Precise Tracking Research Articles

A standardized protocol for assessing the performance of automatic detection systems used in onshore wind power plants to reduce avian mortality

While wind power plants are an important contribution to the production of renewable energy to limit climate change, collision mortality from turbines is a danger for birds, including many protected species. To try to mitigate collision risks, automatic detection systems (ADSs) can be deployed on wind power plants; these work by detecting incoming birds using a detection/classification process and triggering a specific reaction (scaring off the bird or shutting down the turbine). Nonetheless, bird fatalities still occur at ADS-equipped wind power plants, which raises the question of the performance of these tools. To date, the lack of a transparent, peer-reviewed experimental process to compare the performance of types of ADS has meant there is no robust protocol to assess these systems.With the aim of filling this gap, we developed two standardized protocols that provide objective and unbiased assessments of the performance of different types of ADS, based on their probability of detecting/classifying birds at risk of collision. Both protocols rely on precise 3D tracking of wild birds by human observers using a laser rangefinder, and the comparison of these tracks with those detected and recorded by an ADS. The first protocol evaluates a system's general performance, generating comparable data for all types of ADS. In this protocol, detection/classification probability is estimated conditional on several abiotic and biotic environmental factors such as bird size, distance from the target, the flight angle and azimuth of the bird, as well as weather conditions. The second protocol aims to verify that the performance of an ADS installed on a given wind power plant complies with its regulatory requirements. In this protocol, detection/classification probability is specifically estimated for a given target species at a given regulatory detection distance. This protocol also estimates the proportion of time an ADS is functional on site over a year, and the proportion of reaction orders successfully operated by wind turbines. These protocols have been field-tested and made publicly available for use by government agencies and wind power plant operators.

Response of the MIMOSIS-1 CMOS Monolithic Active Pixel Sensor to particle beams with different dE/dx

The ultra-thin and highly granular CMOS Monolithic Active Pixel Sensors (MAPS) are typically optimized for high rate high precision tracking, which implies the use of a very thin active medium and digital readout. Both features hamper using the devices for identifying low momentum particles by means of dE/dx. Still, MAPS feature charge sharing and typically clusters of more than one fired pixel per impinging particles are formed. It was previously shown that the number of fired pixels per cluster scales with the dE/dx, which allowed identifying highly ionizing nuclear fragments [1]. Assuming a sufficiently strong response to different dE/dx, this approach could also be considered for distinguishing minimum ionizing particles (MIP) from light fragments like alpha particles in tracking detectors. In this work, we study this response with particle beams with a dE/dx of up to four times the ones of MIPs, for non-irradiated and irradiated chips, with different sensing nodes as implemented in the MIMOSIS-1 prototype used for the vertex detector of the CBM experiment.

Adaptive radial basis functions based Time-Varying model for EEG analysis in patients with cervical dystonia

Precise time–frequency (TF) analysis of electroencephalogram (EEG) signals is critical in evaluating cortical responses of patients with cervical dystonia (CD). Traditional methods are faced with challenges of constrained time–frequency resolution and accuracy, limiting the application of EEG in CD patients. This study introduces a novel adaptive basis function-based for TF representation method to meet the challenge. The methodology begins by identifying the kernel function center through an adaptive clustering technique. Then, the optimum structures and scales of the kernel function are determined by the improved genetic algorithm, which enable more precise tracking of EEG signals. Finally, accurately estimated parameters are converted to high-resolution TF images using a parameter spectrum estimation method, providing more detailed information of the EEG data. Leveraging the insights from the TF images, a regression model correlating TF features with clinical scores was developed to assess severity of CD patients. Simulation results show that the proposed method has superior tracking capabilities and a higher time–frequency resolution than current state-of-the-art methods. In the analysis of real EEG signals, we observed a notable elevation in gamma band power within the C3 and P3 channels, significantly differing from healthy individuals (p < 0.05), however, which cannot be found by other methods. This indicates distinctive high-frequency cortical activation associated with CD. Moreover, the regression model reaches a correlation coefficient above 0.82, suggesting its potential for objectively assessing severity of CD patients. Collectively, this study provides a robust tool for EEG signal analysis, and the analysis result will contribute to clinic treatment.

MMW‐FC: A novel railway fastener detecting method based on millimetre wave radar for train positioning

AbstractA novel method is proposed for rail fastener detection based on millimetre‐wave (mmWave) radar, mmWave radar fastener counter (MMW‐FC), which can accurately detect and record the fasteners in real‐time as the train traverses its route. Under circumstances where GNSS signals remain unavailable for prolonged durations, precise train localisation can be accomplished by correlating the number of fasteners derived from this method with the corresponding track map. Initially, MMW‐FC utilises fast Fourier transform and adaptive beamforming to focus the energy reflected from fasteners. Subsequently, it applies an adaptive template‐matching algorithm to detect each fastener. Furthermore, by leveraging known fastener spacing and the average time for trains to pass adjacent fasteners, the Kalman filter can execute precise speed tracking, used as a speed reference when adjusting the matching template adaptively. The experimental results indicate that the proposed method can precisely count the fasteners the train encounters in diverse road and speed conditions. The fastener counter maintains the Counting Error less than 0.067%, the speed error stays below 1.8 km/h, and the maximum values of the mean absolute error and root mean square error for speed are 0.7337 and 0.9584 km/h, respectively.

Adaptive saturated two-bit-triggered bipartite consensus control for networked MASs with periodic disturbances: a low-computation method

Abstract This paper investigates the bipartite tracking control problem for a family of networked multi-agent systems with periodic disturbances as well as input saturation. A low-computation two-bit-triggered adaptive control strategy is proposed to achieve precise trajectory tracking and maintain the boundedness of the closed-loop signals. Compared with the existing results, first, this paper considers the problems for the coexistence of cooperation and competition in multi-agent systems, which represents a more common situation; secondly, the explosion of complexity issue is avoided without introducing any auxiliary filters, making our result more applicable and less complex; thirdly, a function approximator incorporating Fourier series expansion and a radial basis function neural network is utilized to model time-varying periodic disturbance functions and lastly, unlike traditional event-triggered control, the issue of controlling signal transmission bits is further explored to conserve system transmission resources. The result from a comparative simulation illustrates the advantages of the proposed method.

Courier Tracking System

The Courier Tracking System is a critical component of modern logistics, enabling efficient parcel management, real-time monitoring, and seamless customer service. This abstract provides an overview of a comprehensive Courier Tracking System designed to streamline the courier industry, enhance operational efficiency, and improve customer satisfaction. The system incorporates various technologies such as GPS, RFID, and online platforms to create a unified, end-to-end tracking solution. Couriers are equipped with GPS-enabled devices to provide real-time location information, ensuring precise parcel tracking. RFID technology is used to assign unique identifiers to parcels, making them easily traceable throughout the supply chain. Key Words: Smart logistics, deep learning, LSTM, multi-objective optimization, intelligent systems.

Fuzzy logic system-based force tracking control of robot in highly dynamic environments

PurposeThe study aims to equip robots with the ability to precisely maintain interaction forces, which is crucial for tasks such as polishing in highly dynamic environments with unknown and varying stiffness and geometry, including those found in airplane wings or thin, soft materials. The purpose of this study is to develop a novel adaptive force-tracking admittance control scheme aimed at achieving a faster response rate with higher tracking accuracy for robot force control.Design/methodology/approachIn the proposed method, the traditional admittance model is improved by introducing a pre-proportional-derivative controller to accelerate parameter convergence. Subsequently, the authors design an adaptive law based on fuzzy logic systems (FLS) to compensate for uncertainties in the unknown environment. Stability conditions are established for the proposed method through Lyapunov analysis, which ensures the force tracking accuracy and the stability of the coupled system consisting of the robot and the interaction environment. Furthermore, the effectiveness and robustness of the proposed control algorithm are demonstrated by simulation and experiment.FindingsA variety of unstructured simulations and experimental scenarios are designed to validate the effectiveness of the proposed algorithm in force control. The outcomes demonstrate that this control strategy excels in providing fast response, precise tracking accuracy and robust performance.Practical implicationsIn real-world applications spanning industrial, service and medical fields where accurate force control by robots is essential, the proposed method stands out as both practical and straightforward, delivering consistently satisfactory performance across various scenarios.Originality/valueThis research introduces a novel adaptive force-tracking admittance controller based on FLS and validated through both simulations and experiments. The proposed controller demonstrates exceptional performance in force control within environments characterized by unknown and varying.

Precise path planning and trajectory tracking based on improved A-star algorithm

Path planning and trajectory tracking are very meaningful for the field of autonomous driving, but currently path planning still has problems such as non-optimal paths and insufficiently accurate paths. This paper addresses the issue of path planning by proposing a improved A-star algorithm and locally zooming on the map technique to achieve precise path planning. Compared with the conventional method, this method reduces the time by 23% and the path length by 21% in the scenarios shown in the paper, respectively, and provides a reference for related research. Moreover, trajectory tracking was achieved using the improved LQR control. Compared with the conventional method, the improved LQR control algorithm reduces the average error by 80% in the scenario shown in the paper. Firstly, the A-star algorithm is enhanced by incorporating an unknown path cost estimation function, thereby improving the effect of its path planning in complex environments. Additionally, the method of locally zooming on the map is incorporated, effectively enhancing the accuracy and safety of path planning. Building upon the path planning, further improvements are made to the LQR control algorithm, enabling autonomous deceleration in complex sections, which facilitates better trajectory tracking and enhances the motion control performance of the robot during practical operations.

A Novel Tracking Algorithm Based on Waveform Selection for Maneuvering Targets in Clutter

The cognition radar utilizes the dynamic waveform configuration to adapt to the environment to improve tracking performance. A novel tracking algorithm based on waveform selection is proposed to address the maneuvering aircraft tracking problem in clutter. Based on the modified current statistical (MCS) model, the modified probabilistic data association filter (MPDAF) is integrated with the square-root cubature Kalman filter (SCKF) to deal with the nonlinear measurement and the clutter. Additionally, the waveform library is established by applying the fractional Fourier transform (FRFT) to a base waveform, and a direct method is proposed to select the optimal waveform to minimize the posterior state error covariance matrix. The simulation results showed that, compared with the filters with the fixed waveform as well as the state-of-the-art algorithms, the proposed algorithm achieved higher estimation precision and lower track loss percentage while maintaining a low computational burden.

Customized Tracking Algorithm for Robust Cattle Detection and Tracking in Occlusion Environments.

Ensuring precise calving time prediction necessitates the adoption of an automatic and precisely accurate cattle tracking system. Nowadays, cattle tracking can be challenging due to the complexity of their environment and the potential for missed or false detections. Most existing deep-learning tracking algorithms face challenges when dealing with track-ID switch cases caused by cattle occlusion. To address these concerns, the proposed research endeavors to create an automatic cattle detection and tracking system by leveraging the remarkable capabilities of Detectron2 while embedding tailored modifications to make it even more effective and efficient for a variety of applications. Additionally, the study conducts a comprehensive comparison of eight distinct deep-learning tracking algorithms, with the objective of identifying the most optimal algorithm for achieving precise and efficient individual cattle tracking. This research focuses on tackling occlusion conditions and track-ID increment cases for miss detection. Through a comparison of various tracking algorithms, we discovered that Detectron2, coupled with our customized tracking algorithm (CTA), achieves 99% in detecting and tracking individual cows for handling occlusion challenges. Our algorithm stands out by successfully overcoming the challenges of miss detection and occlusion problems, making it highly reliable even during extended periods in a crowded calving pen.

Abstract A028: Quantifying resistance to targeted anticancer therapies at scale with duplex sequencing

Abstract Drug resistance to targeted anticancer therapeutics is one of the most researched problems in cancer genetics. A fundamental limiting factor facing most drug resistance studies is that resistance is studied retrospectively, i.e., mutants are characterized for their drug resistance only once they are seen in the clinic. Deep mutational scanning (DMS) is a field of functional genomics that can enable a-priori identification of resistant mutants- long before they are seen in the clinic. Quantifying resistance prospectively can guide clinical treatment decision-making and drug discovery efforts. In order to guide clinical practice, a DMS screen would need to have the sensitivity to measure drug resistance well and be able to relate screen measurements to clinical pharmacology. However, current DMS screens are not adopted for drug resistance and face unique technical challenges that limit the overall interpretability of screen data. Here we demonstrate the first scalable duplex sequencing DMS screen and use it to study Imatinib resistance in BCR-ABL. We first studied the pooled growth of 20 known Imatinib resistant mutants at low allele frequencies. We observed significant depletion artifacts and dose-response variations when measuring mutant outgrowth using allele frequency alone. To correct for these artifacts, we developed an inference-based approach that identifies and addresses depletion and dose variation artifacts that are commonly seen in drug resistance screens. The described measurement methodology enables precise and accurate tracking of low allele-frequency mutants. We also describe the first error-corrected duplex sequencing workflow that can achieve sequencing depths of 3 × 105, which is 20x higher than commercially available duplex sequencing kits. Sequencing at these depths enabled us to detect and measure 96.7% of all possible amino acid substitutions in the ABL kinase (n=4,788 mutants). We used our measurements to characterize all treatment-emergent variants of uncertain drug resistance in CML patients. We find that 22% of the rare variants seen in Imatinib refractory CML patients drive imatinib resistance, while the rest are likely bystanders of another resistance mechanism. Furthermore, because we can relate our measurements to clinical pharmacology, we identify variants that are good candidates for dose escalation from 400mg to 800mg daily dose of imatinib. Here, we demonstrate the first scalable duplex sequencing DMS screen that achieves high levels of sensitivity and specificity in measuring mutant drug resistance. We demonstrate the utility of this workflow by characterizing all variants of uncertain drug resistance in the ABL kinase. Addressing technical key barriers that face DMS screens of drug resistance enables us to make recommendations for treatment decisions on variants of unknown drug resistance. This approach can be used by pharmaceutical companies and geneticists to prospectively identify drug resistant variants to investigational drugs in candidate druggable biomarkers. Citation Format: Haider Inam, Josh Reynolds, Marta Tomaszkiewicz, Scott Leighow, Yiyun Rao, Ivan Sokirniy, Justin Pritchard. Quantifying resistance to targeted anticancer therapies at scale with duplex sequencing [abstract]. In: Proceedings of the AACR Special Conference in Cancer Research: Translating Cancer Evolution and Data Science: The Next Frontier; 2023 Dec 3-6; Boston, Massachusetts. Philadelphia (PA): AACR; Cancer Res 2024;84(3 Suppl_2):Abstract nr A028.

Visual Feature Tuning Properties of Short-Latency Stimulus-Driven Ocular Position Drift Responses during Gaze Fixation.

Ocular position drifts during gaze fixation are significantly less well understood than microsaccades. We recently identified a short-latency ocular position drift response, of ∼1 min arc amplitude, that is triggered within <100 ms by visual onsets. This systematic eye movement response is feature-tuned and seems to be coordinated with a simultaneous resetting of the saccadic system by visual stimuli. However, much remains to be learned about the drift response, especially for designing better-informed neurophysiological experiments unraveling its mechanistic substrates. Here we systematically tested multiple new feature tuning properties of drift responses. Using highly precise eye tracking in three male rhesus macaque monkeys, we found that drift responses still occur for tiny foveal visual stimuli. Moreover, the responses exhibit size tuning, scaling their amplitude (both up and down) as a function of stimulus size, and they also possess a monotonically increasing contrast sensitivity curve. Importantly, short-latency drift responses still occur for small peripheral visual targets, which additionally introduce spatially directed modulations in drift trajectories toward the appearing peripheral stimuli. Drift responses also remain predominantly upward even for stimuli exclusively located in the lower visual field and even when starting gaze position is upward. When we checked the timing of drift responses, we found it was better synchronized to stimulus-induced saccadic inhibition than to stimulus onset. These results, along with a suppression of drift response amplitudes by peristimulus saccades, suggest that drift responses reflect the rapid impacts of short-latency and feature-tuned visual neural activity on final oculomotor control circuitry in the brain.

Joint angle estimation during shoulder abduction exercise using contactless technology

BackgroundTele-rehabilitation, also known as tele-rehab, uses communication technologies to provide rehabilitation services from a distance. The COVID-19 pandemic has highlighted the importance of tele-rehab, where the in-person visits declined and the demand for remote healthcare rises. Tele-rehab offers enhanced accessibility, convenience, cost-effectiveness, flexibility, care quality, continuity, and communication. However, the current systems are often not able to perform a comprehensive movement analysis. To address this, we propose and validate a novel approach using depth technology and skeleton tracking algorithms.MethodsOur data involved 14 participants (8 females, 6 males) performing shoulder abduction exercises. We collected depth videos from an LiDAR camera and motion data from a Motion Capture (Mocap) system as our ground truth. The data were collected at distances of 2 m, 2.5 m, and 3.5 m from the LiDAR sensor for both arms. Our innovative approach integrates LiDAR with the Cubemos and Mediapipe skeleton tracking frameworks, enabling the assessment of 3D joint angles. We validated the system by comparing the estimated joint angles versus Mocap outputs. Personalized calibration was applied using various regression models to enhance the accuracy of the joint angle calculations.ResultsThe Cubemos skeleton tracking system outperformed Mediapipe in joint angle estimation with higher accuracy and fewer errors. The proposed system showed a strong correlation with Mocap results, although some deviations were present due to noise. Precision decreased as the distance from the camera increased. Calibration significantly improved performance. Linear regression models consistently outperformed nonlinear models, especially at shorter distances.ConclusionThis study showcases the potential of a marker-less system, to proficiently track body joints and upper-limb angles. Signals from the proposed system and the Mocap system exhibited robust correlation, with Mean Absolute Errors (MAEs) consistently below 10∘\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$10^\\circ$$\\end{document}. LiDAR’s depth feature enabled accurate computation of in-depth angles beyond the reach of traditional RGB cameras. Altogether, this emphasizes the depth-based system’s potential for precise joint tracking and angle calculation in tele-rehab applications.

RBFNN-Based Anti-Input Saturation Control for Hypersonic Vehicles

In hypersonic flight control, characterized by challenges posed by input saturation, model parameter uncertainties, and external disturbances, this paper introduces a pioneering anti-input saturation control method based on RBFNN adaptivity. We have developed adaptive laws to enhance control system adaptability and robustness by integrating mission profiles, actuator saturation failure modes, and self-evolving neural network design. Furthermore, our approach introduces a novel anti-input saturation auxiliary system, effectively addressing input saturation constraints. This innovation ensures system stability and precise tracking, even in severe input saturation constraints. The results reveal that the system’s steady-state tracking error remains under 2% under input saturation constraints, and the convergence speed demonstrates an impressive 20% improvement. These findings underscore this research’s substantial advancement in hypersonic flight control. It may significantly enhance the controllability and performance of hypersonic vehicles in real-world scenarios.

Mining the Micro-Trajectory of Two-Wheeled Non-Motorized Vehicles Based on the Improved YOLOx

Two-wheeled non-motorized vehicles (TNVs) have become the primary mode of transportation for short-distance travel among residents in many underdeveloped cities in China due to their convenience and low cost. However, this trend also brings corresponding risks of traffic accidents. Therefore, it is necessary to analyze the driving behavior characteristics of TNVs through their trajectory data in order to provide guidance for traffic safety. Nevertheless, the compact size, agile steering, and high maneuverability of these TNVs pose substantial challenges in acquiring high-precision trajectories. These characteristics complicate the tracking and analysis processes essential for understanding their movement patterns. To tackle this challenge, we propose an enhanced You Only Look Once Version X (YOLOx) model, which incorporates a median pooling-Convolutional Block Attention Mechanism (M-CBAM). This model is specifically designed for the detection of TNVs, and aims to improve accuracy and efficiency in trajectory tracking. Furthermore, based on this enhanced YOLOx model, we have developed a micro-trajectory data mining framework specifically for TNVs. Initially, the paper establishes an aerial dataset dedicated to the detection of TNVs, which then serves as a foundational resource for training the detection model. Subsequently, an augmentation of the Convolutional Block Attention Mechanism (CBAM) is introduced, integrating median pooling to amplify the model’s feature extraction capabilities. Subsequently, additional detection heads are integrated into the YOLOx model to elevate the detection rate of small-scale targets, particularly focusing on TNVs. Concurrently, the Deep Sort algorithm is utilized for the precise tracking of vehicle targets. The process culminates with the reconstruction of trajectories, which is achieved through a combination of video stabilization, coordinate mapping, and filtering denoising techniques. The experimental results derived from our self-constructed dataset reveal that the enhanced YOLOx model demonstrates superior detection performance in comparison to other analogous methods. The comprehensive framework accomplishes an average trajectory recall rate of 85% across three test videos. This significant achievement provides a reliable method for data acquisition, which is essential for investigating the micro-level operational mechanisms of TNVs. The results of this study can further contribute to the understanding and improvement of traffic safety on mixed-use roads.

Bidirectional Temporal Pose Matching for Tracking

Multi-person pose tracking is a challenging task. It requires identifying the human poses in each frame and matching them across time. This task still faces two main challenges. Firstly, sudden camera zooming and drastic pose changes between adjacent frames may result in mismatched poses between them. Secondly, the time relationships modeled by most existing methods provide insufficient information in scenarios with long-term occlusion. In this paper, to address the first challenge, we propagate the bounding boxes of the current frame to the previous frame for pose estimation, and match the estimated results with the previous ones, which we call the Backward Temporal Pose-Matching (BTPM) module. To solve the second challenge, we design an Association Across Multiple Frames (AAMF) module that utilizes long-term temporal relationships to supplement tracking information lost in the previous frames as a Re-identification (Re-id) technique. Specifically, we select keyframes with a fixed step size in the videos and label other frames as general frames. In the keyframes, we use the BTPM module and the AAMF module to perform tracking. In the general frames, we propagate poses in the previous frame to the current frame for pose estimation and association, which we call the Forward Temporal Pose-Matching (FTPM) module. If the pose association fails, the current frame will be set as a keyframe, and tracking will be re-performed. In the PoseTrack 2018 benchmark tests, our method shows significant improvements over the baseline methods, with improvements of 2.1 and 1.1 in mean Average Precision (mAP) and Multi-Object Tracking Accuracy (MOTA), respectively.

Smart Body Posture Recognition and Guiding System

In an era prioritizing health and wellness, the integration of the Smart Body Posture Recognition &amp; Guiding System into self- service health kiosks signifies a paradigm shift in healthcare management. This groundbreaking research project leverages cutting-edge MediaPipe Body Tracking technology to revolutionize health monitoring capabilities. At its core, MediaPipe Body Tracking enables precise real-time identification and tracking of human body key points and movements. This breakthrough technology ensures unparalleled accuracy in health parameter measurements within the kiosk interface. A standout feature of this system is its embedded alert mechanism, surpassing conventional health monitoring by actively detecting and notifying individuals about poor body posture. Providing immediate corrective feedback, this feature significantly impacts wellness, fostering a proactive approach to posture and overall health management. This research delves into the intricacies of MediaPipe Body Tracking's algorithms and sensors, elucidating the technology's real-time feedback mechanism. The system's ability to address poor posture not only prompts immediate corrective action but also raises awareness about its long-term health implications. Beyond individual health monitoring, this innovation promises a transformative shift in healthcare paradigms, encouraging proactive health measures and empowering individuals to take charge of their well-being. The Smart Body Posture Recognition &amp; Guiding System represents a significant advancement at the nexus of technology and healthcare, redefining how societies approach proactive health management. Keywords- MediaPipe, Posture Recognition, Heathcare

Adaptive-Robust Controller for Smart Exoskeleton Robot.

Rehabilitation robotics has seen growing popularity in recent years due to its immense potential for improving the lives of people with disabilities. However, the complex, uncertain dynamics of these systems present significant control challenges, requiring advanced techniques. This paper introduces a novel adaptive control framework integrating modified function approximation (MFAT) and double-integral non-singular terminal sliding mode control (DINTSMC). The goal is to achieve precise tracking performance, high robustness, a fast response, a finite convergence time, reduced chattering, and effective handling of unknown system dynamics. A key feature is the incorporation of a higher-order sliding mode observer, eliminating the need for velocity feedback. This provides a new solution for overcoming the inherent variations and uncertainties in robot manipulators, enabling improved accuracy within fixed convergence times. The efficacy of the proposed approach was validated through simulations and experiments on an exoskeleton robot. The results successfully demonstrated the controller's effectiveness. Stability analysis using Lyapunov theory proved the closed-loop system's uniform ultimate boundedness. This contribution is expected to enable enhanced control for rehabilitation robots and improved patient outcomes.

Artificial Flow Guidance Method for Combined Off-Tracking and Stability Improvement for Automated Articulated Vehicles

Abstract This paper considers an integrated control method combining autonomous driving and active steering. By using artificial flow guidance (AFG), the steering at all five axles on a tractor–semitrailer are synchronized for precise low-speed path tracking and improved lateral stability. AFG is a motion planning method which uses velocity vectors to guide the motion of the vehicle; here, two modification on AFG are proposed to form the integrated-AFG which improves the transient performance and generalizes the choice of the tracking points. Simulations rendered in TruckMaker show submillimeter level steady-state off-tracking for a broad speed range, with maximum deviation being 1 cm for a high-speed lane change; amplification of trailer lateral motion is also suppressed, with rearward amplification (RWA) &amp;lt; 1 maintained throughout. This control method is robust to changes in key parameters such as trailer mass and road friction coefficient. The methods presented provide a new foundation for implementing automated freight transportation on highways.

A Strong Maneuvering Target-Tracking Filtering Based on Intelligent Algorithm

In this paper, a variable-structure multimodel (VSMM) filtering algorithm based on the long short-term memory (LSTM) regression-deep Q network (L-DQN) is proposed to accurately track strong maneuvering targets. The algorithm can map the selection of the model set to the selection of the action label and realize the purpose of a deep reinforcement-learning agent to replace the model switching in the traditional VSMM algorithm by reasonably designing a reward function, state space, and network structure. At the same time, the algorithm introduces a LSTM algorithm, which can compensate the error of tracking results based on model history information. The simulation results show that compared with the traditional VSMM algorithm, the proposed algorithm can quickly capture the maneuvering of the target, the response time is short, the calculation accuracy is significantly improved, and the range of adaptation is wider. Precise tracking of maneuvering targets was achieved.