Search

Despite recent advances in automotive sensor technology and artificial intelligence that lead to breakthroughs in sensing capabilities, environment perception in the field of autonomous driving (AD) is still too unreliable for safe operation. Evaluating and managing uncertainty will aid autonomous vehicles (AV) in recognizing perceptual limitations in order to adequately react in critical situations. In this work, we propose an uncertainty evaluation framework in AD based on Dempster-Shafer (DS) theory, that takes context awareness into consideration, a factor that has been so far under-investigated. We formulate uncertainty as a function of context awareness, and examine the effect of redundancy on uncertainty. We also present a modular simulation tool that enables assessing perception architectures in realistic traffic use cases. Our findings show that considering context awareness decreases uncertainty by at least one order of magnitude. We also show that uncertainty behaves exponentially as a function of sensor redundancy.

This article presents a survey of simultaneous localization and mapping (SLAM) and data fusion techniques for object detection and environmental scene perception in unmanned aerial vehicles (UAVs). We critically evaluate some current SLAM implementations in robotics and autonomous vehicles and their applicability and scalability to UAVs. SLAM is envisioned as a potential technique for object detection and scene perception to enable UAV navigation through continuous state estimation. In this article, we bridge the gap between SLAM and data fusion in UAVs while also comprehensively surveying related object detection techniques such as visual odometry and aerial photogrammetry. We begin with an introduction to applications where UAV localization is necessary, followed by an analysis of multimodal sensor data fusion to fuse the information gathered from different sensors mounted on UAVs. We then discuss SLAM techniques such as Kalman filters and extended Kalman filters to address scene perception, mapping, and localization in UAVs. The findings are summarized to correlate prevalent and futuristic SLAM and data fusion for UAV navigation, and some avenues for further research are discussed.

The COVID-19 pandemic has recently brought attention to several acute human needs. However, it has also demonstrated how crisis can spark innovation in the context of information asymmetry and uncertainty. It has raised the importance of early warning systems (EWS) to prevent similar future events and prepare governments, organizations, and individuals in advance. Such efforts in innovating under uncertainty resemble the process entrepreneurs face when creating new ventures and launching new products and services. Moreover, the increasing adoption of mobile technologies associated with the surging Internet of Things (IoT) devices and applications provides cues to a more extensive discussion about the adoption of sensor networks and applied artificial intelligence algorithms to benefit society and improve its relationship with data. Implementing IoT sensor location-based networks to help reduce community-transmitted infections can be a cost-effective solution that adds to broader pandemic control warning systems. In this paper, a novel predictive location-based early warning system is proposed. The system is able to measure people’s density, people flow, and behavior in specific areas of indoor and outdoor environments. Its implementation has been tested in a real public scenario, showing the capacity to operate flawlessly in real-time, thus addressing the needs of a trusted EWS for governments and organizations to manage event-led situations.

The pervasive use of sensors and actuators in the Industry 4.0 paradigm has changed the way we interact with industrial systems. In such a context, modern frameworks are not only limited to the system telemetry but also include the detection of potentially harmful conditions. However, when the number of signals generated by a system is large, it becomes challenging to properly correlate the information for an effective diagnosis. The combination of Artificial Intelligence and sensor data fusion techniques is a valid solution to address this problem, implementing models capable of extracting information from a set of heterogeneous sources. On the other hand, the constrained resources of Edge devices, where these algorithms are usually executed, pose strict limitations in terms of memory occupation and models complexity. To overcome this problem, in this paper we propose an Echo State Network architecture which exploits sensor data fusion to detect the faults on a scale replica industrial plant. Thanks to its sparse weights structure, Echo State Networks are Recurrent Neural Networks models, which exhibit a low complexity and memory footprint, which makes them suitable to be deployed on an Edge device. Through the analysis of vibration and current signals, the proposed model is able to correctly detect the majority of the faults occurring in the industrial plant. Experimental results demonstrate the feasibility of the proposed approach and present a comparison with other approaches, where we show that our methodology is the best trade-off in terms of precision, recall, F1-score and inference time.

In the field of underwater vision, image matching between the main two sensors (sonar and optical camera) has always been a challenging problem. The independent imaging mechanism of the two determines the modalities of the image, and the local features of the images under various modalities are significantly different, which makes the general matching method based on the optical image invalid. In order to make full use of underwater acoustic and optical images, and promote the development of multisensor information fusion (MSIF) technology, this letter proposes to apply an image attribute transfer algorithm and advanced local feature descriptor to solve the problem of underwater acousto-optic image matching. We utilize real and simulated underwater images for testing, experimental results show that our proposed method could effectively preprocess these multimodal images to obtain an accurate matching result, thus providing a new solution for the underwater multisensor image matching task.

This paper describes a configuration of drone swarm that can be used in support of the actions to limit the virus spread during a pandemic period, such as the COVID-19 emergency. The proposed study analyzes a system architecture for the identification of individuals affected by the virus, estimating their biomedical parameters. The presented method exploits different techniques, such as stereoscopy vision, thermal measures and remote photoplethysmography, to acquire standalone data that can be compared to evaluate the target risk. The tested solutions are proposed to measure the social distancing among multiple individuals, the skin temperature of a target person, and the image photoplethysmography signal, that are critical parameters to detect a potentially infect individual during the COVID-19 pandemic. Different test strategies were adopted to carry out the mentioned tasks. To measure the distance between target individuals, two drones equipped with visible band cameras were employed. To measure the skin temperature of a target, a drone equipped with a thermal camera was adopted, performing measures at different distances and heights. To obtain the image photoplethysmography signal, a video file from drone camera is processed. Image processing techniques are required to elaborate the data coming from several images and videos acquired by drones. Comparing the measures, altered biomedical parameters of several targets can be detected and later tested with medical equipment.

International audience; Failure detection and diagnosis are of crucial importance for the reliable and safe operation of industrial equipment and systems, while gearbox failures are one of the main factors leading to long-term downtime. Condition-based maintenance addresses this issue using several expert systems for early failure diagnosis to avoid unplanned shutdowns. In this context, this paper provides a comparative study of two machine-learning-based approaches for gearbox failure diagnosis. The first uses linear predictive coefficients for signal processing and long short-term memory for learning, while the second is based on mel-frequency cepstral coefficients for signal processing, a convolutional neural network for feature extraction, and long short-term memory for classification. This comparative study proposes an improved predictive method using the early fusion technique of multisource sensing data. Using an experimental dataset, the proposals were tested, and their effectiveness was evaluated considering predictions based on statistical metrics.

Trustworthy environment perception is the fundamental basis for the safe deployment of automated agents such as self-driving vehicles or intelligent robots. The problem remains that such trust is notoriously difficult to guarantee in the presence of systematic faults, e.g. non-traceable errors caused by machine learning functions. One way to tackle this issue without making rather specific assumptions about the perception process is plausibility checking. Similar to the reasoning of human intuition, the final outcome of a complex black-box procedure is verified against given expectations of an object's behavior. In this article, we apply and evaluate collaborative, sensor-generic plausibility checking as a mean to detect empirical perception faults from their statistical fingerprints. Our real use case is next-generation automated driving that uses a roadside sensor infrastructure for perception augmentation, represented here by test scenarios at a German highway and a city intersection. The plausibilization analysis is integrated naturally in the object fusion process, and helps to diagnose known and possibly yet unknown faults in distributed sensing systems., 11 pages, 7 figures

Monocular vision systems allow compact and resource-constrained vehicles to perform online state estimation through Structure from Motion approaches. However, it is needed to integrate additional information to obtain a metric scale for the estimated trajectory. We propose a minimalistic approach based on the sensor fusion between a monocular camera and a 1D LiDAR (LIght Detection And Ranging) rangefinder. A classical visual front-end, in charge of tracking the camera pose with respect to a map of landmarks, is paired with an optimization back-end where depth measurements constrain the distance between cameras and 3D points. The fusion methodology is based on a keyframe-wise search of correspondences between visual landmarks and projections of altimeter points. The differences between triangulated landmark depths and associated altimeter measurements are minimized using the iSAM2 incremental smoother. We test our algorithm in a variety of datasets comprising an outdoor scenario with accurate D-GPS ground truth evaluating both tracking accuracy and computational effort. Results show that our algorithm provides comparable performances to scale-aware RGB-D vision systems and obtains relative trajectory errors close to 0.5%. Furthermore, we propose and validate an extrinsic calibration pipeline to refer range measurements in the camera reference system which differs from common LiDAR-camera calibration algorithms due to the 5 Degrees of Freedom (DoF) nature of the single-point rangefinder and camera system.

Technology has been promoting a great transformation in farming. The introduction of robotics, the use of sensors in the field, and the advances in computer vision, allow new systems to be developed to assist processes, such as phenotyping, of crop’s life cycle monitoring. This work presents, which we believe to be the first time, a system capable of generating 3D models of non-rigid corn plants, which can be used as a tool in the phenotyping process. The system is composed by two modules: an terrestrial acquisition module and a processing module. The terrestrial acquisition module is composed by a robot, equipped with an RGB-D camera and three sets of temperature, humidity, and luminosity sensors, that collects data in the field. The processing module conducts the non-rigid 3D plants reconstruction and merges the sensor data into these models. The work presented here also shows a novel technique for background removal in depth images, as well as efficient techniques for processing these images and the sensor data. Experiments have shown that from the models generated and the data collected, plant structural measurements can be performed accurately and the plant’s environment can be mapped, allowing the plant’s health to be evaluated and providing greater crop efficiency.

Spanish Ministry of Science and InnovationMinistry of Science and Innovation, Spain (MICINN)Ministry of Education and Science, Spain; European Regional Development FundEuropean Union (EU) [DPI2015-69891-C2-1-R/2-R], This research was funded by the Spanish Ministry of Science and Innovation and the European Regional Development Fund under project DPI2015-69891-C2-1-R/2-R.

The measurement of geometric deviations within large-size products is a challenging topic. One of the most applied technique compares the nominal product with the digitalization of real product obtained by a reverse engineering process. Digitalization of big geometric models is usually performed by means of multiple acquisitions from different scanning locations. Therefore, digitalization needs to correctly place the acquired point clouds in 3D digital environment. For this purpose, it is very important identifying the exact scanning location in order to correctly realign point clouds and generate an accurate 3D CAD model.The present paper faces the locating problem of a handling device for reverse engineering scanning systems. It proposes a locating method by using sensor data fusion based on Kalman filter, implemented in Matlab environment by using a low-cost equipment.

Autonomous robots that assist humans in day to day living tasks are becoming increasingly popular. Autonomous mobile robots operate by sensing and perceiving their surrounding environment to make accurate driving decisions. A combination of several different sensors such as LiDAR, radar, ultrasound sensors and cameras are utilized to sense the surrounding environment of autonomous vehicles. These heterogeneous sensors simultaneously capture various physical attributes of the environment. Such multimodality and redundancy of sensing need to be positively utilized for reliable and consistent perception of the environment through sensor data fusion. However, these multimodal sensor data streams are different from each other in many ways, such as temporal and spatial resolution, data format, and geometric alignment. For the subsequent perception algorithms to utilize the diversity offered by multimodal sensing, the data streams need to be spatially, geometrically and temporally aligned with each other. In this paper, we address the problem of fusing the outputs of a Light Detection and Ranging (LiDAR) scanner and a wide-angle monocular image sensor for free space detection. The outputs of LiDAR scanner and the image sensor are of different spatial resolutions and need to be aligned with each other. A geometrical model is used to spatially align the two sensor outputs, followed by a Gaussian Process (GP) regression-based resolution matching algorithm to interpolate the missing data with quantifiable uncertainty. The results indicate that the proposed sensor data fusion framework significantly aids the subsequent perception steps, as illustrated by the performance improvement of a uncertainty aware free space detection algorithm.

Internet of Things (IoT) is a promising technology for improving our lives and society by integrating smart devices in our environment and paving the way for novel ICT application, spanning from smart cities to energy efficiency and home automation. However, such a vision encompasses the availability of thousands of smart devices, or even more, that continuously exchange a huge volume of data among each other and with cloud-based services, raising a big data problem. Such a problem can be approached by properly applying data fusion practices within an IoT infrastructure. Due to the characteristics and peculiarities of the communications among smart devices within the IoT, an event-based data fusion is needed, where devices exchange notifications of events among each others. Such data fusion should be focused on special devices where notification heterogeneity, and data source trust issues have to be faced with. Accordingly, the contribution of this work is proposing (i) a novel broker-less event-based communication protocol specifically tailored to sensors with constrained resources, (ii) a solution for flexible event-based communications among heterogeneous data sources, and (iii) an approach based on the theory of evidence for data fusion processes that depend on the matching and trust degree of the data to be fused.

Rendezvous & Docking to passive objects, as of relevance for space debris removal, raises new challenges with respect to relative navigation. Whenever the position and orientation (pose) of an object is required in terrestrial and in space applications, sensor systems such as laser scanners and stereo vision systems are often employed. This paper presents an approach to pose estimation using a 3D time-of-flight camera for ranging information in combination with a high resolution grayscale camera. We have designed a pose estimation method that fuses the data streams of the two sensors in order to benefit from each sensors׳ advantages. A rigorous test campaign on a Real-Time Hardware-In-The-Loop Rendezvous and Docking Simulator – the European Proximity Operations Simulator (EPOS) – was performed in order to evaluate the performance of the resulting algorithm. The proposed pose estimation method does not exceed an average distance error of 3 cm while being capable of providing pose estimates at up to 60 FPS on recent hardware. Thus, when regarding proximity operations, an attractive sensor system is used to characterize the dynamics of the target object for safe approach results.

Currently, such microelectromechanical sensors as accelerome­ters, gyroscopes and magnetometers are the dominant sensors in mobile devices. The market of mobile devices is constantly expanding and focused on sensor integration process by adding supplementary functionality for the applications; therefore, it is possible to adapt these sensors for augmented reality technology solutions. Many augmented reality solutions are based on computer vision processing methods in order to identify and track markers or other objects. However, the main problem is chaotic environment, lighting conditions where object recognition and tracking in real-time becomes difficult and sometimes is an impossible process. This paper analyses possibilities to apply microelectromechanical sensors. Additionally, it investigates quaternion use for sensor data to estimate reliable and accurate camera orientation and represent virtual content in augmented reality technology. Santrauka Šiuo metu mikroelektromechaniniai jutikliai (akcelerometrai, giroskopai ir magnetometrai) dominuoja mobiliuosiuose įrenginiuose. Mobiliųjų įrenginių rinka nepaliaujamai plečiasi ir telkiasi į jutiklių integracijos procesą, kuriamoms aplikacijoms pridedama papildomo funkcionalumo. Tokiu būdu suteikiama galimybė pritaikyti jutiklių informaciją priimant papildytosios realybės technologijos sprendimus. Daugelis papildytosios realybės sprendimų veikia remiantis vaizdų apdorojimo metodais, norint atpažinti ir sekti žymeklį ar kitus objektus bei atvaizduoti kompiuteriu generuojamą virtualų turinį. Pagrindinė tokių metodų problema – netvarkinga aplinka, apšvietimo sąlygos, todėl objektą atpažinti ir sekti realiuoju laiku tampa sudėtinga arba neįmanoma. Darbe nagrinėjamos mikroelektromechaninių jutiklių naudojimo galimybės ir kvaternionų taikymas jutiklių duomenims, norint patikimai ir tiksliai įvertinti kameros orientaciją erdvėje. Tokiu būdu virtualus turinys atvaizduojamas papildytosios realybės technologijoje, netaikant vaizdų apdorojimo metodų. Reikšminiai žodžiai: mikroelektromechaniniai jutikliai, jutiklių duomenų sujungimas, orientacijos įvertinimas, papildytosios realybės technologija.

This paper surveys the developments of last 10 years in the area of vision based target tracking for autonomous vehicles navigation. First, the motivations and applications of using vision based target tracking for autonomous vehicles navigation are presented in the introduction section. It can be concluded that it is very necessary to develop robust visual target tracking based navigation algorithms for the broad applications of autonomous vehicles. Then this paper reviews the recent techniques in three different categories: vision based target tracking for the applications of land, underwater and aerial vehicles navigation. Next, the increasing trends of using data fusion for visual target tracking based autonomous vehicles navigation are discussed. Through data fusion the tracking performance is improved and becomes more robust. Based on the review, the remaining research challenges are summarized and future research directions are investigated.

Multi-agent systems (MAS) through their intrinsically distributed nature offer a promising software modelling and implementation framework for wireless sensor network (WSN) applications. WSNs are characterised by limited resources from a computational and energy perspective; in addition, the integrity of the WSN coverage area may be compromised over the duration of the network's operational lifetime, as environmental effects amongst others take their toll. Thus a significant problem arises--how can an agent construct an accurate model of the prevailing situation in order that it can make effective decisions about future courses of action within these constraints? In this paper, one popular agent architecture, the BDI architecture, is examined from this perspective. In particular, the fundamental issue of belief generation within WSN constraints using classical reasoning augmented with a fuzzy component in a hybrid fashion is explored in terms of energy-awareness and utility. Science Foundation Ireland

International audience; Proper modeling of dynamic environments is a core task in the field of intelligent vehicles. The most commonapproaches involve the modeling of moving objects, through Detection And Tracking of Moving Objects (DATMO) methods.An alternative to a classic object model framework is the occupancy grid filtering domain. Instead of segmenting the sceneinto objects and track them, the environment is represented as a regular grid of occupancy, in which spatial occupancy istracked at a sub-object level. In this paper, we present the Conditional Monte Carlo Dense Occupancy Tracker, a genericspatial occupancy tracker, which infers dynamics of the scene through an hybrid representation of the environment, consistingof static occupancy, dynamic occupancy, empty spaces and unknown areas. This differentiation enables the use of state specificmodels (classic occupancy grid for motion-less components, set of moving particles for dynamic occupancy) as well as properconfidence estimation and management of data-less areas. The approach leads to a compact model that drastically improves theaccuracy of the results and the global efficiency in comparison to previous methods.

The multi-sensor data fusion technique plays a significant role in fault diagnosis and in a variety of such applications, and the Dempster–Shafer evidence theory is employed to improve the system performance; whereas, it may generate a counter-intuitive result when the pieces of evidence highly conflict with each other. To handle this problem, a novel multi-sensor data fusion approach on the basis of the distance of evidence, belief entropy and fuzzy preference relation analysis is proposed. A function of evidence distance is first leveraged to measure the conflict degree among the pieces of evidence; thus, the support degree can be obtained to represent the reliability of the evidence. Next, the uncertainty of each piece of evidence is measured by means of the belief entropy. Based on the quantitative uncertainty measured above, the fuzzy preference relations are applied to represent the relative credibility preference of the evidence. Afterwards, the support degree of each piece of evidence is adjusted by taking advantage of the relative credibility preference of the evidence that can be utilized to generate an appropriate weight with respect to each piece of evidence. Finally, the modified weights of the evidence are adopted to adjust the bodies of the evidence in the advance of utilizing Dempster’s combination rule. A numerical example and a practical application in fault diagnosis are used as illustrations to demonstrate that the proposal is reasonable and efficient in the management of conflict and fault diagnosis.

Real-time environmental depth perception and ego-motion estimation is essential for all mobile robotic systems. We present a system that computes high quality depth images with 0.5 MPixel resolution using Semi-Global Matching (SGM) and estimates the ego-motion by key frame based visual odometry fused with the data of an inertial measurement unit (IMU). The hardware includes a pair of cameras, a small Intel Core2Duo CPU board, a Spartan 6 FPGA board, an OMAP3530 ARM processor board as well as an IMU. The total weight of the experimental setup is 830 g and is, thus, also feasible for hand-held or flying platforms. Experiments show that the vision system runs at 14.6 Hz with a latency of around 250 ms and produces high quality depth images as well as reliable 6D ego-motion estimates. In the fusion algorithm of visual odometry and IMU data, time delays of the vision system are compensated and a system state estimate is available at the full data rate of the IMU which is important for system control. This paper presents the integration of different techniques into a fast, light weight, real-time system and validates its performance by experiments on real data.

Object detection and tracking is a crucial task as a basis for advanced driver assistance and automation systems. For this purpose a fusion system at object level is proposed, which allows high availability and reliability, since a high independence of the sensors can be reached. In order to deal with common challenges of object detection and tracking, such as maneuvering vehicles, data outliers, partial observability and split and merge effects, a series of novel strategies have been developed. These include the adaptive noise modeling, the definition of an object logical reference, the partial observability modeling, the multiple association of observations, and strategies to duplicate and unify object hypotheses. The proposed fusion system has been prototypically implemented based on a camera and a laser scanner. Furthermore, it has been tested with both simulated and real data. The test results show a win in data quality and robustness, with which an improvement of driver assistance and automation systems can be reached.

Robots operating in complex environments shared with humans are confronted with numerous problems. One important problem is the identification of obstacles and interaction partners. In order to reach this goal, it can be beneficial to use data from multiple available sources, which need to be processed appropriately. Furthermore, such environments are not static. Therefore, the robot needs to learn novel objects. In this paper, we propose a method for learning and identifying obstacles based on multi-modal information. As this approach is based on Adaptive Resonance Theory networks, it is inherently capable of incremental online learning.

In home-based care, reliable contextual information of remotely monitored patients should be generated to recognize activities and to identify hazardous situations of the patient. This is difficult for several reasons. First, low level data obtained from multisensor have different degrees of uncertainty. Second, generated contexts can be conflicting even if they are acquired by simultaneous operations. And last, context reasoning over time is difficult for temporal changes in sensory information. In this paper, we propose the dynamic evidential fusion approach as a context reasoning method in home-based care. The proposed approach processes the generated contexts with Dynamic Evidential Network (DEN), which is composed of the combination of Dezert-Smarandache Theory (DSmT) and Markov Chain (MC). The DSmT reduces ambiguous or conflicting contextual information and the MC processes the association and correlation of sensory information that may change based on time series. Finally, we compare the dynamic evidential fusion approach with the static evidential fusion approach for analyzing the improvement of the dynamic evidential fusion approach.

This paper presents the fusion algorithm for navigation information from three distinct sources: strapdown inertial navigation system (SINS), GPS receiver and astronavigation system (ANS) i.e. for SINS/ANS/GPS integrated navigation system in the presence of nonstationary Gaussian noise. Adaptive innovation-based (maximumlikelihood covariance) Kalman filter is used to estimate errors of SINS position, velocity, attitude, accelerometers, gyroscopes and gravitation acceleration to yield improved integrated navigation solution. Firstorder Gauss-Markov processes are used to simulate time-correlation of SINS and GPS errors. Lagrange polynomials are used to interpolate data from each source of navigation information with different output rates. © 2007 IEEE.

Subjects used the dichoptic combination of a monocular image intensifier (NVG) and a monocular uncooled microbolometer (LWIR) to detect and localise both visual targets and camouflaged thermal targets while moving through a dimly lit complex environment. The NVG imagery enabled the subjects to move freely through the environment with high accuracy, but did not mediate the detection of camouflaged thermal targets. The LWIR mode mediated the detection of camouflaged thermal targets but did not allow the detection of visual targets, and provided insufficient detail to allow accurate movement through the environment. Subjects were quite capable to dichoptically fuse the individual LWIR and NVG images, enabling them to detect all (visual and thermal) targets while moving accurately through the environment. We conclude that dichoptic fusion of NVG and LWIR imagery is quite feasible and is a simple way to provide observers with enhanced situational awareness in nighttime operations.

Date of Conference: 22-28 April 1996 Conference Name: International Conference on Robotics and Automation, IEEE 1996 A novel, flexible, three-dimensional (3-D) multi-sensor sonar system is employed to localize the center of a spherical target and estimate its radius of curvature. The interesting limiting cases for the problem under study are the point and planar targets, both of which are important for the characterization of a mobile robot's environment. A noise model is developed based on real sonar data. An extended Kalman filter (EKF) which incorporates the developed noise model is employed as an estimation tool for optimal processing of the sensor data. Simulations and experimental results are provided for specularly reflecting cylindrical targets.

Date of Conference: 13-17 October 1998 Conference Name: 1998 IEEE/RSJ International Conference on Intelligent Robots and Systems, IEEE 1998 This paper presents a novel method for surface profile determination using multiple sensors. Our approach is based on morphological processing techniques to fuse the range data from multiple sensor returns in a manner that directly reveals the target surface profile. The method has the intrinsic ability of suppressing spurious readings due to noise, crosstalk, and higher-order reflections, as well as processing multiple reflections informatively. The algorithm is verified both by simulations and experiments in the laboratory by processing real sonar data obtained from a mobile robot. The results are compared to those obtained from a more accurate structured-light system, which is however more complex and expensive.

Date of Conference: 20-25 April 1997 Conference Name: International Conference on Robotics and Automation, IEEE 1997 In this study, physical models are used to model reflections from target primitives commonly encountered in a mobile robot's environment. These targets are differentiated by employing a multi-transducer pulse/echo system which relies on both amplitude and time-of-flight data, allowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused by employing multiple logical sonars at different geographical sites. Feature data from multiple logical sensors are fused with Dempster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Dempster-Shafer fusion results are contrasted with the results of combination of sensor beliefs through simple majority vote. The method is verified by experiments with a real sonar system. The evidential approach employed here helps to overcome the vulnerability of the echo amplitude to noise and enables the modeling of non-parametric uncertainty in real time.

Date of Conference: 20-22 Aug. 2001 Conference name: Conference Documentation International Conference on Multisensor Fusion and Integration for Intelligent Systems. MFI 2001 The comparison of different classification and fusion techniques was done for target classification and localization with sonar. Target localization performance of artificial neural networks (ANN) was found to be better than the target differentiation algorithm (TDA) and fusion techniques. The target classification performance of non-parametric approaches was better than that of parameterized density estimator (PDE) using homoscedastic and heteroscedastic NM for statistical pattern recognition techniques.

A novel method is described for surface profile extraction based on morphological processing of multiple range sensor data. The approach taken is extremely flexible and robust, in addition to being simple and straightforward. It can deal with arbitrary numbers and configurations of sensors as well as synthetic arrays. The method has the intrinsic ability to suppl css spurious readings, crosstalk, and higher-order reflections, and process multiple reflections informatively. The performance of the method is investigated by analyzing its dependence on surface structure and distance, sensor beamwidth, and noise on the time-of-flight measurements. (C) 2001 Pattern Recognition Society. Published by Elsevier Science Ltd. All rights reserved.

This study investigates the processing of sonar signals using neural networks for robust differentiation of commonly encountered features in indoor environments. The neural network can differentiate more targets, and achieves high differentiation and localization accuracy, improving on previously reported methods. It achieves this by exploiting the identifying features in the differential amplitude and time-of-flight characteristics of these targets. An important observation follows from the robustness tests, which indicate that the amplitude information is more crucial than time-of-flight for reliable operation. The study suggests wider use of neural networks and amplitude information in sonar-based mobile robotics.

This paper investigates the use of voting as a conflict-resolution technique for data analysis in robot programming. Voting represents an information-abstraction technique. It is argued that in some cases a voting approach is inherent in the nature of the data being analyzed: where multiple, independent sources of information must be reconciled to give a group decision that reflects a single outcome rather than a consensus average. This study considers an example of target classification using sonar sensors. Physical models of reflections from target primitives that are typical of the indoor environment of a mobile robot are used. Dispersed sensors take decisions on target type, which must then be fused to give the single group classification of the presence or absence and type of a target. Dempster-Shafer evidential reasoning is used to assign a level of belief to each sensor decision. The decisions are then fused by two means. Using Dempster’s rule of combination, conflicts are resolved through a group measure expressing dissonance in the sensor views. This evidential approach is contrasted with the resolution of sensor conflict through voting. It is demonstrated that abstraction of the level of belief through voting proves useful in resolving the straightforward conflicts that arise in the classification problem. Conflicts arise where the discriminant data value, an echo amplitude, is most sensitive to noise. Fusion helps to overcome this vulnerability: in Dempster-Shafer reasoning, through the modeling of nonparametric uncertainty and combination of belief values; and in voting, by emphasizing the majority view. The paper gives theoretical and experimental evidence for the use of voting for data abstraction and conflict resolution in areas such as classification, where a strong argument can be made for techniques that emphasize a single outcome rather than an estimated value. Methods for making the vote more strategic are also investigated. The paper addresses the reduction of dimension of sets of decision points or decision makers. Through a consideration of combination order, queuing criteria for more strategic fusion are identified.

This paper reports on the fusion of IR imagery with range data such as obtained from a laser range finder. Both a air/sea, and land based scenario has been studied. The range information is used to calculate a priori scale information for the detection process in the IR images. The use of this scale information leads to substantial improvement of the recognition performance.

Date of Conference: 5-9 August 1995 Conference Name: IEEE/RSJ International Conference on Intelligent Robots and Systems: Human Robot Interaction and Cooperative Robots, IEEE 1995 The performance of a commonly employed linear array of sonar sensors is assessed for point-obstacle localization intended for robotics applications. Two different methods of combining time-of-flight information from the sensors are described to estimate the range and azimuth of the obstacle: pairwise estimate method and the maximum likelihood estimator. The variances of the methods are compared to the Cramer-Rao Lower Bound, and their biases are investigated. Simulation studies indicate that in estimating range, both methods perform comparably; in estimating azimuth, maximum likelihood estimate is superior at a cost of extra computation. The results are useful for target localization in mobile robotics.

We propose an extension of our previous work on spatial domain Time-of-Flight (ToF) data enhancement to the temporal domain. Our goal is to generate enhanced depth maps at the same frame rate of the 2-D camera that, coupled with a ToF camera, constitutes a hybrid ToF multi-camera rig. To that end, we first estimate the motion between consecutive 2-D frames, and then use it to predict their corresponding depth maps. The enhanced depth maps result from the fusion between the recorded 2-D frames and the predicted depth maps by using our previous contribution on ToF data enhancement. The experimental results show that the proposed approach overcomes the ToF camera drawbacks; namely, low resolution in space and time and high level of noise within depth measurements, providing enhanced depth maps at video frame rate. © 2012 IEEE.

Date of Conference: 8-11 December 1996 Conference Name: 1996 IEEE/SICE/RSJ International Conference on Multisensor Fusion and Integration for Intelligent Systems Physical models are used to model reflections from target primitives commonly encountered in mobile robot applications. These targets are differentiated by employing a multi-transducer pulse/echo system which relies on both amplitude and time-of-flight (TOF) data in the feature fusion process, allowing more robust differentiation. Target features are generated as being evidentially tied to degrees of belief which are subsequently fused for multiple logical sonars at different geographical sites. This evidential approach helps to overcome the vulnerability of echo amplitude to noise and enables the modeling of non-parametric uncertainty. Feature data from multiple logical sensors are fused with Dempster-Shafer rule of combination to improve the performance of classification by reducing perception uncertainty. Using three sensing nodes, improvement in differentiation is between 20-40% without false decision, at the cost of additional computation. Simulation results are verified by experiments with a real sonar system. This evidential approach helps to overcome the vulnerability of the echo amplitude to noise and enables the modeling of non-parametric uncertainty in real time.