inproceedings{dars2002,
  author = {S. P. N. Singh and S. Thayer},
  title = {{Kilorobot Search and Rescue Using an Immunologically Inspired Approach}},
  booktitle = {{Distributed Autonomous Robotic Systems ({DARS})}},
  year = {2002},
  volume = {5},
  pages = {300-305}
}
Abstract: This paper presents a new concept called the Immunology-derived Distributed Autonomous Robotics Architecture (IDARA) for the manipulation of "kilorobots" (large multi-robot colonies) modeled on the actions of the human immune system. The paper presents the development of the IDARA algorithms for the control and coordination of kilorobots for robot exploration tasks in four mapping scenarios. As characterized via computer simulations with robot populations of up to 1,500, IDARA-based exploration proved to be an efficient, robust, and compact method for large-scale multirobot control that combines the speed of reflexive methods with the precision of deliberative control.
BibTeX:
@inproceedings{iros2002,
  author = {Thayer, S.M. and Singh, S.P.N.},
  title = {{Development of an Immunology-Based Multi-Robot Coordination Algorithm for Exploration and Mapping Domains}},
  booktitle = {Proceedings of the International Conference on Intelligent Robots and Systems ({IROS})},
  year = {2002},
  volume = {3},
  pages = {2735-2739},
  doi = {10.1109/IRDS.2002.1041683}
}
Abstract: Using an instrumented surgical tool, high-precision recordings of hand tremor were taken during vitreoretinal microsurgery. The data obtained using a compact, custom six-degree-of-freedom inertial sensing module were filtered and analyzed to characterize the physiological hand tremor of the surgeon. Tremor during the most delicate part of the procedure was measured at a vector magnitude of 38 &mu;m rms. Nontremulous, lower-frequency components of instrument movement were also characterized. The data collected provide an important baseline for design specification and performance evaluation of engineered microsurgical devices
BibTeX:
@inproceedings{tremor.2002,
  author = {S. P. N. Singh and C. N. Riviere},
  title = {{Physiological Tremor Amplitude During Vitreoretinal Microsurgery}},
  booktitle = {{Proceedings of the 28th Annual Northeast Bioengineering Conference}},
  year = {2002},
  pages = {171-172},
  doi = {10.1109/NEBC.2002.999520}
}
BibTeX:
@article{coursera.calib.peer,
  author = {Ralph Robinson},
  title = {Calibrated Peer Review},
  journal = {The American Biology Teacher},
  year = {2001},
  volume = {63},
  number = {7},
  pages = {474-480}
}
Review: Platypus
BibTeX:
@article{Lin_Liu_Yuan_2001,
  author = {Lin, S.S.J. and Liu, E.Z.F. and Yuan, S.M.},
  title = {Web-based peer assessment: feedback for students with various thinking-styles},
  month = {Dec},
  journal = {Journal of Computer Assisted Learning},
  publisher = {Wiley Blackwell (Blackwell Publishing)},
  year = {2001},
  volume = {17},
  number = {4},
  pages = {420ִ32},
  url = {http://dx.doi.org/10.1046/j.0266-4909.2001.00198.x},
  doi = {10.1046/j.0266-4909.2001.00198.x}
}
BibTeX:
@incollection{spie2001,
  author = {S. P. N. Singh and S. Thayer},
  title = {{Immunology Directed Methods for Distributed Robotics: A Novel, Immunity-Based Architecture for Robust Control and Coordination}},
  booktitle = {{Mobile Robots XVI}},
  publisher = {{Proceedings of the {SPIE}}},
  year = {2001},
  volume = {4573},
  pages = {44-55},
  url = {http://bookstore.spie.org/index.cfm?fuseaction=DetailPaper&ProductId=457453}
}
Review: Platypus
BibTeX:
@article{Tsai_Liu_Lin_Yuan_2001,
  author = {Tsai, Chin-Chung and Liu, Eric Zhi-Feng and Lin, Sunny S J and Yuan, Shyan-Ming},
  title = {A Networked Peer Assessment System Based on a Vee Heuristic},
  month = {Jan},
  journal = {Innovations in Education and Teaching International},
  publisher = {Informa UK (Taylor \& Francis)},
  year = {2001},
  volume = {38},
  number = {3},
  pages = {220ֲ30},
  doi = {10.1080/14703290110051415}
}

Created by JabRef on 11/07/2013.