<rss version="2.0" xmlns:atom="https://www.w3.org/2005/Atom">
  <channel>
    <title>Transport Research International Documentation (TRID)</title>
    <link>https://trid.trb.org/</link>
    <atom:link href="https://trid.trb.org/Record/RSS?s=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" rel="self" type="application/rss+xml" />
    <description></description>
    <language>en-us</language>
    <copyright>Copyright © 2026. National Academy of Sciences. All rights reserved.</copyright>
    <docs>http://blogs.law.harvard.edu/tech/rss</docs>
    <managingEditor>tris-trb@nas.edu (Bill McLeod)</managingEditor>
    <webMaster>tris-trb@nas.edu (Bill McLeod)</webMaster>
    <image>
      <title>Transport Research International Documentation (TRID)</title>
      <url>https://trid.trb.org/Images/PageHeader-wTitle.jpg</url>
      <link>https://trid.trb.org/</link>
    </image>
    <item>
      <title>Two-Stage Rapidly-Exploring Maneuvering Target Pursuit Strategy for Radar-Enabled Uav</title>
      <link>https://trid.trb.org/View/2727946</link>
      <description><![CDATA[This paper explores the maneuvering target pursuit problem of the radar-enabled unmanned aerial vehicle (RUAV). The target pursuit problem is modeled as an autonomous sensing and decision-making process of the RUAV, in which the state of the target is estimated by the radar and is utilized as the environmental information to plan the flight trajectory of the RUAV. The cumulative distance between the RUAV and the target plus the length of the trajectory in multiple predictive steps is used as the utility function to characterize the expected revenue of the RUAV for the target pursuit task, and a dynamic optimization model with practical constraints is formulated on the basis of the model predictive control framework. The two-stage rapidly-exploring maneuvering parget pursuit (TRMTP) algorithm consisting of multi-step target state prediction, global path generation, local trajectory optimization, and target state estimation is proposed, which integrates the interacting multiple model filter, optimal rapidly-exploring random tree, and receding-horizon particle swarm optimization to obtain the real-time path planning strategy while avoiding the forbidden region. Numerical results are provided to evaluate the effectiveness and superiority of the TRMTP algorithm over some typical counterparts in terms of optimality and completion time for the target pursuit mission.]]></description>
      <pubDate>Mon, 27 Jul 2026 11:16:35 GMT</pubDate>
      <guid>https://trid.trb.org/View/2727946</guid>
    </item>
    <item>
      <title>A berthing state estimation method based on shipborne LiDAR target detection</title>
      <link>https://trid.trb.org/View/2608879</link>
      <description><![CDATA[To improve the accuracy and generalisation of the berthing perception system based on shipborne LiDAR, thereby enhancing the safety and operational efficiency of ship berthing, a berthing perception system based on laser point cloud data is proposed. This system consists of four components: laser point cloud data collection, three-dimensional ship target detection, boundary plane fitting of target berths, and berthing state estimation. The shipborne LiDAR captures three-dimensional environmental information around the vessel. By incorporating point cloud reflectivity into the encoding network, loss function, and ground truth label file of the PointPillar detection network, the accuracy of ship target detection is enhanced, and the point cloud of the detected vessel is extracted based on the location of the detection box. A plane model of the target vessel or berth boundary is extracted using the Random Sample Consensus (RANSAC) algorithm, and the berthing state of the ship is calculated based on this plane model. The berthing perception system was validated in real-world experiments using an unmanned vessel (Zhilong NO.1) at Lingshui Port and a section of the Tianjin Haihe River, where the vessel was berthed alongside a moored ship and in available berth areas. Real-time positioning data from the Real-Time Kinematic (RTK) system is used to validate the accuracy of the proposed berth state estimation. The experimental results show that, compared to representative ship detection models, the mean Average Precision (mAP) of the proposed three-dimensional ship target detection method increased by 14.3 %. The root mean square error of the distance measurement in the berthing state estimation module was approximately 0.2514 m, which is an improvement of 0.1107 m over methods based on berth lines. The experiments demonstrate that the proposed berthing perception system can provide accurate berthing state estimates to assist operators in berthing operations.]]></description>
      <pubDate>Mon, 08 Dec 2025 11:41:46 GMT</pubDate>
      <guid>https://trid.trb.org/View/2608879</guid>
    </item>
    <item>
      <title>A two-stage detection method for vessel targets in sea clutter based on time-frequency feature anomalies in shipborne HFSWR</title>
      <link>https://trid.trb.org/View/2614929</link>
      <description><![CDATA[In shipborne high-frequency surface wave radar (HFSWR), platform motion causes sea clutter expansion, target echo broadening, and reduced signal-to-clutter ratio (SCR), thereby complicating target detection in sea clutter regions. Existing detection methods primarily focus on targets with significantly higher SCR than the surrounding sea clutter, whereas low-SCR targets are often obscured and difficult to detect. In this paper, we employ time-frequency analysis combined with signal decomposition and reconstruction to derive distinctive time-frequency ridge (TFR) difference features that discriminate between sea clutter with and without a target. Based on these TFR differences, a novel two-stage method is proposed for detecting target anomalies in sea clutter. First, the relevant frequency range of sea clutter is estimated using the motion state of shipborne platform. In Stage 1, primary TFRs of sea clutter are used to construct an image feature (IF)-based one-class classification network (OCCN), which identifies TFRs exhibiting significant target anomalies. In Stage 2, the remaining ambiguous TFRs are decomposed and reconstructed to generate secondary distinguishable TFRs. Handcrafted features (HFs) extracted from these secondary TFRs are then fed into HF-OCCN to identify anomalies caused by targets. Simulation and real dataset validation demonstrate that the proposed method significantly improves target detection accuracy in sea clutter.]]></description>
      <pubDate>Fri, 05 Dec 2025 14:08:31 GMT</pubDate>
      <guid>https://trid.trb.org/View/2614929</guid>
    </item>
    <item>
      <title>High-Fidelity Real-Time Radar Modeling With Consideration of False and Missed Alarms for Autonomous Driving Simulation</title>
      <link>https://trid.trb.org/View/2591783</link>
      <description><![CDATA[Simulation is crucial for autonomous driving technology evolution. Radar, as an essential sensor in this field, significantly influences decision-making with its outputs. High-fidelity autonomous driving simulations require radar models that replicate radar outputs, including false alarms, missed alarms, and measurement errors, both in real-time and with high fidelity. The radar detection process is highly complex, and false and miss alarms add significant uncertainty to the detection results. Current radar models cannot accurately predict radar outputs. To address these issues, this study introduces a data-driven radar modeling approach. Initially, an analysis of factors influencing radar detection outcomes was conducted. Then proposes a labeling method for radar output objects, identify the corresponding scene targets, and distinguish between ghost and real objects. Following this, it introduces a modeling technique that separates radar output status and parameters, aiming to accurately predict radar outputs in the presence of false and missed alarms. It further decouples output parameters to boost prediction accuracy. Radar data is then collected to create a dataset. The radar model is developed and validated against conventional models. The model achieves a 96.5% accuracy in predicting false and missed alarms, with its predictions for radar output parameters closely approximating actual values. Compared to traditional models, there are improvements exceeding 70.60% and 93.68% respectively. Its 5-millisecond processing speed is substantially faster than actual radar speeds. This demonstrates the method's ability to create high-fidelity, real-time models.]]></description>
      <pubDate>Fri, 31 Oct 2025 17:03:53 GMT</pubDate>
      <guid>https://trid.trb.org/View/2591783</guid>
    </item>
    <item>
      <title>Improving SNR for NLoS Target Detection Using Multi-RIS-Assisted Monostatic Radar</title>
      <link>https://trid.trb.org/View/2553800</link>
      <description><![CDATA[The use of a reconfigurable intelligent surface (RIS) in radar systems significantly enhances target detection, particularly in challenging non-line-of-sight (NLoS) scenarios. In urban environments, where structures frequently obstruct line-of-sight (LoS) paths, the integration of RISs with existing radars can offer a viable solution for enhancing signal-to-noise ratio (SNR) and improving target detection. Approaches utilizing a single RIS can still fail in scenarios where a link cannot be established. This paper presents a novel approach for deriving a comprehensive expression for the received power, SNR and path loss (PL) in systems where multiple RISs assist a monostatic radar. The authors analyze the power received in dual RIS configurations and extend this to include additional RISs, demonstrating how each additional RIS placement affects the system's performance. Moreover, the analysis explores the impact of different Swerling target models on the SNR and PL, highlighting the optimal angles for target detection. This multi-RIS strategy offers a substantial performance boost over conventional radars and single RIS-assisted systems, particularly in environments with obstacles. Simulation results demonstrate a significant improvement in SNR with a dual RIS-assisted radar, with up to 14.42 dB gains observed when employing a $46 \times 46$ element RIS configuration at L-band and 65.47 dB gain when employing a $328 \times 328$ element RIS configuration at X-band, corresponding to a RIS size of $ 5\text{ m} \times 5\text{ m}$ at both frequencies, showing the efficacy of the proposed multi-RIS strategy.]]></description>
      <pubDate>Fri, 18 Jul 2025 15:10:25 GMT</pubDate>
      <guid>https://trid.trb.org/View/2553800</guid>
    </item>
    <item>
      <title>Track-to-track association from diverse source ship trajectory based on an improved graph neural network</title>
      <link>https://trid.trb.org/View/2557065</link>
      <description><![CDATA[With the development of maritime surveillance technologies, large volumes of ship trajectory data have been collected through various monitoring methods. The accuracy of targets tracking can be significantly improved by associating these trajectories, particularly in cases of partial equipment monitoring failures. Different acquisition approaches and data standards of marine monitoring methods lead to differences in the quality and precision of ship trajectory data from diverse sources, which significantly affects the accuracy of track-to-track association. According to AIS and Radar trajectory data, a novel multi-graph neural network combined with Cross-Attention (CA-MGNN) is proposed to realize the association with precision bias. The MGNN module is employed to convert AIS and Radar trajectory points into corresponding features, which are extracted from multiple spatiotemporal dimensions. The interactive features are then constructed by Cross-Attention mechanism, thereby achieving the association based on trajectory features. Experimental results demonstrate that the proposed method achieves high efficiency with association accuracy of 92.61% and inference time of 83.4 (ms), thereby providing more accurate tracking information to meet the demands of maritime awareness application.]]></description>
      <pubDate>Sat, 31 May 2025 15:16:08 GMT</pubDate>
      <guid>https://trid.trb.org/View/2557065</guid>
    </item>
    <item>
      <title>Multiple Subbands Coherent Accumulation Target Detection Algorithm for DDMA-MIMO Radar</title>
      <link>https://trid.trb.org/View/2425300</link>
      <description><![CDATA[Compared with the traditional time division multiple access - multiple input multiple output (TDMA-MIMO) radar, Doppler division multiple access - multiple input multiple output (DDMA-MIMO) radar enables the design of orthogonal waveform in Doppler domain instead of in time domain. Thus DDMA-MIMO radar performs well in long range radar application. However, it suffers from Doppler ambiguous and energy defocus of the target spectrum in DDMA-MIMO radar, and as a result the target detection performance degrades. To tackle these problems, a target detection algorithm based on multiple subbands coherent-accumulation (MSCA) is proposed in this paper. First, the empty-band is inserted into the Doppler domain by modifying the phase modulation of the transmitting antennas. Based on the periodic extension of Doppler in DDMA-MIMO system, a coherent accumulation and Doppler ambiguity mitigation method based on subband correlation is proposed. By exploiting the low energy characteristic of the empty subband, this method compares the energy of accumulated subband after MSCA to extract the real velocity of target. It also solves the problem of Doppler ambiguity caused by the period extension of target velocity. Besides, the proposed method can improve the detection performance, avoiding the target being drowned by noise. Simulation and real data results show that the proposed method can effectively alleviate the Doppler ambiguity, improve the target detection performance under low signal-to-noise scenarios.]]></description>
      <pubDate>Mon, 16 Dec 2024 11:59:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2425300</guid>
    </item>
    <item>
      <title>Joint Trajectory Planning and Transmit Resource Optimization for Multi-Target Tracking in Multi-UAV-Enabled MIMO Radar System</title>
      <link>https://trid.trb.org/View/2425296</link>
      <description><![CDATA[Multi-target tracking (MTT) plays a significant role in intelligent transportation systems, serving as an enabling technology for applications such as self-driving, surveillance, and navigation. To enhance the MTT performance, the unmanned aerial vehicles (UAVs) have emerged as effective assistants to MIMO radar system, due to their advantages of high flexibility, controllable deployment and cost-effectiveness. Towards this end, this work investigates a multi-UAV-enabled MIMO radar system, in which each UAV is equipped with a MIMO radar unit and dispatched to track multiple targets simultaneously. The authors are interested in the joint trajectory planning and transmit resource optimization (i.e. radar waveform optimization and transmit power allocation) to minimize the system power consumption, subject to constraints related to UAVs motion, system resources, and tracking accuracy. Specifically, the posterior Cramér-Rao Lower Bound (PCRLB) is derived and employed as a guideline for the joint optimization. Given the non-convex and inter-variable coupling nature of the formulated problem, the authors decompose it into three sub-problems and design an alternating optimization method. Firstly, for the UAVs trajectory planning, the authors obtain sub-optimal results leveraging the successive convex approximation (SCA)-based algorithm. Next, the authors present a feasible solution set for radar waveform optimization. For transmit power allocation, the authors perform a convex transformation and find the numerical solution. In addition, through introducing the Lagrange dual method, the authors further obtain the optimal analytical solution. Finally, simulation results demonstrate the effectiveness and advantages of the developed strategy.]]></description>
      <pubDate>Mon, 16 Dec 2024 11:59:22 GMT</pubDate>
      <guid>https://trid.trb.org/View/2425296</guid>
    </item>
    <item>
      <title>Estimation of Moving Direction and Size of Vehicle in High-Resolution Automotive Radar System</title>
      <link>https://trid.trb.org/View/2402002</link>
      <description><![CDATA[In this paper, the authors propose methods to estimate the moving direction and size of a target vehicle based on point cloud data detected by high-resolution automotive radar sensor. Previous studies using automotive radar sensors have proposed methods to roughly estimate the moving direction of vehicles, such as left, straight, or right. This study proposes methods to estimate not only the specific moving direction but also the approximate size of the vehicle. First, the authors use the high-resolution frequency-modulated continuous wave radar to acquire point cloud data for vehicles moving at various angles. In the point cloud data, radar signals are strongly reflected from the side of the vehicle and detected as a line segment. The proposed moving direction and size estimation method is based on line segment extracted from the Hough transform (HT). To extract the line segment from the point cloud data, the Hough transform is used. Using the extracted line segment, methods for estimating the moving direction and size of the vehicle are proposed. And then, the quick hull algorithm is used to estimate the center point of the vehicle to match the position of the target in the coordinate system. Finally, the direction, width, and length of the vehicle estimated from the proposed methods show average errors of 1.94°, 4.32%, and 6.32%, respectively. In addition, when compared to the conventional principal component analysis (PCA)-based method, the authors' proposed method exhibits superior performance in terms of estimation accuracy. Moreover, the authors have validated the effectiveness of the proposed method even in scenarios with multiple vehicles and in noisy road environments.]]></description>
      <pubDate>Wed, 06 Nov 2024 16:48:45 GMT</pubDate>
      <guid>https://trid.trb.org/View/2402002</guid>
    </item>
    <item>
      <title>AIS aided marine radar target tracking in a detection occluded environment</title>
      <link>https://trid.trb.org/View/2285594</link>
      <description><![CDATA[Radar signal occlusion due to islands and large ships occurs frequently in maritime environments, degrading the performance of marine radar target detection and tracking. In order to address the common track breakages and tracking inaccuracies during occlusion, both prior environment knowledge from electronic navigation chart (ENC) and information from automatic identification systems (AIS) are exploited. An AIS-aided integrated probabilistic data association (A-IPDA) algorithm is proposed for maritime target tracking in an occluded environment. It recursively identifies target occlusion based on environmental knowledge and applies a tailored track existence probability transition matrix for track existence estimation during occlusion, meanwhile rich AIS information is exploited to maintain target tracking performance. Experiments based on both simulated data and real data show that A-IPDA has the ability to counter long period target occlusion in complex maritime environments, where track continuity and tracking accuracy can be well maintained.]]></description>
      <pubDate>Mon, 13 Nov 2023 09:01:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2285594</guid>
    </item>
    <item>
      <title>Boids Flocking Algorithm for Situation Assessment of Driver Assistance Systems</title>
      <link>https://trid.trb.org/View/2230962</link>
      <description><![CDATA[Driver assistance systems are increasingly becoming part of the standard equipment of vehicles and thus contribute to road safety. However, as they become more widespread, the requirements for cost efficiency are also increasing, and so few and inexpensive sensors are used in these systems. Especially in challenging situations, this leads to the fact that target discrimination cannot be ensured which may lead to false reactions of the driver assistance system. In this paper, the Boids flocking algorithm is used to generate semantic neighborhood information between tracked objects which in turn can significantly improve the overall performance. Two different variants were developed: First, a freemoving flock whereby a separate flock is generated per tracked object and second, a formation-controlled flock where boids of a single flock move along the future road course in a pre-defined formation. In the first approach, the interaction between the flocks as well as the interaction between the boids within a flock is used to generate additional information, which in turn can be used to improve, for example, lane change detection. For the latter approach, new behavioral rules have been developed, so that the boids can reliably identify control-relevant objects to a driver assistance system. Finally, the performance of the presented methods is verified through extensive simulations.]]></description>
      <pubDate>Mon, 28 Aug 2023 09:19:11 GMT</pubDate>
      <guid>https://trid.trb.org/View/2230962</guid>
    </item>
    <item>
      <title>Integrated single target sensing and multiuser communications based on zero-forcing beamforming</title>
      <link>https://trid.trb.org/View/2214058</link>
      <description><![CDATA[Integrated sensing and communication (ISAC) is a promising approach that utilizes a single waveform for both information transmission and target object acquisition. In this study, the authors focus on the challenges posed by inter-user and inter-ISAC-antenna interference, specifically the self-interference from ISAC transmit antennas to receive antennas. Further, the benefit of a multi-functional ISAC scheme is clarified by comparing it with single function-aware schemes: sensing- and communication-aware approaches. To address these issues, they investigate the application of a zero-forcing (ZF)-based beamforming and power allocation (PA) technique. A sum rate maximization problem with a target object sensing signal-to-noise (SNR) threshold is formulated and split into two subproblems for improved tractability. To tackle the first subproblem of precoder design, they develop a constraint-aware greedy algorithm that employs communication SNR ordering. Subsequently, they propose a feasibility test-based algorithm to solve the second subproblem of PA.Through an extensive performance evaluation, encompassing computational complexity, sum rate, and ISAC received SNR, they verify that relying solely on a single function-aware scheme is insufficient for accommodating ISAC's multifunctional capabilities. Additionally, they demonstrate that a naive switching strategy between two single function-aware schemes can result in inefficient communication performance. Considering both sensing and communication functions, they identify the need for an adaptive balance between sensing and communication capabilities in a multi-functional ISAC system. This can be achieved by dynamically adjusting the target object sensing SNR threshold within the optimization problem's constraint. The proposed ZF-based ISAC with the designed PA scheme offers an optimal strategy when the transmit power of the ISAC is low. Conversely, an equal PA to multiple users emerges as the best strategy when the transmit power of the ISAC is sufficiently high. In conclusion, the authors' study highlights the significance of integrating sensing and communication functionalities in ISAC systems. Moreover, by providing insights into the interplay between target object sensing, beamforming, and power allocation, they contribute to the development of efficient and adaptable ISAC architectures.]]></description>
      <pubDate>Wed, 26 Jul 2023 15:59:13 GMT</pubDate>
      <guid>https://trid.trb.org/View/2214058</guid>
    </item>
    <item>
      <title>Non-Line-of-Sight Multi-Target Localization Algorithm for Driver-Assistance Radar System</title>
      <link>https://trid.trb.org/View/2156259</link>
      <description><![CDATA[In automatic driving, it is difficult for automotive radar to capture the information of vehicles and pedestrians located in blind areas such as street corners and urban intersections, which may lead to collision risks. To deal with it, this paper investigates the problem of multiple target localization in a non-line-of-sight (NLOS) scenario. Specifically, first, the propagation paths of the electromagnetic waves in the L-shaped NLOS scenario are analyzed and a multipath echoes model for the multiple-input-multiple-output (MIMO) radar is established. Then, the time of arrivals (ToAs) with respect to different paths are estimated by the matrix pencil algorithm. Based on the estimated delays, a path recognition strategy, by fully considering the range and angle information of targets, is proposed to pair the ToAs with different types of multipath and targets. Finally, the performance of the proposed method is verified via simulations and experiments, which reveal that the positions of the NLOS targets can be estimated with high precision.]]></description>
      <pubDate>Fri, 21 Apr 2023 09:49:29 GMT</pubDate>
      <guid>https://trid.trb.org/View/2156259</guid>
    </item>
    <item>
      <title>A Verification Method for Traffic Radar-Based Speed Meter With Target Position Determination in Road Vehicle Speeding Enforcement</title>
      <link>https://trid.trb.org/View/1899842</link>
      <description><![CDATA[Traffic radar-based speed meter (TRSM) is an important measuring instrument for measuring the speed of target vehicle based on the radar Doppler effect, and has been legally used in road vehicle speeding enforcement for more than 30 years in China. TRSM with target position determination (TRSM-TPD) is a new generation of TRSM with the advantages of speeding enforcement by lane, high accuracy of speed measurement and target position determination, high efficiency, low cost, etc. This paper proposes a new verification method for TRSM-TPD in road vehicle speeding enforcement. The proposed verification method includes the simulated speed calibration method for initial verification in the laboratory, and the online speed and position calibration method for subsequent verification in the field. The range of simulated radial speed is up to (1~400) km/h and the maximum permissible error is within ±0.03 km/h, which can satisfy the full-range and high-accuracy speed calibration requirements for TRSM-TPD. The uncertainty of the reference facility in actual traffic is 0.12% within the speed range of (60~250) km/h, where coverage factor k = 3. The simulated and online calibration results validate the effectiveness of the proposed verification method and the feasibility of the realized target speed simulator and the established reference facility.]]></description>
      <pubDate>Tue, 25 Jan 2022 09:50:48 GMT</pubDate>
      <guid>https://trid.trb.org/View/1899842</guid>
    </item>
    <item>
      <title>Robust Detection of Infrared Maritime Targets for Autonomous Navigation</title>
      <link>https://trid.trb.org/View/1755363</link>
      <description><![CDATA[This paper addresses a problem on infrared maritime target detection robustly in various situations. Its main contribution is to improve the infrared maritime target detection accuracy in different backgrounds, for various targets, using multiple infrared wave bands. The accuracy and the computational time of traditional infrared maritime searching systems are improved by the authors' proposed Local Peak Singularity Measurement (LPSM)-Based Image Enhancement and Grayscale Distribution Curve Shift Binarization (GDCSB)-Based Target Segmentation. The first part uses LPSM to quantize the local singularity of each peak. Additionally, an enhancement map (EM) is generated based on the quantitative local singularity. After multiplying the original image by the EM, targets can be enhanced and the background will be suppressed. The second part of GDCSB-Based Target Segmentation calculates the desired threshold by cyclic shift of the grayscale distribution curve (GDC) of the enhanced image. After binarizing the enhanced image, real targets can be segmented from the image background. To verify the proposed algorithm, experiments based on 13,625 infrared maritime images and five comparison algorithms were conducted. Results show that the proposed algorithm has solid performance in strong and weak background clutters, different wave bands, different maritime targets, etc.]]></description>
      <pubDate>Mon, 28 Dec 2020 10:01:00 GMT</pubDate>
      <guid>https://trid.trb.org/View/1755363</guid>
    </item>
  </channel>
</rss>