By Topic

Multisensor Fusion and Integration for Intelligent Systems (MFI), 2010 IEEE Conference on

Date 5-7 Sept. 2010

Filter Results

Displaying Results 1 - 25 of 47
  • MFI2010 technical program

    Publication Year: 2010 , Page(s): 1 - 2
    Save to Project icon | Request Permissions | PDF file iconPDF (51 KB)  
    Freely Available from IEEE
  • Keyword index

    Publication Year: 2010 , Page(s): 1
    Save to Project icon | Request Permissions | PDF file iconPDF (49 KB)  
    Freely Available from IEEE
  • Table of contents

    Publication Year: 2010 , Page(s): 1 - 4
    Save to Project icon | Request Permissions | PDF file iconPDF (103 KB)  
    Freely Available from IEEE
  • Heading prediction in unmanned ground vehicles by laser compass

    Publication Year: 2010 , Page(s): 255 - 260
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1557 KB) |  | HTML iconHTML  

    This paper presents an on-line algorithm that provides accurate heading predictions for Unmanned Ground Vehicles (UGVs). The algorithm uses cross-correlation of SICK laser scans to improve the heading predictions from GPS. It was tested on our Centaur vehicles in outdoor urban environments and verified to provide accurate smooth heading predictions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Cyber-physical trade-offs in distributed detection networks

    Publication Year: 2010 , Page(s): 88 - 95
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (750 KB) |  | HTML iconHTML  

    We consider a network of sensors that measure the scalar intensity due to the background or a source combined with background, inside a two-dimensional monitoring area. The sensor measurements may be random due to the underlying nature of the source and background or due to sensor errors or both. The detection problem is infer the presence of a source of unknown intensity and location based on sensor measurements. In the conventional approach, detection decisions are made at the individual sensors, which are then combined at the fusion center, for example using the majority rule. With increased communication and computation costs, we show that a more complex fusion algorithm based on measurements achieves better detection performance under smooth and non-smooth source intensity functions, Lipschitz conditions on probability ratios and a minimum packing number for the state-space. We show that these conditions for trade-offs between the cyber costs and physical detection performance are applicable for two detection problems: (i) Poisson radiation sources amidst background radiation, and (ii) sources and background with Gaussian distributions. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Handling heterogeneous information sources for multi-robot sensor fusion

    Publication Year: 2010 , Page(s): 133 - 138
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (507 KB) |  | HTML iconHTML  

    In real world scenarios, measurements from a robot's environment and their respective models are rarely homogeneous in terms of their uncertainty. Instead it is likely to have classes of objects that greatly differ in this respect, such as static and dynamic, unique and ambiguous or previously known and previously unknown objects. This paper extends the concept of FastSLAM to exploit this fact in order to more efficiently localize an autonomous mobile robot and simultaneously map features and track dynamic objects in its environment in a cooperative multi-robot scenario. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fusion of tactile sensing and haptic feedback for unknown object identification aimed to tele-manipulation

    Publication Year: 2010 , Page(s): 205 - 210
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1628 KB) |  | HTML iconHTML  

    This paper describes the design and development of a system combining autonomous collision detection with force-reflective teleoperation. This setup allows a human operator to feel the geometrical relationship between the robot and the remote environment. The aim for the user is to explore object position and shape in an obstacle-cluttered remote environment via a haptic device. The novelty of the approach lays in coupling such a setup with a control algorithm that ensures transparency of the remote robot's kinematic structure to the user. Experiments were conducted to evaluate both the userfriendliness of the setup and its potential for investigating human cognitive process related to pattern generation during tactile exploration. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 3D laser range sensor module with roundly swinging mechanism for fast and wide view range image

    Publication Year: 2010 , Page(s): 156 - 161
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (591 KB) |  | HTML iconHTML  

    We developed a three dimensional range sensor module for taking wide view field laser reflecting points in which the body of two dimensional SOKUIKI sensor is swung by roundly swinging mechanism. We have defined the communication interface with SCIP-3D mini, as a minimum set of command system for 3D SOKUIKI sensor. To indicate the performance of the SOKUIKI sensor module, we took the reflecting points in real space in various environment. The results have shown the usefulness for the real-time environmental measurements. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Target parameter estimation with heterogeneous sensor networks

    Publication Year: 2010 , Page(s): 96 - 101
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (309 KB) |  | HTML iconHTML  

    A distributed network of sensors leverages its performance by aggregating information gathered by individual sensors. This process is referred to as sensor fusion. The primary goal of sensor fusion is to process and progressively refine information from multiple sensors to eventually create situation awareness (SA). Sensor fusion requires sensors to exchange data and information over a network with limited capacity. Consequently, fusing raw sensor data may not be desirable, since transporting large amounts of data from sensor nodes will consume a lot of bandwidth, which is in short supply in a typical wireless sensor network. More importantly, when a network has heterogeneous sensors with widely varying signal characteristics, it may not even be possible to mix sensor data from different sensor modalities. To minimize network bandwidth requirements and to deal with the multiple sensing modalities, we propose an alternative approach in which sensors compute their individual estimates, which are then sent to a fusion center that generates global estimates by optimally aggregating individual estimates. Since sensors do not have any prior knowledge about the value of the parameters to be estimated, each sensor independently computes its maximum likelihood estimates of the unknown parameters, based on the limited sensed data gathered in its local vicinity. These estimates along with their distributions are then communicated to a fusion center. The global estimator computes the final maximum likelihood estimates by maximizing a new likelihood function using the distribution of the individual estimates provide by different sensors. Since the distribution of an estimate typically requires a small number of parameters or moments, the amount of data that a sensor needs to communicate over the network is significantly reduced. The performance of the global estimator is evaluated by computing the Cramer-Rao lower bound of the variance of the estimates. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Sensor fusion based on multi-self-organizing maps for SLAM

    Publication Year: 2010 , Page(s): 139 - 143
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (868 KB) |  | HTML iconHTML  

    This paper proposes the use of topological maps in order to provide a method of SLAM feature, based on sensor fusion, that treats better the problem of inaccuracy of the current systems. The contribution of the work is in the algorithm that uses multiple sensory sources, multiple topological maps, to improve the estimation of localization, in order to be as generic as possible, so the same is valid for both internal and external environments (structured or not). When this is made with sensors of clashing characteristics we can obtain better results, because something not perceived by a sensor might be perceived by others, so we can also reduce the effects of error measurement and obtaining a method that works with the uncertainties of the sensors. A simulator was developed to validate the proposed system, through a series of tests with a set of real data. The results show the robustness of the system in relation to the sensorial imprecision and to the gain in predicting the robot's location, resulting in a more appropriate treatment to the errors associated with each sensor. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Fusing multiple sensors through behaviors with the distributed architecture

    Publication Year: 2010 , Page(s): 115 - 120
    Cited by:  Papers (2)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (362 KB)  

    This paper describes a new action selection mechanism that allows the robot controller to dynamically determine which goals (tasks) are most applicable in the current state of the environment. This allows the robotic controller to resolve conflicting goals that arise, allow multiple non-conflicting goals to run simultaneously, and dynamically switch to a new goal if the target for the goal has been found in the environment. This is accomplished by using a behavior based paradigm and allowing each behavior to calculate its own activation level (run level). The behaviors then use the activation level to compete for control in a new distributed control architecture to allow execution of multiple (and sometimes conflicting) goals on a robotic system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Click Fraud Prevention via multimodal evidence fusion by Dempster-Shafer theory

    Publication Year: 2010 , Page(s): 26 - 31
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1044 KB) |  | HTML iconHTML  

    We address the problem of combining information from diversified sources in a coherent fashion. A generalized evidence processing theory and an architecture for data fusion that accommodates diversified sources of information are presented. Different levels at which data fusion may take place such as the level of dynamics, the level of attributes, and the level of evidence are discussed. A multi-level fusion architecture based Collaborative Click Fraud Detection and Prevention (CCFDP) system for real time click fraud detection and prevention is proposed and its performance is compared with a traditional rule based click fraud detection system. Both systems are tested with real world data from an actual ad campaign. Results show that use of multi-level data fusion improves the quality of click fraud analysis. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hierarchical SLAM for uncertain range data

    Publication Year: 2010 , Page(s): 144 - 149
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (531 KB) |  | HTML iconHTML  

    This paper describes a new approach to SLAM problems using low quality range data. Vision sensors are useful for acquiring various kinds of environmental information but range data obtained by stereo vision is less reliable than other active sensors like laser range finders. False stereo matches often result in spurious obstacles, which may degrade the map when directly used in existing SLAM methods. We therefore propose a hierarchical approach in which local probabilistic occupancy maps are first generated to filter out such spurious obstacles and then used as inputs to an RBPF-based SLAM. Experimental results in simulation and in a real environment show that a consistent map can be generated by the proposed method with low quality stereo range data. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Autonomous Mobile Robot Navigation and Localization Based on Floor Plan Map Information and Sensory Fusion approach

    Publication Year: 2010 , Page(s): 121 - 126
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1349 KB) |  | HTML iconHTML  

    The objective of this paper is to develop a Mobile Robot Navigation and Localization Based on Floor Plan Map Information and Sensory Fusion approach. We have developed map recognition algorithm for recognizing the floor plan and high level multi-sensor topological navigation system utilizing the information to perform navigation tasks. In our algorithm, robot can recognize the floor plan to get enough information automatically like human. First, it recognizes the floor plan map, generates the path to destination and extracts two kinds of landmarks location from floor plan map. One is room plate landmark and the other is passage corner landmark. Second, these landmarks can be detected by camera and ultrasonic sensor in experimental environment. Robot can then navigate to the destination by following these landmarks and generated path. The main contributions of this paper are: 1).floor plan can be reconstructed quickly. 2). It is easier to describe the destination for user. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • TaG-Games: Tangible geometric games for assessing cognitive problem-solving skills and fine motor proficiency

    Publication Year: 2010 , Page(s): 32 - 37
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (593 KB) |  | HTML iconHTML  

    This paper presents Tangible Geometric Games (TaG-Games) as a novel play-based assessment tool for measuring cognitive problem-solving skills and fine motor proficiency. TaG-Games are based on sensor-integrated geometric blocks (SIG-Blocks) and an interactive graphical user interface providing a means for real-time and remote monitoring of a player through wireless communication between the blocks and a host computer. The data made available by employing TaG-Games includes: 1) accelerations, 2) time at each stage of assembly completion, 3) total completion time for each quiz, and 4) correctness of each assembly step. In addition, the user interface displays the real-time assembly configuration of the blocks. As a computational method for analyzing complexity associated with geometric play, a quantitative measure of play complexity is defined based on an information-theoretic approach. The validity of the sensors integrated in each SIG-Block (an accelerometer and optical sensors) is evaluated for measuring tilt angles and detecting assemblies between the blocks. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • MMS-PSO for distributed regression over sensor networks

    Publication Year: 2010 , Page(s): 68 - 73
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (618 KB) |  | HTML iconHTML  

    Regression is one of the effective techniques for data analysis in a WSN. Besides distributed data, the limited power supply and bandwidth capacity of nodes makes doing regression difficult in WSNs. Conventional methods, which employ some numerical optimization techniques such as Nelder-Mead simplex and gradient descent, generally work in a pre-established Hamiltonian path among the nodes. Low estimation accuracy and high latency are common shortcomings appear in these approaches. In this paper, we propose a distributed approach based on PSO, denoted as MMS-PSO (Multi Master Slave PSO), for regression analysis over sensor networks. Accordingly, after clustering the network each cluster is initially dedicated a swarm. The swarm of cluster, which sponsors learning the regressor of cluster, is equally distributed amongst the member nodes and consequently optimized through optimization of the sub-swarms (slaves). To guarantee the convergence of the cluster's swarm, some sharing points are placed between the sub-swarms via designated cluster head (master). After completion of in-cluster optimizations, each cluster head sends its regressor to the fusion center. Finally, the fusion center uses weighted averaging combination rule to combine the received regressors for constructing the final model. Our evaluation and results show that the proposed approach has quite better performance in terms of the estimation accuracy, latency and energy efficiency compared to its counterparts. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Context awareness emergence for distributed binary pyroelectric sensors

    Publication Year: 2010 , Page(s): 162 - 167
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (407 KB) |  | HTML iconHTML  

    We have built a distributed binary pyroelectric sensor network (PSN) for the purpose of multi-walker recognition and tracking. It is important to identify a region of interest (RoI) in the monitoring area in order to find any interesting targets (i.e., walkers). The prerequisite of RoI identification is to accurately extract context features (such as the target IDs and positions) from a hybrid, binary, multi-walker sensor data stream. In this paper, we present our research results on the contextual basis learning and context feature extraction through signal projection in orthogonal subspaces. Particularly, the context identification effects (from signal reconstruction viewpoint) have been investigated a signal projection scheme called non-negative matrix factorization (NMF). Our results have shown the accuracy of context feature learning under a PSN-based multi-walker monitoring scenario. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • 1-bit walker recognition with distributed binary pyroelectric sensors

    Publication Year: 2010 , Page(s): 168 - 173
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (452 KB) |  | HTML iconHTML  

    This paper presents a wireless compressive pyroelectric sensor system for walker recognition. The research aims to make wireless distributed pyroelectric sensors a low-cost, low-data-throughput alternative to the expensive infrared video sensors in behavioral biometric applications. The compressive measurements are achieved by using both (1) non-uniform sensor sampling structures and (2) random projection based sensing protocols. As a result, the gait biometric feature can be represented by a 1-bit data stream. Both decentralized and centralized data fusion schemes are developed to improve the recognition speed and accuracy. A prototype of wireless pyroelectric sensor system has been developed to demonstrate the discrimination capability of the proposed 1-bit walker recognition system for a small group of subjects. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • A hybrid intelligent system combining self organizing maps and case based reasoning for evaluating postural control

    Publication Year: 2010 , Page(s): 38 - 43
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (382 KB) |  | HTML iconHTML  

    Evaluating performance is crucial in stability assessments and training as it provides a valuable measure to examine postural control and recommend rehabilitation strategies for improvement. This paper proposes a novel methodology combining self organizing maps and case based reasoning implemented using a relational database management system to access, examine, diagnose and propose recommendations for improving trunk postural control. A self organizing map was developed to classify the input dataset gathered during a tandem Romberg stability test which behaved as the knowledgebase of the system. Case based reasoning was incorporated based on its ability to solve new problems by adopting previously defined, successful solutions to analogous problems. The case based reasoning architecture was implemented using a relational database with the self organizing map integrated to retrieve analogous case records to solve a new case. The prediction accuracy of the hybrid system to accurately produce the most similar case for a given new case was tested using leave-one-out-cross-validation method. The results demonstrated a high prediction accuracy of over 90% confirming the effectiveness of the hybrid methodology for evaluating and predicting recommendations for performance improvement based on existing knowledgebase for postural control. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Evaluation of gait parameters for gait phase detection during walking

    Publication Year: 2010 , Page(s): 127 - 132
    Cited by:  Papers (3)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (796 KB) |  | HTML iconHTML  

    Two gait phase detection systems (GPDS) are evaluated to obtain the most accurate and reliable approach. First system incorporates only kinematic gait parameters (hip, knee and ankle angles), while the second system incorporates both kinetic (foot pressure) and kinematic (knee angle) parameters. The results report the reliability of GPDS based on kinetic and kinematic parameters as 100% in contrast to the reliability of the GPDS based on only kinematic parameters as 67.4%. Furthermore, during stance phase, the foot pressure patterns provided a clear differentiation of the gait phases in comparison to joint angles. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Computing with uncertainty in a smart textile surface for object recognition

    Publication Year: 2010 , Page(s): 174 - 179
    Cited by:  Papers (7)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1010 KB) |  | HTML iconHTML  

    A wearable surface capable of performing object recognition on objects placed on it has many applications in health care such as surgery, assisted living posture monitoring, specifically movement of body parts during sleep and etc. The flexibility and wearability of textile material allows its widespread applications in body-worn contexts. In this work, we propose a portable and wearable smart textile surface which is capable of performing object recognition on a set of prior known objects. We integrate data from multiple sensors to gain knowledge about objects in the environment. The uncertainty present in such systems can lead to inaccurate interpretation of the data which is crucial in various medical applications. The most significant part of this uncertainty is due to effects of multiple sensors on each other. We look at different sources of uncertainties in such systems and formulate them. We modify vision algorithm to account for these uncertainties and in the end we present precision bounds for the accuracy of the system. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Mission-oriented design: A fully autonomous mobile urban robot

    Publication Year: 2010 , Page(s): 261 - 266
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1833 KB) |  | HTML iconHTML  

    This paper describes a fully autonomous mobile urban robot-X1, which can perform multiple tasks autonomously in an unknown urban environment without human guidance, including mobile reconnaissance, target searching, and object manipulation. The mission-oriented design, which allows reliability and extensibility of the robotic system, includes a high degree of modularity for both hardware and software architecture, and coordination between tasks. Our strategy specifically addresses fundamental issues such as autonomous navigation in unknown urban environments and vision-based object manipulation. All the functionalities have been proved effective in the real urban environments. The robot platform is being built to provide valuable experiences on autonomous robotics research. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Biologically-inspired image-based sensor fusion approach to compensate gyro sensor drift in mobile robot systems that balance

    Publication Year: 2010 , Page(s): 102 - 108
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1568 KB) |  | HTML iconHTML  

    Current approaches to determine the orientation and maintain balance of mobile robots typically rely on gyro and tilt sensor data. This paper presents an image-based sensor fusion approach using sensed data from a MEMS gyro and a digital image processing system. The approach relies on the statistical property of man-made or cultural environments to exhibit predominately more horizontal and vertical edges than oblique edges. The gyro data and statistical image data is Kalman filtered to estimate the roll angle. The system was tested both indoors and outdoors at the University of Arizona campus, and it demonstrated continuous roll angle drift correction, without prior knowledge of or training on the environment. The algorithm was then implemented in a biped walking robot to demonstrate the real-time, end-to-end proof of concept. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Semi-analytic stochastic linearization for range-based pose tracking

    Publication Year: 2010 , Page(s): 44 - 49
    Cited by:  Papers (4)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (897 KB) |  | HTML iconHTML  

    In range-based pose tracking, the translation and rotation of an object with respect to a global coordinate system has to be estimated. The ranges are measured between the target and the global frame. In this paper, an intelligent decomposition is introduced in order to reduce the computational effort for pose tracking. Usually, decomposition procedures only exploit conditionally linear models. In this paper, this principle is generalized to conditionally integrable substructures and applied to pose tracking. Due to a modified measurement equation, parts of the problem can even be solved analytically. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.
  • Radio-visual signal fusion for localization in cellular networks

    Publication Year: 2010 , Page(s): 150 - 155
    Cited by:  Papers (1)
    Save to Project icon | Request Permissions | Click to expandQuick Abstract | PDF file iconPDF (1985 KB) |  | HTML iconHTML  

    Location based services in wireless networks is a quite demanding application especially in urban areas. Cellular network provides measurements regarding the signal attenuations from serving and neighbouring base stations for managing radio resources. Localization based on this inconsistent received signal strength is a challenging problem. This paper describes a novel bimodal localization idea for mobile users in cellular networks. A series of vision-based algorithms are applied to extract user position from monocular vision and then augment it with extracted location in cellular network. A probabilistic framework based on particle filters developed to fuse the bimodal data as well as localize the mobile user from inconsistent measurements. An adaptive particle weighting scheme based on the modal confidence coefficient is also developed. This approach can be easily implemented to utilize available online visual databases to increase accuracy of conventional localization methods for wireless networks even in indoor environments that other navigation signals are not available. View full abstract»

    Full text access may be available. Click article title to sign in or learn about subscription options.