Adaptive Tracking System Research Articles

Adaptive tracking control of nonlinear systems with unknown time‐varying parameters via a monotonically increasing function

AbstractThis article considers the adaptive tracking control problem of a class of strict feedback nonlinear systems with unknown time‐varying parameters. Note that the recent adaptive method, that is, congelation of variables, is built upon the assumption that the known basis functions are zeros as zero states. To remove this assumption, a novel monotonically increasing function is designed to transform the output tracking error and the backstepping tracking errors into increasing forms, which is integrated into the congelation of variables to design the ‐modification adaptive tracking control law. It is noted that the proposed form of monotonically increasing function is general, which includes positive proportional functions, exponential functions, and logarithmic functions and so on. To yield the boundedness of increasing tracking errors, a barrier Lyapunov function is designed. The asymptotic convergence of the resulting adaptive tracking system is analyzed in detail. Simulations demonstrate the effectiveness of the proposed method.

Adaptive path planning and tracking system based on model predictive control for autonomous vehicle local obstacle avoidance

AbstractPath planning and tracking control are the key technologies of autonomous vehicle. The planned path and tracking results affect driving stability and safety directly. In this paper, an improved local path planning method based on model predictive control is proposed to match the variation of vehicle speed and road adhesion coefficient. A two‐layer model predictive control (MPC) path planning and tracking system is further designed to validate the method and the simulation results show that the proposed solution solves the problem of excessive avoidance and reduces the lateral deviation with the reference path.

A horizontal single-axis tracking bracket with an adjustable tilt angle and its adaptive real-time tracking system for bifacial PV modules

An efficient photovoltaic (PV) tracking system enables solar cells to produce more energy. However, commonly-used PV tracking systems experience the following limitations: (ⅰ) they are mainly applied to single-sided PV panels; (ⅱ) they employ conventional astronomical algorithms that cannot adjust the tracking path in real time according to variable weather. In this study, a model of horizontal single-axis tracking bracket with an adjustable tilt angle (HSATBATA) is developed, and the irradiance model of moving bifacial PV modules is designed, which considers the mounting height, spacing and ground shading of PV panels. Furthermore, an adaptive real-time tracking (ARTT) algorithm is put forward to obtain the optimal tracking path for PV cells, which considers the energy consumption of tracking motors, the front and back irradiance of solar cells, cell temperature and ambient wind speed. The test results indicate that the presented ARTT algorithm enhances the energy of PV modules by 32.7 % and 7.5 %, respectively, compared to the fixed bracket and the conventional tracking algorithm. Additionally, the number of motor starts of the PV tracking system is reduced by 71.7 % compared with that of the conventional algorithm, which greatly contributes to extending the service life of PV tracking brackets and lowering the cost of electricity. Present study will help to improve the theoretical research system of PV tracking bracket construction, irradiance modeling of moving bifacial modules, and intelligent tracking algorithms.

Quantized-state-based decentralized neural network control of a class of uncertain interconnected nonlinear systems with input and interaction time delays

This paper presents a quantized-state-based decentralized control strategy for uncertain interconnected nonlinear systems with time-varying delays under a networked control environment. Full state variables quantized via a uniform-hysteretic quantizer are available only for a decentralized adaptive control design. Unlike the existing decentralized adaptive recursive control designs, this study is focused on establishing a quantized-state-based decentralized learning mechanism for neural networks using discontinuously quantized states. Moreover, the stability of a decentralized neural network tracking system in the presence of time delays is analyzed. For each subsystem, a neural-network-based local adaptive tracker using a delay compensator is designed based on the local quantized state feedback. Technical lemmas pertaining to quantization errors and adaptive laws are presented to ensure the boundedness of all closed-loop signals and the convergence of local tracking errors to an adjustable neighborhood of the origin. Finally, illustrative simulations clarify and verify the decentralization strategy of the developed state-quantized adaptive tracking system. The control performance is evaluated using the root mean square control errors, where the values are 0.0293 and 0.0134 for each subsystem in Example 1 and 0.0467 and 0.0384 for each subsystem in Example 2.

An Adaptive Gaze Tracking System in the Diverse Environment

For understanding the learning effect, the gaze tracking is a more objective method to collect the data on eye movement and used to analyze the learning behaviors. In order to provide an analysis tool to apply in diverse environments, an adaptive gaze tracking system is proposed in this paper. This system can offer helpful suggestions for educators when improving the instruction. Additionally, the experimental results show that the estimation of gaze points was successful even when the distance and head rotation alter.

Assessment of Clonotypic Rearrangements and Minimal Residual Disease in Lymphoid Malignancies.

Measurable (minimal) residual disease (MRD) is an independent prognostic factor for survival outcomes in patients with lymphoid and plasma cell malignancies and has been incorporated into consensus criteria regarding treatment response, strategy, and clinical trial endpoints. clonoSEQ (a next-generation sequencing [NGS]-MRD assay) uses multiplex polymerase chain reaction and NGS to identify clonotypic rearrangements at the immunoglobulin (Ig) H, IgK, IgL, T-cell receptor (TCR)-β, and TCR-γ loci, as well as translocated B-cell lymphoma 1/IgH and 2/IgH sequences for MRD assessment. Additionally, it can be used to confirm diagnoses of cutaneous T-cell lymphoma (CTCL). To review the technical aspects of our experience using the clonoSEQ Assay in routine clinical practice. In this single-center experience, 390 patients with lymphoid and plasma cell malignancies were assessed with the NGS-MRD Assay at a central laboratory. Median time from arrival of the shipment to initiation of the assay (defined as captured in Adaptive's secure tracking system) was 2.1 hours. Overall, 317 patients had 1 or more samples submitted for sequence identification. Of these, 290 (91.5%) had trackable sequences identified. The median calibration rate of samples by malignancy (where n ≥ 10 samples, excluding CTCL samples) was 88.1%, across a variety of fresh and archived sample sources (177 of 201 samples). TCR-β and/or TCR-γ clonotypes were identified in 40 of 95 samples (42.1%) from 66 patients with suspected CTCL. This NGS-MRD Assay is a valuable and sensitive tool for monitoring MRD in patients with plasma cell and lymphoid malignancies and assisting in the diagnosis of CTCL.

Adaptive trajectory tracking control for remotely operated vehicles considering thruster dynamics and saturation constraints

This paper discusses the problem of adaptive trajectory tracking control for remotely operated vehicles (ROVs). Considering thruster dynamics, a third-order state space equation is used to describe the dynamic model of ROVs. For the problem of unknown dynamics and partially known input gain, an adaptive sliding mode control design scheme based on RBF neural networks is developed using a backstepping design technique. Because of the saturation constraints of the thrusters, a first-order auxiliary state system is applied, and subsequently, a saturation factor is constructed for designing adaptive laws to ensure the stability of the adaptive trajectory tracking system when the thrusters are saturated. The proposed controller guaranteed that trajectory tracking errors are uniformly ultimately bounded (UUD). Finally, the effectiveness of the proposed controller is verified by simulations.

Natural Human–Robot Interface Using Adaptive Tracking System with the Unscented Kalman Filter

Traditional human–robot interfaces usually have limitations in accuracy and/or operational space. This article proposes a natural human–robot interface using an adaptive tracking method, which can effectively expand the operational space while ensuring high accuracy. The natural interface allows the robot to directly reproduce the user's hand movement, making the interaction more intuitive and natural. The leap motion is fixed on the Cartesian platform to capture the movement of the user's hand. Because the Cartesian platform follows the hand and keeps the hand in the center of the detection area, the measurement accuracy is improved and the measurement space can be extended. During the process of acquiring gesture data, the measurement errors were found to increase over time because of the inherent noise of the sensor. To deal with this problem, the unscented Kalman filter is applied to estimate the position of the hand. Moreover, an adaptive velocity control method is proposed to improve the operation accuracy and reduce the task execution time with the consideration of users’ habits and easiness of usage. The effectiveness of this interface is verified by a series of experiments, and the results show that the proposed interface can be used by nonprofessional users for object operation tasks and can provide users with superior interactive experiences.

Toward Scalable and Robust Indoor Tracking: Design, Implementation, and Evaluation

Although indoor localization has been studied over a decade, it is still challenging to enable many IoT applications, such as activity tracking and monitoring in smart home and customer navigation and trajectory mining in smart shopping mall, which typically require meter-level localization accuracy in a highly dynamic and large-scale indoor environment. Therefore, this article aims at designing and implementing an adaptive and scalable indoor tracking system in a cost-effective way. First, we propose a zero site-survey overhead (ZSSO) algorithm to enhance the system scalability. It integrates the step information and map constraints to infer user’s positions based on the particle filter and supports the auto labeling of scanned Wi-Fi signal for constructing the fingerprint database without the extra site-survey overhead. Further, we propose an iterative-weight-update (IWU) strategy for ZSSO to enhance system robustness and make it more adaptive to the dynamic changing of environments. Specifically, a two-step clustering mechanism is proposed to delete outliers in the fingerprint database and alleviate the mismatch between the auto-tagged coordinates and the corresponding signal features. Then, an iterative fingerprint update mechanism is designed to continuously evaluate the Wi-Fi fingerprint localization results during online tracking, which will further refine the fingerprint database. Finally, we implement the indoor tracking system in real-world environments and conduct a comprehensive performance evaluation. The field testing results conclusively demonstrate the scalability and effectiveness of the proposed algorithms.

Dynamic simulation of the adaptive sun tracking system used for an electric unmanned ground vehicle

In this article, the modeling and simulation of the adaptive sun tracking system used for an electric unmanned ground vehicle is carried out. The power supply of the vehicle is an electric one, supported by a photovoltaic (PV) panel with solar tracker, which is positioned on the upper platform of the vehicle (practically, the tracking system thus defined is one with mobile base). The main feature of the adaptive tracking mechanism consists in its ability to correlate the predefined tracking law (which it is designed as system would be one with fixed base) with the random movement of the vehicle. The mechatronic model contains both mechanical and electronic (control) elements, being conceived and analyzed in virtual prototyping environment by using the MBS software package ADAMS.

Dynamic simulation of the adaptive sun tracking system used for an electric unmanned ground vehicle

Dynamic simulation of the adaptive sun tracking system used for an electric unmanned ground vehicle

Adaptive tracking of people and vehicles using mobile platforms

Tracking algorithms have important applications in detection of humans and vehicles for border security and other areas. For large-scale deployment of such algorithms, it is critical to provide methods for their cost- and energy-efficient realization. To this end, commodity mobile devices have significant potential for use as prototyping and testing platforms due to their low cost, widespread availability, and integration of advanced communications, sensing, and processing features. Prototypes developed on mobile platforms can be tested, fine-tuned, and demonstrated in the field and then provide reference implementations for application-specific disposable sensor node implementations that are targeted for deployment. In this paper, we develop a novel, adaptive tracking system that is optimized for energy-efficient, real-time operation on off-the-shelf mobile platforms. Our tracking system applies principles of dynamic data-driven application systems (DDDAS) to periodically monitor system operating characteristics and apply these measurements to dynamically adapt the specific classifier configurations that the system employs. Our resulting adaptive approach enables powerful optimization of trade-offs among energy consumption, real-time performance, and tracking accuracy based on time-varying changes in operational characteristics. Through experiments employing an Android-based tablet platform, we demonstrate the efficiency of our proposed tracking system design for multimode detection of human and vehicle targets.

Design Algorithm of Moving Target Adaptive Tracking System

According to the characteristics of the moving target state information, we propose a multi-mode adaptive CamShift algorithm (MACA), and using the adaptive algorithm designed a real-time tracking system. The large number of experiments show that the algorithm robustness, real-time, high degree of system automation.

Adaptive Topic Tracking Research Based on Title Semantic Domain and Double-state Mode

Aiming at problems of sparse training corpora and topic excursion existing in topic detection and tracking, this paper examines twenty one most recent references and patents, proposes an adaptive topic tracking strategy based on title semantic domain topic model and double-state model. Title semantic domain topic model can enhance the title-centric semantic domain cohesion of reports, and reduce dimensions of reports' feature space effectively. The double-state strat- egy is a tracking technology based on the combination of static model and dynamic model: static model uses a given number of training reports to construct topic model which is the basis of topic tracking; dynamic model uses the sliding text window mechanism to capture new contents of a topic, remove outdated ones and reflect the changes of topic's focus in a timely manner. Experimental results show that the combination of double-state model tracking strategy and title se- mantic domain topic model can improve the performance of adaptive topic tracking system.

B108 内部ループPFC導入によるクアッドロータの適応軌道追従制御系設計(OS1 適応学習制御とその応用2)

In this paper, we deal with an adaptive trajectory tracking control system design scheme for a quadrotor. ASPR based high gain adaptive output feedback strategy will be applied to design a trajectory tracking control of a quadrotor by introducing an inner-loop PFC so as to guarantee the ASPRness of the quadrotor. The proposed method can design a relatively simple controller by introducing a PFC for a quadrotor inner-loop model. The stability of the obtained adaptive tracking system will also be analyzed and the effectiveness of the proposed method will be confirmed through numerical simulations.

Adaptive motion/force control strategy for non-holonomic mobile manipulator robot using recurrent fuzzy wavelet neural networks

In our study, we develop an adaptive position tracking system and a force control strategy for non-holonomic mobile manipulator robot, which combine the merits of Recurrent Fuzzy Wavelet Neural Networks (RFWNNs). In order to deal with the unknown knowledge problems of the robotic system, an adaptive RFWNNs control scheme with the dynamic structure and online learning ability is utilized to approximate unknown dynamics without the requirement of prior controlled system information. In addition, an adaptive robust compensator is proposed to eliminate uncertainties that consist of approximation errors, disturbances. According to the adaptive position tracking control design, an adaptive robust controller is also considered for the non-holonomic constraint force. The design of the adaptive online learning algorithms is derived by using the Lyapunov stability theorem. Therefore, the proposed controllers prove that they not only can guarantee the stability but also the tracking performance of the mobile manipulator robot control system. The effectiveness and robustness of the proposed method are demonstrated by comparative simulation and experimental results that are implemented in an indoor cleaning crawler-type mobile manipulator robot system.

Adaptive Position Tracking System and Force Control Strategy for Mobile Robot Manipulators Using Fuzzy Wavelet Neural Networks

In this paper, we propose an adaptive position tracking system and a force control strategy for nonholonomic mobile robot manipulators, which incorporate the merits of Fuzzy Wavelet Neural Networks (FWNNs). In general, it is not easy to adopt a model-based method to achieve this control object due to the uncertainties of mobile robot manipulators control system, such as unknown dynamics, disturbances and parameter variations. To solve this problem, an adaptive FWNNs control scheme with the online learning ability is utilized to approximate the unknown dynamics without the requirement of prior system information. In addition, an adaptive robust compensator is proposed to eliminate uncertainties that consist of approximation errors, disturbances, optimal parameters and higher order terms in Taylor series. According to adaptive position tracking control design, an adaptive robust control strategy is also considered for nonholonomic constraint force. The design of adaptive online learning algorithms is derived using Lyapunov stability theorem. Therefore, the proposed controllers prove that they not only can guarantee the stability of mobile robot manipulators control system but also guarantee tracking performance. The effectiveness and robustness of the proposed method are demonstrated by comparing simulations and experimental results that are implemented in an indoor cleaning crawler-type mobile robot manipulators system.

2B37 Adaptive Control System Design of a Quadrotor by High Gain Based Feedback Control via Backstepping Strategy with an Inner-Loop PFC(The 12th International Conference on Motion and Vibration Control)

This paper deals with a control system design problem for a quadrotor with unknown parameters. An adaptive trajectory tracking control of quadrotor with an ASPR based high gain feedback strategy and adaptive method will be proposed by combining the backstepping strategy. In the proposed method, by introducing a parallel feedforward compensator (PFC) in the inner loop of the quadrotor control system, one can design a relatively simple controller compared with the method which directly applying backstepping strategy. The stability of the obtained adaptive tracking system will also be analyzed and the effectiveness of the proposed method will be confirmed through numerical simulations.

A Low-Cost Mobile Adaptive Tracking System for Chronic Pulmonary Patients in Home Environment

The main objective of this study is presenting a real-time mobile adaptive tracking system for patients diagnosed with diseases such as asthma or chronic obstructive pulmonary disease and application results at home. The main role of the system is to support and track chronic pulmonary patients in real time who are comfortable in their home environment. It is not intended to replace the doctor, regular treatment, and diagnosis. In this study, the Java 2 micro edition-based system is integrated with portable spirometry, smartphone, extensible markup language-based Web services, Web server, and Web pages for visualizing pulmonary function test results. The Bluetooth(®) (Bluetooth SIG, Kirkland, WA) virtual serial port protocol is used to obtain the test results from spirometry. General packet radio service, wireless local area network, or third-generation-based wireless networks are used to send the test results from a smartphone to the remote database. The system provides real-time classification of test results with the back propagation artificial neural network algorithm on a mobile smartphone. It also provides the generation of appropriate short message service-based notification and sending of all data to the Web server. In this study, the test results of 486 patients, obtained from Atatürk Chest Diseases and Thoracic Surgery Training and Research Hospital in Ankara, Turkey, are used as the training and test set in the algorithm. The algorithm has 98.7% accuracy, 97.83% specificity, 97.63% sensitivity, and 0.946 correlation values. The results show that the system is cheap (900 Euros) and reliable. The developed real-time system provides improvement in classification accuracy and facilitates tracking of chronic pulmonary patients.

Online Appearance Model Learning and Generation for Adaptive Visual Tracking

Several adaptive visual tracking algorithms have been recently proposed to capture the varying appearance of target. However, adaptability may also result in the problem of gradual drift, especially when the target appearance changes drastically. This paper gives some theoretical principles for online learning of target model, and then presents a novel adaptive tracking algorithm which is able to effectively cope with drastic variations in target appearance and resist gradual drift. Once target is localized in each frame, the patches sampled from target observation are first classified into foreground and background using an effective classifier. Then the adaptive, pure and time-continuous target model is extracted online through two processes: absorption process and rejection process, through which only the reliable features with high separability are absorbed in the new target model, while the “dangerous” features which may cause interfusion of background patterns are rejected. To minimize the influence of background and keep the temporal continuity of target model, two collaborative models dominant model and continuous model are designed. The proposed learning and generation mechanisms of target model are finally embedded in an adaptive tracking system. Experimental results demonstrate the robust performance of the proposed algorithm under challenging conditions.