Download or read book The Control of Mobile Sensing Platforms to Perform Estimation of Mobile Targets written by Xiao Xiao and published by . This book was released on 2008 with total page 326 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Sensor Management for Target Tracking Applications written by Per Boström-Rost and published by Linköping University Electronic Press. This book was released on 2021-04-12 with total page 61 pages. Available in PDF, EPUB and Kindle. Book excerpt: Many practical applications, such as search and rescue operations and environmental monitoring, involve the use of mobile sensor platforms. The workload of the sensor operators is becoming overwhelming, as both the number of sensors and their complexity are increasing. This thesis addresses the problem of automating sensor systems to support the operators. This is often referred to as sensor management. By planning trajectories for the sensor platforms and exploiting sensor characteristics, the accuracy of the resulting state estimates can be improved. The considered sensor management problems are formulated in the framework of stochastic optimal control, where prior knowledge, sensor models, and environment models can be incorporated. The core challenge lies in making decisions based on the predicted utility of future measurements. In the special case of linear Gaussian measurement and motion models, the estimation performance is independent of the actual measurements. This reduces the problem of computing sensing trajectories to a deterministic optimal control problem, for which standard numerical optimization techniques can be applied. A theorem is formulated that makes it possible to reformulate a class of nonconvex optimization problems with matrix-valued variables as convex optimization problems. This theorem is then used to prove that globally optimal sensing trajectories can be computed using off-the-shelf optimization tools. As in many other fields, nonlinearities make sensor management problems more complicated. Two approaches are derived to handle the randomness inherent in the nonlinear problem of tracking a maneuvering target using a mobile range-bearing sensor with limited field of view. The first approach uses deterministic sampling to predict several candidates of future target trajectories that are taken into account when planning the sensing trajectory. This significantly increases the tracking performance compared to a conventional approach that neglects the uncertainty in the future target trajectory. The second approach is a method to find the optimal range between the sensor and the target. Given the size of the sensor's field of view and an assumption of the maximum acceleration of the target, the optimal range is determined as the one that minimizes the tracking error while satisfying a user-defined constraint on the probability of losing track of the target. While optimization for tracking of a single target may be difficult, planning for jointly maintaining track of discovered targets and searching for yet undetected targets is even more challenging. Conventional approaches are typically based on a traditional tracking method with separate handling of undetected targets. Here, it is shown that the Poisson multi-Bernoulli mixture (PMBM) filter provides a theoretical foundation for a unified search and track method, as it not only provides state estimates of discovered targets, but also maintains an explicit representation of where undetected targets may be located. Furthermore, in an effort to decrease the computational complexity, a version of the PMBM filter which uses a grid-based intensity to represent undetected targets is derived.

Download or read book Distributed Tracking and Information drivien Control for Mobile Sensor Networks written by Parisa Jalalkamali and published by . This book was released on 2012 with total page 238 pages. Available in PDF, EPUB and Kindle. Book excerpt: "The main research objective of this thesis is to address distributed target tracking for mobile sensor networks. Based on real-life limitations, we are particularly interested in mobile sensors with Limited Sensing Range (LSR). There are three possible multi-target tracking scenarios for n mobile sensors tracking m targets: i) many sensors tracking few targets n ” m (e.g. tracking high-valued targets), ii) a few sensors track many targets n “ m (e.g. the sensor coverage problem and situational awareness in a crowded airport terminal), and iii) swarms of sensors tracking swarms of targets n,m ” 1 (e.g. selflocalization of autonomous vehicles in intellegent transportation systems). First, we show that all three problems can be posed as coupled distributed estimation and control problems for mobile sensor networks. To tackle this estimation and control problem, we propose a unified theoretical framework in which every mobile agent (or sensor) has a two-fold objective: a) maintaining a safe distance (or minimum separation) from neighboring mobile agents during target tracking and b) enhancing the quality of sensed information collectively by the team of sensors to improve the performance of distributed estimation. In many real-life applications, the quality of sensed data is a function of the proximity to the target. We propose an information-theoretic measure for quality of sensed data by each sensor called the information value as the trace of the Fisher Information Matrix (FIM). This metric of quality of sensed data plays a key role in all of our proposed distributed tracking and control algorithms. We show that objective a) of any mobile agent is fundamentally a "collision-avoidance" (or "separation") objective that is a byproduct of flocking behavior for multi-agent systems [48], while objective b) for LSR-type sensors requires solving an additional control problem to enhance the collective information value of the team of agents. We refer to the latter problem as the information-driven control problem. For distributed tracking on mobile networks, we apply Information Filter and Kalman-Consensus Filter (KCF) as effective algorithms for distributed multi-target tracking on networks. The other problem of interest is the formal stability analysis of the coupled distributed estimation and flocking-based mobility-control and self-deployment algorithms for problems i) and ii). We prove that the error dynamics of the KCF and the structural dynamics of the flock of sensors from a cascade nonlinear system and provide a Lyapunov-based stability analysis of case i). We present additional theoretical results on analysis of information-driven control and tracking algoritjms for problems i) and ii) together with successful experimental results. In addition, we identify the key questions regarding problem iii) that remains the subject of ongoing and future research."

Download or read book Distributed Target Engagement in Large scale Mobile Sensor Networks written by Samaneh Hosseini Semnani and published by . This book was released on 2015 with total page 194 pages. Available in PDF, EPUB and Kindle. Book excerpt: Sensor networks comprise an emerging field of study that is expected to touch many aspects of our life. Research in this area was originally motivated by military applications. Afterward sensor networks have demonstrated tremendous promise in many other applications such as infrastructure security, environment and habitat monitoring, industrial sensing, traffic control, and surveillance applications. One key challenge in large-scale sensor networks is the efficient use of the network's resources to collect information about objects in a given Volume of Interest (VOI). Multi-sensor Multi-target tracking in surveillance applications is an example where the success of the network to track targets in a given volume of interest, efficiently and effectively, hinges significantly on the network's ability to allocate the right set of sensors to the right set of targets so as to achieve optimal performance. This task can be even more complicated if the surveillance application is such that the sensors and targets are expected to be mobile. To ensure timely tracking of targets in a given volume of interest, the surveillance sensor network needs to maintain engagement with all targets in this volume. Thus the network must be able to perform the following real-time tasks: 1) sensor-to-target allocation; 2) target tracking; 3) sensor mobility control and coordination. In this research I propose a combination of the Semi-Flocking algorithm, as a multi-target motion control and coordination approach, and a hierarchical Distributed Constraint Optimization Problem (DCOP) modelling algorithm, as an allocation approach, to tackle target engagement problem in large-scale mobile multi-target multi-sensor surveillance systems. Sensor-to-target allocation is an NP-hard problem. Thus, for sensor networks to succeed in such application, an efficient approach that can tackle this NP-hard problem in real-time is disparately needed. This research work proposes a novel approach to tackle this issue by modelling the problem as a Hierarchical DCOP. Although DCOPs has been proven to be both general and efficient they tend to be computationally expensive, and often intractable for large-scale problems. To address this challenge, this research proposes to divide the sensor-to-target allocation problem into smaller sub-DCOPs with shared constraints, eliminating significant computational and communication costs. Furthermore, a non-binary variable modelling is presented to reduce the number of inter-agent constraints. Target tracking and sensor mobility control and coordination are the other main challenges in these networks. Biologically inspired approaches have recently gained significant attention as a tool to address this issue. These approaches are exemplified by the two well-known algorithms, namely, the Flocking algorithm and the Anti-Flocking algorithm. Generally speaking, although these two biologically inspired algorithms have demonstrated promising performance, they expose deficiencies when it comes to their ability to maintain simultaneous reliable dynamic area coverage and target coverage. To address this challenge, Semi-Flocking, a biologically inspired algorithm that benefits from key characteristics of both the Flocking and Anti-Flocking algorithms, is proposed. The Semi-Flocking algorithm approaches the problem by assigning a small flock of sensors to each target, while at the same time leaving some sensors free to explore the environment. Also, this thesis presents an extension of the Semi-Flocking in which it is combined with a constrained clustering approach to provide better coverage over maneuverable targets. To have a reliable target tracking, another extension of Semi-Flocking algorithm is presented which is a coupled distributed estimation and motion control algorithm. In this extension the Semi-Flocking algorithm is employed for the purpose of a multi-target motion control, and Kalman-Consensus Filter (KCF) for the purpose of motion estimation. Finally, this research will show that the proposed Hierarchical DCOP algorithm can be elegantly combined with the Semi-Flocking algorithm and its extensions to create a coupled control and allocation approach. Several experimental analysis conducted in this research illustrate how the operation of the proposed algorithms outperforms other approaches in terms of incurred computational and communication costs, area coverage, target coverage for both linear and maneuverable targets, target detection time, number of undetected targets and target coverage in noise conditions sensor network. Also it is illustrated that this algorithmic combination can successfully engage multiple sensors to multiple mobile targets such that the number of uncovered targets is minimized and the sensors' mean utilization factor sensor surveillance systems.is maximized.

Download or read book Active Information Gathering Using Distributed Mobile Sensing Networks written by Jun Chen and published by . This book was released on 2021 with total page 179 pages. Available in PDF, EPUB and Kindle. Book excerpt: An autonomous robot system requires robots to actively gather information using sensors in order to make control decisions. Some problems where autonomous robots are useful include mapping, environmental monitoring, and surveillance. In some cases, information gathering turns into a multiple target tracking (MTT) problem. Usually, an MTT tracker is utilized to recursively estimate both the number of targets and the state of each target. In order to estimate more efficiently and reliably, sensors must balance exploiting current knowledge to track known targets while simultaneously exploring to find information about new targets. This yields to the coverage control problem, which is aimed at maximizing the total sensing capability of a sensing network over the entire mission space. Many applications of sensing networks benefit from utilizing distributed manners, in which cases networks are able to be scaled to large swarms and better tolerate failures of individual sensors. A distributed network requires sensors to exchange data locally and cooperate in decision making globally.This dissertation studies MTT based on random finite set (RFS) for iterative target states estimation and Voronoi-based coverage control algorithms for target tracking. We address a series of four main problems aiming at allowing reliable and efficient target tracking for distributed multi-robot systems in complicated real-world scenarios and push forward the realization of robot coordination techniques. Firstly, we propose novel target estimation and coverage control schemes to incorporate robots with localization uncertainty. Secondly, we improve target search efficiency for teams of robot with no prior knowledge of target models or distributions by enabling active search and environment learning. Thirdly, we allow robots with heterogeneous capacities in perception and kinematics to cooperatively search and track in an efficient way. Lastly, we develop an improved MTT tracker to allow estimating semantic object labels over time. The efficacy of the proposed methods has been validated in series of simulations and/or hardware validations.

Download or read book Mechanical Engineering And Control Systems Proceedings Of 2015 International Conference Mecs2015 written by Xiaolong Li and published by World Scientific. This book was released on 2016-01-15 with total page 543 pages. Available in PDF, EPUB and Kindle. Book excerpt: This book consists of 113 selected papers presented at the 2015 International Conference on Mechanical Engineering and Control Systems (MECS2015), which was held in Wuhan, China during January 23-25, 2015. All accepted papers have been subjected to strict peer review by two to four expert referees, and selected based on originality, ability to test ideas and contribution to knowledge.MECS2015 focuses on eight main areas, namely, Mechanical Engineering, Automation, Computer Networks, Signal Processing, Pattern Recognition and Artificial Intelligence, Electrical Engineering, Material Engineering, and System Design. The conference provided an opportunity for researchers to exchange ideas and application experiences, and to establish business or research relations, finding global partners for future collaborations. The conference program was extremely rich, profound and featured high-impact presentations of selected papers and additional late-breaking contributions.

Download or read book Information theoretic Control for Mobile Sensor Teams written by Allison Denise Ryan and published by . This book was released on 2008 with total page 336 pages. Available in PDF, EPUB and Kindle. Book excerpt:

Download or read book Springer Handbook of Robotics written by Bruno Siciliano and published by Springer. This book was released on 2016-07-27 with total page 2259 pages. Available in PDF, EPUB and Kindle. Book excerpt: The second edition of this handbook provides a state-of-the-art overview on the various aspects in the rapidly developing field of robotics. Reaching for the human frontier, robotics is vigorously engaged in the growing challenges of new emerging domains. Interacting, exploring, and working with humans, the new generation of robots will increasingly touch people and their lives. The credible prospect of practical robots among humans is the result of the scientific endeavour of a half a century of robotic developments that established robotics as a modern scientific discipline. The ongoing vibrant expansion and strong growth of the field during the last decade has fueled this second edition of the Springer Handbook of Robotics. The first edition of the handbook soon became a landmark in robotics publishing and won the American Association of Publishers PROSE Award for Excellence in Physical Sciences & Mathematics as well as the organization’s Award for Engineering & Technology. The second edition of the handbook, edited by two internationally renowned scientists with the support of an outstanding team of seven part editors and more than 200 authors, continues to be an authoritative reference for robotics researchers, newcomers to the field, and scholars from related disciplines. The contents have been restructured to achieve four main objectives: the enlargement of foundational topics for robotics, the enlightenment of design of various types of robotic systems, the extension of the treatment on robots moving in the environment, and the enrichment of advanced robotics applications. Further to an extensive update, fifteen new chapters have been introduced on emerging topics, and a new generation of authors have joined the handbook’s team. A novel addition to the second edition is a comprehensive collection of multimedia references to more than 700 videos, which bring valuable insight into the contents. The videos can be viewed directly augmented into the text with a smartphone or tablet using a unique and specially designed app. Springer Handbook of Robotics Multimedia Extension Portal: http://handbookofrobotics.org/

Download or read book Coverage Control in Sensor Networks written by Bang Wang and published by Springer Science & Business Media. This book was released on 2010-01-11 with total page 214 pages. Available in PDF, EPUB and Kindle. Book excerpt: The advances in sensor design have decreased the size, weight, and cost of sensors by orders of magnitude, yet with the increase of higher spatial and temporal re- lution and accuracy. With the fast progress of sensors design and communications technique, sensor networks have also been quickly evolving in both research and practical domains in the last decade. More and more sensor networks have been - ployed in real-world to gather information for our daily life. Applications of sensor networks can be found in battle?eld surveillance, environmental monitoring, b- logical detection, smart spaces, industrial diagnostics, etc. Although the technique of sensor networks has a very promising future, many challenges are still deserving lots of research efforts for its successful applications. Thisbookisdevotedtocoveragecontrol,oneofthemostfundamentalandimportant research issues in sensor networks. The aim of the book is to provide tutorial-like and up-to-date reference resources on various coverage control problems in sensor networks, a hot topic that has been intensively researched in recent years. Due to some unique characteristics of sensor networks such as energy constraint and - hoc topology, the coverage problems in sensor networks have many new scenarios and features that entitle them an important research issue in recent years. I have done my best to include in the book the most recent advances, techniques, protocols, results, and ?ndings in this ?eld.

Download or read book Mobile Sensors Environmental Assessment written by and published by . This book was released on 2005 with total page 275 pages. Available in PDF, EPUB and Kindle. Book excerpt: The Missile Defense Agency (MDA) prepared this Environmental Assessment (EA) to evaluate the potential environmental impacts of the use of mobile sensors (i.e., radar, telemetry, command and control, and optical systems) from land-based platforms and the use of airborne sensor systems. The use of mobile sensors from sea-based platforms was analyzed in the Mobile Launch Platform Environmental Assessment (Missile Defense Agency [MDA], 2004). This EA considers impacts associated with the proposed use of land-based mobile sensors and airborne sensor systems on targets of opportunity. Where appropriate this EA also considers environmental impacts from specific tests identified by the MDA that are proposed to use land-based mobile sensors and airborne sensor systems. Finally, the EA addresses cumulative impacts associated with test events using mobile sensors from land-based platforms and airborne sensor systems. The purpose of the proposed action is to provide increasingly robust and comprehensive realistic test surveillance and tracking data capabilities in support of the MDA's mission to implement an integrated and effective Ballistic Missile Defense System (BMDS). As BMDS capabilities advance, testing events becomes increasingly complex. Sensors are needed at additional locations to capture data from these events. Mobile land- and airbased sensors provide a more versatile and cost effective method for meeting this requirement than construction of fixed assets at required locations. The proposed action requires the transport, set-up, and operation of mobile land-based sensors (i.e., radar, telemetry, command and control, and optical systems) from land-based platforms and setup and operation of airborne sensor systems.

Download or read book Robotics written by Yoky Matsuoka and published by MIT Press. This book was released on 2011-08-05 with total page 341 pages. Available in PDF, EPUB and Kindle. Book excerpt: Papers from a flagship robotics conference that cover topics ranging from kinematics to human-robot interaction and robot perception. Robotics: Science and Systems VI spans a wide spectrum of robotics, bringing together researchers working on the foundations of robotics, robotics applications, and the analysis of robotics systems. This volume presents the proceedings of the sixth Robotics: Science and Systems conference, held in 2010 at the University of Zaragoza, Spain. The papers presented cover a wide range of topics in robotics, spanning mechanisms, kinematics, dynamics and control, human-robot interaction and human-centered systems, distributed systems, mobile systems and mobility, manipulation, field robotics, medical robotics, biological robotics, robot perception, and estimation and learning in robotic systems. The conference and its proceedings reflect not only the tremendous growth of robotics as a discipline but also the desire in the robotics community for a flagship event at which the best of the research in the field can be presented.

Download or read book Networked Filtering and Fusion in Wireless Sensor Networks written by Magdi S. Mahmoud and published by CRC Press. This book was released on 2014-12-20 with total page 576 pages. Available in PDF, EPUB and Kindle. Book excerpt: By exploiting the synergies among available data, information fusion can reduce data traffic, filter noisy measurements, and make predictions and inferences about a monitored entity. Networked Filtering and Fusion in Wireless Sensor Networks introduces the subject of multi-sensor fusion as the method of choice for implementing distributed systems.T

Download or read book Mobile Sensor Systems for Field Estimation and hot Spot Identification written by Sumeet Kumar (Ph. D.) and published by . This book was released on 2014 with total page 166 pages. Available in PDF, EPUB and Kindle. Book excerpt: Robust, low-cost mobile sensing enables effective monitoring and management of urban environment and infrastructure which contributes towards a sustainable future. While mobile sensor systems have attracted significant attention in recent years, a large scale deployment for urban infrastructure monitoring poses many research challenges. One fundamental challenge is dealing with noisy and uncontrolled samples stemming from both noisy sensor measurements and locations, and lack of control on sensor deployment. Such conditions pose difficulties in field estimation and "hot spot" identification from sensor data. My thesis contributions aim to bridge this gap. In this thesis, I designed and developed a mobile sensor system for urban light infrastructure monitoring and studied two problems on field estimation in the presence of noisy and uncontrolled samples with general implications on mobile sensing. As an example system, I designed and successfully tested a city-wide street light scanning mobile sensor platform. Currently, street light maintenance uses labor-intensive, poorly scalable manual inspection techniques. My system automatically maps street illumination levels and lamp infrastructure. The collected data presents challenges in identifying lamp "hot spots" from false positives and using sensor data from noisy sensor locations for estimating luminosity maps. I present an algorithm for identifying various light sources from video streams and combining that data with location information to geotag lamps. To identity the light sources, I developed a supervised classifier for lamp classification and later extended it to develop a method for estimating the height of the street lamps. As accurate car location information is critical for successful luminosity mapping, I discuss how I improved car location estimates by integrating multiple independent data streams such as vehicle speed data obtained via on-board diagnostic systems and GPS. Towards such field deployments, one must address fundamental challenges related to both hardware implementation and data analytics. In this thesis, I addressed two problems related to mobile sensor based sampling and signal estimation: nonuniform sampling and errors in sample location. Uniform grid sampling is often impractical in the context of mobile spatial sampling. As an alternative, I studied [delta]-dense sensor arrangements as a realistic scheme for non-uniform flexible sampling. To assess its utility, I derived sufficient conditions for estimating a signal represented in a finite-dimensional basis set and present simulation results on the numerical stability of signal estimation under [delta]-dense sampling. Furthermore, I present the use of proper orthogonal decomposition as a technique to obtain basis sets for signals that are solutions to a parametric differential equation. Finally, I studied how errors in the location measurements of mobile nodes affect the overall signal estimation problem. To address such signal estimation problems, I developed a computationally efficient iterative linear estimator and compared my approach to the state of the art expectation-maximization technique. I present simulation studies on the performance of the estimator and discuss results on its numerical stability. My approach offers several orders of magnitude reduction in computational time while achieving comparable mean squared estimation error to other techniques making it an appealing candidate for real-time embedded mobile sensing applications.

Download or read book Experimental Robotics written by Jaydev P. Desai and published by Springer. This book was released on 2013-07-09 with total page 966 pages. Available in PDF, EPUB and Kindle. Book excerpt: The International Symposium on Experimental Robotics (ISER) is a series of bi-annual meetings, which are organized, in a rotating fashion around North America, Europe and Asia/Oceania. The goal of ISER is to provide a forum for research in robotics that focuses on novelty of theoretical contributions validated by experimental results. The meetings are conceived to bring together, in a small group setting, researchers from around the world who are in the forefront of experimental robotics research. This unique reference presents the latest advances across the various fields of robotics, with ideas that are not only conceived conceptually but also explored experimentally. It collects robotics contributions on the current developments and new directions in the field of experimental robotics, which are based on the papers presented at the 13the ISER held in Québec City, Canada, at the Fairmont Le Château Frontenac, on June 18-21, 2012. This present thirteenth edition of Experimental Robotics edited by Jaydev P. Desai, Gregory Dudek, Oussama Khatib, and Vijay Kumar offers a collection of a broad range of topics in field and human-centered robotics.

Download or read book A Self organizing Hybrid Sensor System with Distributed Data Fusion for Intruder Tracking and Surveillance written by Ravishankar Palaniappan and published by . This book was released on 2010 with total page 109 pages. Available in PDF, EPUB and Kindle. Book excerpt: A wireless sensor network is a network of distributed nodes each equipped with its own sensors, computational resources and transceivers. These sensors are designed to be able to sense specific phenomenon over a large geographic area and communicate this information to the user. Most sensor networks are designed to be stand-alone systems that can operate without user intervention for long periods of time. While the use of wireless sensor networks have been demonstrated in various military and commercial applications, their full potential has not been realized primarily due to the lack of efficient methods to self organize and cover the entire area of interest. Techniques currently available focus solely on homogeneous wireless sensor networks either in terms of static networks or mobile networks and suffers from device specific inadequacies such as lack of coverage, power and fault tolerance. Failing nodes result in coverage loss and breakage in communication connectivity and hence there is a pressing need for a fault tolerant system to allow replacing of the failed nodes. In this dissertation, a unique hybrid sensor network is demonstrated that includes a host of mobile sensor platforms. It is shown that the coverage area of the static sensor network can be improved by self-organizing the mobile sensor platforms to allow interaction with the static sensor nodes and thereby increase the coverage area. The performance of the hybrid sensor network is analyzed for a set of N mobile sensors to determine and optimize parameters such as the position of the mobile nodes for maximum coverage of the sensing area without loss of signal between the mobile sensors, static nodes and the central control station. A novel approach to tracking dynamic targets is also presented. Unlike other tracking methods that are based on computationally complex methods, the strategy adopted in this work is based on a computationally simple but effective technique of received signal strength indicator measurements. The algorithms developed in this dissertation are based on a number of reasonable assumptions that are easily verified in a densely distributed sensor network and require simple computations that efficiently tracks the target in the sensor field. False alarm rate, probability of detection and latency are computed and compared with other published techniques. The performance analysis of the tracking system is done on an experimental testbed and also through simulation and the improvement in accuracy over other methods is demonstrated.

Download or read book Development and Implementation of Low Cost Mobile Sensor Platforms Within a Wireless Sensor Network written by Michael Jay Tozzi and published by . This book was released on 2010 with total page 61 pages. Available in PDF, EPUB and Kindle. Book excerpt: Sensor networks are used throughout the government and industry for a wide variety of purposes. Mobile Sensor Platforms (MSPs), from surface combatant vessels to unmanned aerial vehicles, have been integrated into these sensor networks since their inception. Unmanned MSPs currently used in sensor networks have two major drawbacks: They are extremely expensive and they require the control of a human operator. Remote controlled unmanned systems currently do not eliminate risk to personnel entirely, because they are typically too expensive to be considered expendable. If these standard unmanned systems are downed in a hostile environment, their recovery is often attempted by personnel on the ground; thus, still risking human lives. The military is exploring the use of low-cost unmanned MSPs to eliminate the need to risk personnel in their recovery. One of the greatest expenses in the life cycle of any system is operator cost. To reduce or eliminate operator cost, a platform must be autonomous. Though algorithms exist for adding autonomous capabilities to a mobile platform, such algorithms are typically designed for robust systems with a great deal of processing power. Low-cost systems are typically limited in capability by a low-processing power CPU. For this reason, small footprint alternatives to existing autonomous control algorithms must be developed to truly implement a low-cost MSP. This thesis applies the systems engineering process to developing a generic system solution for the need of a low-cost MSP, with concept of operations, external systems diagram, generic requirements, functional architecture and decompositions developed. The proposed generic system solution is then further designed in a scoped environment and implemented as a proof of concept prototype.

Download or read book Towards Low cost and Real time Mobile Sensing written by Hao Li and published by . This book was released on 2021 with total page 103 pages. Available in PDF, EPUB and Kindle. Book excerpt: With the increasing popularity of sensor-equipped smartphones, mobile sensing nowadays emerges as a promising direction. Mobile sensing applications analyze the collected signal data from the surroundings and thus understand the physical environment. Various applications have been developed through this new paradigm,such as mobile location estimation, audio recognition, and augmented reality. However, many practical issues need to be addressed when deploying mobile sensing applications in real-world scenarios. In this thesis, we investigate three practical problems related to mobile sensing applications and design customized frameworks and methods to provide low-cost and real-time mobile sensing services, particularly in the area of mobile location sensing. First, we investigate the high data collection cost problem in WiFi fingerprint-based mobile location sensing. We propose a general framework with a low-cost offline data collection while maintaining high localization accuracy. In particular, we reduce the number of reference points to obtain a sparse fingerprint. Our framework adopts the clustering method to reduce the adverse effects when applying regression-based approaches on the sparse fingerprint. The proposed framework can provide high localization accuracy through extensive experiments on the campus. Second, we study the heterogeneous mobile devices problem in passive mobile location sensing systems. We propose a customized localization approach that auto-matically infers a signal-strength-to-distance function for every device on the fly and simultaneously estimates its location with the Expectation-Maximization algorithm. A real-world pilot test at an exhibition center is conducted, and heterogeneous mobile devices can be localized and tracked accurately. Third, we present a mobile deep learning inference framework to schedule multiple DNN jobs with real-time requirements for deep mobile sensing tasks. Considering characteristics of DNN workloads and mobile hardware, we design the framework with mobile GPU/CPU collaboration by DNN partitioning and CPU offloading. The proposed framework can better utilize all computational resources on mobile phones. We evaluate our system on the mobile platform by extending Tensor Flow Lite. The evaluation results indicate that our framework can support real-time deep mobile sensing tasks.