Showing papers presented at "International Conference on Control, Automation, Robotics and Vision in 2006"

Multi-Agent Reinforcement Learning: A Survey

Abstract: Multi-agent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, economics. Many tasks arising in these domains require that the agents learn behaviors online. A significant part of the research on multi-agent learning concerns reinforcement learning techniques. However, due to different viewpoints on central issues, such as the formal statement of the learning goal, a large number of different methods and approaches have been introduced. In this paper we aim to present an integrated survey of the field. First, the issue of the multi-agent learning goal is discussed, after which a representative selection of algorithms is reviewed. Finally, open issues are identified and future research directions are outlined

SnakeFighter - Development of a Water Hydraulic Fire Fighting Snake Robot

Abstract: This paper presents the SnakeFighter concept and describes the generic element within this concept in the form of a water hydraulic snake robot. Applications of a SnakeFighter system are presented with focus on fire intervention tasks. The development of a water hydraulic snake robot that demonstrates the concept is described. The robot is the first water hydraulic snake robot ever constructed. The paper identifies design challenges of a complete SnakeFighter system and describes future research on this concept.

Motion Estimation to a Failed Satellite on Orbit using Stereo Vision and 3D Model Matching

Abstract: An algorithm is developed for estimating the motion (relative attitude and relative position) of large pieces of space debris, such as failed satellites. The algorithm is designed to be used by a debris removal system which would perform various operations on space debris such as observation, investigation, capture, repair, refuel and de-orbit. During these operations, the debris removal system must control its position and attitude simultaneously. Such six degree-of-freedom control becomes more difficult if the failed satellite is changing attitude, such as by nutation. The information required as feedback signals for such a controller is relative - position, velocity, attitude and angular velocity - and these are expected to be measured or estimated from image data. The algorithm uses a combination of stereo vision and 3D model matching, applying the ICP (iterative closest point) algorithm, and uses time series of images to increase the reliability of the relative attitude and position estimates. To evaluate the algorithm, a visual simulator is prepared to simulate the on-orbit optical environment in terrestrial experiments, and the motion of a miniature satellite model is estimated using images obtained from the simulator

A New End-effector for On-orbit Assembly of a Large Reflector

Abstract: In Earth orbit, astronomical observations are possible free from any absorption or disturbances by the Earth's atmosphere. Therefore, some large space telescopes and large space radio telescopes are planned for the future. We discuss the design of a radio telescope reflector which can be assembled in orbit by a space robot arm, with its networks and connecting mechanisms suitable for robot tasks. The characteristics of the new end-effector of robot arm and their suitability for onboard assembly tasks were confirmed by testing using a prototype end-effector and a two dimensional ground test arm. The test results are also described in this paper.

Dynamic Environment Modeling with Gridmap: A Multiple-Object Tracking Application

Abstract: The Bayesian occupancy filter (BOF) (Coue et al., 2002) has achieved promising results in the object tracking applications. This paper presents a new development of BOF which inherits original BOF's advantages. Meanwhile, the new formulation has significantly reduced original BOF's complexities and can be run in realtime. In Bayesian occupancy filter, the environment is finely divided into 2-dimensional grids. Different from conventional occupancy gridmaps, in BOF, each grid has both static (occupancy) and dynamic (velocity) characteristics. In the new proposed BOF, the velocity of each cell is modeled as a distribution. The distribution for each cell occupancy can therefore be inferred using a filtering mechanism. A segmentation algorithm is implemented to extract the objects from BOF estimation. Thereafter, standard target tracking methods are employed to further analyze each object's motion. By using BOF as a pre-processing tool, the complexity of the data association is significantly reduced. Experiments using data from an indoor human tracking application demonstrate that our approach yields satisfactory results

Estimating Malaria Parasitaemia from Blood Smear Images

Abstract: A technique is proposed for estimating parasitaemia from blood smear images by extracting healthy and parasite infected red blood cells. The developed approach accounts for uncertain imaging conditions due to microscope settings as well as the quality of the blood smear preparation. The solution is based on a multi-stage estimation process with minimal prior knowledge starting from a model representation of red blood cells. Based on pattern matching with parameter optimisation and cross-validation against the expected biological characteristics, red blood cells are determined. In a final stage, the parasitaemia measure is carried out by partitioning the uninfected and infected cells using an unsupervised and in comparison a training-based technique. Finally, the obtained estimates were analysed with respect to manually acquired results from professionals. Red blood cells detection resulted in precision and recall rates of 80-88% and 92-98%, respectively. By using a training-based method, the precision and recall rates were improved to 92% and 95%, respectively.

Biophasor: Token Supplemented Cancellable Biometrics

Abstract: Biometrics characteristics are immutable, resulting in permanent biometrics compromise. To address this problem, we prescribe a generic cancellable biometrics formulation - BioPhasor. BioPhasor is a set of binary code based on iterated mixing between the user-specific tokenised pseudo-random number and the biometric feature. This method enables straightforward revocation of biometric template via token replacement. The transformation is non-invertible and BioPhasor able to achieve extremely low error rate compare to sole biometrics in verification setting. The privacy invasion and non-revocable problems in biometrics could be resolved by revocation of resulting feature through the pseudo-random number replacement. We also consider an unfavorable scenario in which an imposter has access genuine token and used by the imposter to claim as the genuine user. The feasibility of the formulation is demonstrated by the experiments on fingerprint images from the FVC2004 database.

Nanorobot Communication Techniques: A Comprehensive Tutorial

Abstract: This work presents chemical communication techniques for nanorobots foraging in fluid environments relevant for medical applications. Unlike larger robots, viscous forces and rapid diffusion dominate their behaviors. Examples range from modified microorganisms to nanorobots using ongoing developments in molecular computation, sensors and motors. The nanorobots use an innovative methodology to achieve decentralized control for a distributed collective action in the combat of cancer. A communication approach is described in the context of recognize a single tumor cell in a small venule as a target for medical treatment. Thus, a higher gradient of signal intensity of E-cadherin is used as chemical parameter identification in guiding nanorobots to identify malignant tissues. A nanorobot can effectively use chemical communication to improve intervention time to identify tumor cells.

The Effect of Image Resolution on the Performance of a Face Recognition System

Abstract: In this paper we investigate the effect of image resolution on the error rates of a face verification system. We do not restrict ourselves to the face recognition algorithm only, but we also consider the face registration. In our face recognition system, the face registration is done by finding landmarks in a face image and subsequent alignment based on these landmarks. To investigate the effect of image resolution we performed experiments where we varied the resolution. We investigate the effect of the resolution on the face recognition part, the registration part and the entire system. This research also confirms that accurate registration is of vital importance to the performance of the face recognition algorithm. The results of our face recognition system are optimal on face images with a resolution of 32 times 32 pixels

2D/3D Vision-Based Mango's Feature Extraction and Sorting

Abstract: This paper describes a vision system that can extract 2D and 3D visual properties of mango such as size (length, width, and thickness), projected area, volume, and surface area from images and use them in sorting. The 2D/3D visual properties are extracted from multiple view images of mango. The images are first segmented to extract the silhouette regions of mango. The 2D visual properties are then measured from the top view silhouette as explained by Yimyam et al. (2005). The 3D mango volume reconstruction is done using volumetric caving on multiple silhouette images. First the cameras are calibrated to obtain the intrinsic and extrinsic camera parameters. Then the 3D volume voxels are crafted based on silhouette images of the fruit in multiple views. After craving all silhouettes, we obtain the coarse 3D shape of the fruit and then we can compute the volume and surface area. We then use these features in automatic mango sorting which we employ a typical backpropagation neural networks. In this research, we employed the system to evaluate visual properties of a mango cultivar called "Nam Dokmai". There were two sets total of 182 mangoes in three various sizes sorted by weights according to a standard sorting metric for mango export. Two experiments were performed. One is for showing the accuracy of our vision-based feature extraction and measurement by comparing results with the measurements using various instruments. The second experiment is to show the sorting accuracy by comparing to human sorting. The results show the technique could be a good alternative and more feasible method for sorting mango comparing to human's manual sorting.

Road-Junction Traffic Signal Timing Optimization by an adaptive Particle Swarm Algorithm

Abstract: The purpose of this paper is to investigate the application of particle swarm optimization (PSO) algorithm in solving the traffic signal timing optimization problem. A local fuzzy-logic controller (FLC) installed at each junction is used to provide some initial solutions for the particle swarm optimization algorithm. Coordination parameters from adjacent junctions are taken into consideration by local fuzzy-logic controller. The membership functions and the rules of the fuzzy logic controller (FLC) are optimized using the standard particle swarm optimization (SPSO) algorithm. A new particle swarm optimization algorithm is used to optimize the average delay and average number of stops for adjacent junctions and to handle the constraints. The simulation results show that the delay per vehicle can be substantially reduced under constant traffic demands and time-varying traffic demands, particularly when the traffic demands on the upstream is larger than the traffic demand on the downstream. The implementation of this method does not require complicated hardware, and such simplicity makes it a useful tool for offline studies or real-time control purposes

Fast Distance Preserving Level Set Evolution for Medical Image Segmentation

Abstract: Accurate and fast image segmentation algorithms are of paramount importance for a wide range of medical imaging applications. Level set algorithms based on narrow band implementation have been among the most widely used segmentation algorithms. However, the accuracy of standard level set algorithms is compromised by the fact that their evolution schemes deteriorate the signed distance level set functions required for accurate computation of normals and curvatures. The most common remedy is to use an ad-hoc reinitialization step to rebuild the signed distance function frequently. Meanwhile, complex upwind finite difference schemes are required for stable evolution. They together make the overall computation expensive. In this paper, we propose a novel fast narrow band distance preserving level set evolution algorithm that eliminates the need for both reinitialization and complex upwind finite difference schemes. This is achieved by incorporating into a variational level set formulation with a signed distance preserving term that regularizes the evolution. As a result, stable, accurate, fast evolution could be obtained using a simple finite difference scheme within a very narrow band, defined as the union of all 3times3 pixel blocks around the zero crossing pixels. Also, our method allows the use of larger time step to speed up the convergence while ensuring accurate result, as well as the use of more general and computational efficient initial level set functions rather than the signed distance functions required by standard level set methods. The proposed algorithm has been applied on both synthetic and real images of different modalities with promising results

Decentralized Reinforcement Learning Control of a Robotic Manipulator

Abstract: Multi-agent systems are rapidly finding applications in a variety of domains, including robotics, distributed control, telecommunications, etc. Learning approaches to multi-agent control, many of them based on reinforcement learning (RL), are investigated in complex domains such as teams of mobile robots. However, the application of decentralized RL to low-level control tasks is not as intensively studied. In this paper, we investigate centralized and decentralized RL, emphasizing the challenges and potential advantages of the latter. These are then illustrated on an example: learning to control a two-link rigid manipulator. Some open issues and future research directions in decentralized RL are outlined

A HHMM-Based Approach for Robust Fall Detection

Abstract: Automatic detection of a falling person in video sequences is an important part of future pervasive home monitoring systems. We propose here a robust method to achieve this goal. Motion is modeled by a Hierarchical Hidden Markov Model (HHMM) whose first layer states are related to the orientation of the tracked person. Finding a consistent way for robustly linking the observation vector to the human poses is the heart of our contribution. In that sense, we carefully study the relationship between angles in the 3D world and their projection onto the image plane. After performing an initial image metric rectification, we derive theoretical properties making it possible to bound the error angle introduced by the image formation process for a standing posture. This allows us to confidently identify other poses as "non-standing" ones, and thus to robustly analyze pose sequences against a given motion model. Several results illustrate the efficiency of the algorithm by pointing out its ability to accurately recognize a person falling down from another walking or sitting, as well as its capacity to run in an unspecified configuration.

3D Mapping of Surface Temperature Using Thermal Stereo

Abstract: In this paper we present a simple but novel technique to recover 3D temperature map from a pair of calibrated thermal cameras. The method is also useful in estimating depth of an object in the dark environment.

Preprocessing of Fingerprint Images Captured with a Digital Camera

Abstract: Reliable touch-less fingerprint recognition still remains a challenge nowadays as the conventional techniques that used to preprocess the optical or capacitance sensor acquired fingerprint image, for segmentation, enhancement and core point detection, are inadequate to serve the purpose. The problems of the touch-less fingerprint recognition are the low contrast between the ridges and the valleys in fingerprint images, defocus and motion blur. However, it imposes a competency for a further advancing of this biometric modality since it frees from the problems in terms of hygienic, maintenance and latent fingerprints. In this paper, the digital camera is opted as the device to capture the fingerprint image in RGB format and the procedures to segment, enhance and detect the core point of the fingerprint image are outlined.

Object-based Surveillance Video Compression using Foreground Motion Compensation

Abstract: Video surveillance is currently one of the most active area of research in both academia and industry. Though much work has been done in the area of smart surveillance, relatively little work has been reported to compress the surveillance videos. In this paper, we propose an object based video compression system using foreground motion compensation for applications such as archival and transmission of surveillance video. The proposed system segments independently moving objects from the video and codes them with respect to the previously reconstructed frame. The error resulting from object-based motion compensation is coded using SA-DCT procedure. The proposed system codes the surveillance video using far lesser bits compared to conventional video compression techniques.

Sensor Interoperability and Fusion in Fingerprint Verification: A Case Study using Minutiae-and Ridge-Based Matchers

Abstract: Information fusion in fingerprint recognition has been studied in several papers. However, only a few papers have been focused on sensor interoperability and sensor fusion. In this paper, these two topics are studied using a multisensor database acquired with three different fingerprint sensors. Authentication experiments using minutiae and ridge-based matchers are reported. Results show that the performance drops dramatically when matching images from different sensors. We have also observed that fusing scores from different sensors results in better performance than fusing different instances from the same sensor1.

Road Scene Analysis by Stereovision: a Robust and Quasi-Dense Approach

Abstract: A stereovision method is presented in his paper, to compute reliable and quasi-dense disparity maps of road scenes using in-vehicle cameras. It combines the advantages of the "v-disparity" approach and a quasi-dense matching algorithm. In this aim, road surface and vertical planes of the scene are first extracted using the sparse "v-disparity" approach. The knowledge of these global surfaces of the scene is then used to guide a quasi-dense matching algorithm and to propagate disparity information on horizontal edges. Both algorithms are presented and compared. Then, our approach is presented and examples of quasi-dense disparity maps are given. Finally, the efficiency of the method is illustrated by the accurate positioning of a bounding box around a vehicle in a bad contrasted video sequence.

Control Performance Analysis of Feedforward and Maximum Peak Power Tracking for Small-and Medium-Sized Fixed Pitch Wind Turbines

Abstract: As the wind has become one of the fastest growing renewable energy sources, the key issue of wind energy conversion systems is how to efficiently operate the wind turbines in a wide range of wind speeds. In this paper where small- and medium-sized fixed pitch wind turbines are focused, a control performance analysis of the feedforward and maximum peak power tracking (MPPT) to maximize the power of the turbines while operating in their below rated power and to limit the power while operating in their above rated power is presented. The algorithms were implemented on a low cost digital signal controller (DSC) board and tested with a developed real-time wind turbine simulator, consisting of an induction motor driven by a torque control inverter, and computer interface for data acquisition. The experimental results show that the feedforward performs more satisfactorily when compared to the MPPT and has better performance indices in overall operating conditions. However, the feedforward causes power oscillation in the above rated power and needs wind turbine parameters as a control reference, but those parameters are not necessary in the MPPT, which exhibits an attractive feature

Developments in Snake Robot Modeling and Locomotion

Abstract: Snake robots may one day play a crucial role in search and rescue operations and fire-fighting where it may either be too narrow or to dangerous for personnel to operate. Properties such as high terrainability, redundancy, and the possibility of complete sealing of the body of the robot, make snake robots very interesting for practical applications and hence as a research topic. During the last ten to fifteen years, the published literature on snake robots has increased vastly. However, no thorough review of the theory presented in this period regarding mathematical modeling techniques and locomotion of snake robots has been found. The purpose of this paper is to give such a review. Both purely kinematic models and models including dynamics are investigated. The choice of modeling method is linked to snake robot design characteristics and locomotion approach. Different approaches to biologically inspired locomotion are also discussed.

A Compact 24 GHz Sensor for Beam-Forming and Imaging

Abstract: A compact 24 GHz sensor setup for experimental verifications of radar imaging and digital beam-forming has been designed and realized. The sensor consists of a FM-CW radar front-end and a remote radar electronic unit. The front-end consists of a switched antenna array of 25 linearly arranged elements fed by one transmitter and two parallel homodyne receivers connected to separate receive antenna elements. The remote radar electronic unit includes the base-band signal generation, analog inputs for data acquisition and programmable digital circuitry for measurement control, data storage and interface handling. The sensor can be operated from a notebook computer via standard PC interfaces, thus forming a compact imaging radar system well suited for field tests. The sensor addresses primarily short and medium range automotive applications, but its flexibility in signal generation, sampling and coherent signal processing makes it interesting for many other application fields. In this article a detailed description of the total system is given and exemplary signal processing methods for imaging and beam-forming are introduced and demonstrated with measurement results.

Adaptive Neural Network Control of Uncertain Nonlinear Systems in the Presence of Input Saturation

Abstract: In this paper, we present a new scheme to design adaptive controller for uncertain nonlinear systems in the presence of input saturation. The control design is achieved by using backstepping technique and neural network. Unlike some existing control schemes for systems with input saturation, the developed controller does not require uncertain parameters within a known compact set. Besides showing stability, transient performance is also established and can be adjusted by tuning certain design parameters.

Tracking of a Moving Object Using One-Dimensional Optical Flow with a Rotating Observer

Abstract: The optical flow is a useful tool for the tracking of a moving object. Estimation of the optical flow based on the gradient method is an ill-posed problem. In order to avoid this ill-posed problem, we proposed a tracking method using a one-dimensional optical flow, which is calculated on a straight line (called the calculation axis) spanning several directions. However, the motion of the observer was not considered. In this paper, we propose object tracking by a one-dimensional optical flow under a rotating observer. The apparent motion of a stationary environment object should be eliminated for calculating the one-dimensional optical flow. Hence, we introduce the detection method of a moving object by mapping, which converts the motion of a stationary environment object into a linear signal trajectory. We calculate the one-dimensional optical flow by using pixels, which belong to the moving object, to eliminate the apparent motion of the stationary environment object. In order to verify the efficacy of the proposed method, simulation is performed using synthesized images. The proposed method successfully tracks the moving object when the observer rotates at a constant angular velocity

Adaptive Stable PID Controller with Parallel Feedforward Compensator

Abstract: In this paper, a new design method of adaptive PID controller is proposed. The method utilizes the plant characteristics called almost strict positive realness (ASPR) so that the stability of the adaptive PID control system is always guaranteed. The design scheme is derived for the design of adaptive tracking PID control system. Here it is also proposed a new design procedure of the parallel feedforward compensator (PFC) which actually guarantees the ASPRness of the controlled plant. The result is examined by applying it to the design of the first order with time delay process system. The effectiveness of the method is examined through simulations and experiments using thermal pilot plant.

GestureCam: A Smart Camera for Gesture Recognition and Gesture-Controlled Web Navigation

Abstract: Smart camera, or an intelligent camera, is an embedded vision system which captures and processes image to extract application-specific information in real time. Smart cameras are used in many applications such as automatic control systems, machine vision systems, automatic video surveillance systems and human computer interfaces. What makes a smart camera `smart' is a special processing unit inside the camera which performs application specific information processing, for example, skin color detection and motion detection for surveillance purpose. The design of smart camera as an embedded system is challenging because on one hand video processing has insatiable demand for performance and power, and on the other hand embedded systems place considerable constraints on the design. We present our work in progress to build GestureCam, an FPGA-based smart camera that can recognize simple pre-defined head and hand gestures. As an application of the GestureCam, we present the design of a GestureBrowser, an extension to the Mozilla Firefox browser which uses the GestureCam to capture and recognize a user's head and hand gesture commands to control web navigation. The GestureBrowser idea is a step further toward next generation natural human computer interaction. Also presented is a proof of concept work for the GestureBrowser idea, using a webcam as image capture device.

A Rear-Vehicle Detection System for Static Images Based on Monocular Vision

Abstract: A rear-vehicle detection system of static images based on monocular vision is presented. It does not need the road boundary and lane information. Firstly, it segments the region of interest (ROI) by using the shadow underneath the vehicle and edges. Secondly, it accurately localizes the ROI by vehicle features such as symmetry, edges and the shadow underneath the vehicle, etc. Finally, it completes vehicle detection by combining knowledge-based and statistics-based methods. Under various illuminations and different roads (different day time, different scenes: highway, urban common road, urban narrow road), the system shows good results of recognition and performance.

Submerged Robotic Micromanipulation and Dielectrophoretic Micro-object Release

Abstract: The development of new hybrid microsystems needs new technologies which are able to perform assembly of small micro-objects. Now, the current micromanipulation technologies are still unreliable for micro-objects which typical size is down to hundred micrometers. Consequently, the study and the development of innovative artificial micro-object manipulation strategies in these dimensions is particularly relevant. As presented in the literature, micromanipulations are perturbed by the adhesion and surface forces which depend on surrounding mediums. We propose to perform micro-assembly tasks in liquid medium, because adhesion and surface forces applied on submerged micro-objects are less important than in air. The comparative analysis of micro-forces in air and in liquid is presented in this paper. Although the micro-forces reduce in liquid, they stay disturbed the micro-objects release. Thus, we propose to extend the dielectrophoresis micromanipulation principles which are currently done in the biological micromanipulation to submerged artificial objects micro-assembly. The negative dielectrophoresis principle is used to release a micro-object grasped with a micro-gripper. Physical principle and first experimentations is presented in this article. Further works will focus on the optimization of the principle, and on the micro-object release modelling and control.

The Algorithm For Berth Scheduling Problem By The Hybrid Optimization Strategy GASA

Abstract: In the operations of the container terminals, berth scheduling problem is one of the main bottlenecks that restrict the container terminals to reduce the turnaround time of the ships and the operation costs. In this paper we described a nonlinear model for the berth scheduling problem and solved this model by the genetic algorithm GA and the hybrid optimization strategy GASA (namely the combination of genetic algorithm and simulated annealing) respectively. The results indicated that compared with GA, the GASA algorithm increased the diversity of the individuals, accelerated the evolution process and avoided sinking into the local optimal solution early

Platform Enhancements and System Identification for Control of an Unmanned Helicopter

Abstract: This paper discusses a common approach to systems integration and automation for two different sizes of rotary wing UAVs. A linear model has been identified using time domain methods for both platforms. The identified models will help to evaluate parameters for designing nonlinear control systems for automatic landing of UAVs on moving platforms. In this paper, the innovation is the enhancement of experimental platforms to better suit experimental research in the design of controllers.