Multi-target Trajectory Research Articles

Optimization of multi-target continuous dynamic trajectory for unmanned aerial vehicles

In the problem of trajectory optimization for unmanned aerial vehicles (UAVs) passing through multiple target points, continuous velocity and acceleration in the process of optimization are essential for maintaining a feasible trajectory. This paper proposes a multi-segment holistic Bezier shaping method (MHBSM) for dynamic trajectory optimization. The MHBSM not only achieves holistic optimization of UAVs passing through a multi-target trajectory but also ensures high-order continuity at the junctions of trajectory segments. Unlike methods that generate non-dynamic trajectories by connecting arcs and straight lines (such as Dubins curves) without considering speed changes, MHBSM optimizes the trajectory while taking into account the dynamics of UAVs. The method optimizes the differential flat output space of a fixed-wing UAV dynamic model and transforms the dynamic optimization problem into a three-dimensional position optimization problem. The problem is then further transformed into an optimization of control points using the Bezier curve. The resulting trajectory satisfies the dynamic constraints. In comparison to the Gaussian pseudospectral method (GPM), MHBSM achieves similar optimization results with only a 2.58% difference, while requiring approximately 1.36% of the computational time on average. The MHBSM demonstrates excellent convergence performance while satisfying the constraints of continuous acceleration and obstacle avoidance.

A Robust TCPHD Filter for Multi-Sensor Multitarget Tracking Based on a Gaussian–Student’s t-Mixture Model

To realize multitarget trajectory tracking under non-Gaussian heavy-tailed noise, we propose a Gaussian–Student t-mixture distribution-based trajectory cardinality probability hypothesis density filter (GSTM-TCPHD). We introduce the multi-sensor GSTM-TCPHD (MS-GSTM-TCPHD) filter to enhance tracking performance. Conventional cardinality probability hypothesis density (CPHD) filters typically assume Gaussian noise and struggle to accurately establish target trajectories when faced with heavy-tailed non-Gaussian distributions. Heavy-tailed noise leads to significant estimation errors and filter dispersion. Moreover, the exact trajectory of the target is crucial for tracking and prediction. Our proposed GSTM-TCPHD filter utilizes the GSTM distribution to model heavy-tailed noise, reducing modeling errors and generating a set of potential target trajectories. Since single sensors have a limited field of view and limited measurement information, we extend the filter to a multi-sensor scenario. To tackle the issue of data explosion from multiple sensors, we employed a greedy approximation method to assess measurements and introduced the MS-GSTM-TCPHD filter. The simulation results demonstrate that our proposed filter outperforms the CPHD/TCPHD filter and Student’s t-based TCPHD filter in terms of accurately estimating the trajectories of multiple targets during tracking while also achieving improved accuracy and shorter processing time.

Multi-target trajectory planning and control technique for autonomous navigation of multiple robots

The autonomous robot has been the attraction point among robotic researchers since the last decade by virtue of increasing demand of automation in defence and intelligent industries. In the current research, a modified flow direction optimization algorithm (MFDA) and firefly algorithm (FA) are hybridized and implemented on wheeled robots to encounter multi-target trajectory optimization with smooth navigation by negotiating obstacles present within the workspace. Here, a hybrid algorithm is adopted for designing the controller with consideration of navigational parameters. A Petri-Net controller is also aided with the developed controller to resolve any conflict during navigation. The developed controller has been investigated on WEBOTS and MATLAB simulation environments coupled with real-time experiments by considering Khepera-II robot as wheeled robot. Single robot- multi-target, multiple robot single target and multiple robots-multiple target problems are tackled during the investigation. The outcomes of simulation are verified through real-time experimental outcomes by comparing results. Further, the proposed algorithm is tested for its suitability, precision, and stability. Finally, the developed controller is tested against existing techniques for authentication of proposed technique, and significant improvements of an average 34.2% is observed in trajectory optimization and 70.6% in time consumption.

A learning system for motion planning of free-float dual-arm space manipulator towards non-cooperative object

In recent years, non-cooperative objects, such as failed satellites and space junk, can be detected in space. These objects are usually manipulated or collected by free-floating dual-arm space manipulators. Reinforcement learning methods show more promise in trajectory planning for space manipulators as difficulties in modeling and manual parameter tuning have been recently surmounted. Although previous studies demonstrated their effectiveness, they cannot be applied to track dynamic targets with unknown rotation (non-cooperative objects). In this paper, we proposed a learning system for free-floating dual-arm space manipulator motion planning against non-cooperative objects. Specifically, our method consists of two modules. Module I realizes the multi-target trajectory planning for two end-effectors within a large target space. Next, Module II takes the point clouds of the non-cooperative object as input to estimate the motional properties, and then the location of the target points on the non-cooperative object can be predicted. Target points on rotating objects with unknown rotation can be successfully tracked by the end-effectors through the combination of Module I and Module II. Furthermore, experiments also demonstrate the scalability and generalization of our learning system.

Multi-target trajectory tracking in multi-frame video images of basketball sports based on deep learning

INTRODUCTION: There is occlusion interference in the multi-target visual tracking process of basketball video images, which leads to poor accuracy of multi-target trajectory tracking. This paper studies the multi-target trajectory tracking method in multi-frame video images of basketball sports based on deep learning. OBJECTIVES: Aiming at the problem of target occlusion in the tracking process and the problem of trajectory tracking anomaly caused by target occlusion, a modified algorithm is proposed. METHODS: The method is divided into two parts: detection and tracking. In the detection part, the YOLOv3 algorithm in deep learning technology is used to detect each target in the video, and the original YOLOv3 backbone network Darknet-53 is replaced by the lightweight backbone network MobileNetV2 to extract the target features. RESULTS: Based on the target detection results, the Kalman filter is used to predict the next position and bounding box size of the target to obtain the target trajectory prediction results according to the current target position, then a hierarchical data association algorithm is designed, and multi-target tracking of the same category is completed based on the target appearance feature similarity and feature similarity. CONCLUSION: The experimental results show that the method can accurately detect the targets in multi-frame video images in basketball sports and obtain high-precision target trajectory tracking results.

Collision-Free Trajectory Planning for a 6-DoF Free-Floating Space Robot via Hierarchical Decoupling Optimization

Collision-free trajectory planning is a critical technique for space robot mission. In this letter, we developed a model-free Hierarchical Decoupling Optimization (HDO) algorithm to realize 6D-pose multi-target trajectory planning for the free-floating space robot. In order to reduce the complexity of exploration, the whole system consists of two layers: the high-level policy completes the collision-free trajectory planning of the end-effector’s pose; the low-level policy divides the task of reaching arbitrary pose into two decoupling sub-tasks (position and orientation) within a large target space. By introducing the Hindsight Experience Replay (HER), we successfully trained two agents based on multi-goal reinforcement learning. We proposed an Event-based Alternating Optimization (EAO) to stabilize the training and efficiently approximate the optimal policy. Theoretical analysis shows EAO can guarantee the learning stability and reachability of the equilibrium point. The simulation results illustrate that the proposed algorithm achieves high environmental adaptability and anti-disturbance capacity. Furthermore, we demonstrated our proposed method in a practical space mission by applying it to capture a target satellite. Qualitative results (videos) are available at 1.

UAV monitoring and forecasting model in intelligent traffic oriented applications

Intelligent transportation system is a traffic management system developed with the progress of society and traffic. Its idea is to integrate the real-time operation of people, vehicles, roads and traffic involved in the traffic. The purpose of this paper is to build a safe, reliable and efficient vehicle monitoring and forecasting model for IOT. Based on the Beidou satellite positioning technology and Lora communication technology, aiming at the problem that the deep learning detection method cannot meet the real-time requirements in processing the monitoring video, this paper proposes a method of using multiple single target trackers instead of some yolov3 detection tasks, and puts forward the design idea and specific implementation scheme of the vehicle monitoring and prediction model. The vehicle monitoring and prediction model is used to detect four kinds of targets, namely, small cars, buses, trucks and pedestrians. The multi-target trajectory tracking is used to carry out the traffic statistics of multi vehicle types, the detection of two kinds of abnormal behaviors of traffic targets is low speed and parking, and the capture of pedestrians. The experimental results show that the vehicle monitoring and prediction model has the highest accuracy of location and type recognition for four types of traffic objects, namely, small cars, trucks, buses and pedestrians, reaching 80%.

Spatio-Temporal Alignment and Trajectory Matching for Netted Radar Without Prior Spatial Information and Time Delay

For netted radars, a new alignment algorithm without prior spatial information (i.e., locations and attitudes of radars) and time delay is proposed to keep the spatio-temporal alignment. The unknown parameters to be estimated include the rotation matrix, the translation vector and the delay between radar stations in this paper. The minimum error function in unified space and time coordinate system is established based on the target trajectory measured by each radar. Firstly, the alternating spatio-temporal alignment method is used to estimate the spatial and temporal parameters, and its statistical performance is compared to the Cramer-Rao bound. Even under severe conditions in which each radar in the network can only observe part of the trajectory, the proposed algorithm can still be adopted to estimate the alignment parameters and complete the trajectory. Then, a trajectory matching algorithm based on random sample consensus (RANSAC) is proposed for multitarget. The corresponding relationship between trajectories is established through minimizing sum of paired trajectory error, and multitarget trajectories from each radar are matched. Finally, the spatio-temporal parameters are refined by all matched trajectory pairs. Simulation results show that the tracking information from different radars is transformed into a unified coordinate after spatio-temporal alignment. Moreover, the registration error is reduced and the tracking accuracy is improved.

Sequential Monte Carlo Cardinalized probability hypothesized density filter based on Track-Before-Detect for fluctuating targets in heavy-tailed clutter

In this paper, a Sequential Monte Carlo Cardinalized Probability Hypothesized Density (SMC-CPHD) filter based on Track-Before-Detect (TBD) algorithm in heavy-tailed clutter is proposed. The CPHD filter, which jointly propagates the first-order statistical moment and cardinality distribution, is an effective and efficient solution to multitarget filter problem in the presence of data association uncertainty, detect uncertainty, and time-varying. The TBD algorithm is extremely sensitive to the presence of clutter spikes in the data as the formulation of the TBD filter is dependent on knowledge of underlying clutter behavior. Therefore, the clutter is modeled in terms of K distribution with sea surface background and G0 distribution with primary forest background, while the popular Swerling targets of type 1 and 3 are considered to capture the target amplitude fluctuation frame-to-frame in this paper. The utilization of K distribution and G0 distribution clutter models instead of conventional Rayleigh distribution are verified through analysis of simulated and realistic data. The relevant results prove that proposed SMC-CPHD-TBD algorithm based on K distribution model and G0 distribution model can improve the detect and tracking performance over the conventional method in heavy-tailed clutter scenario. Additionally, the numerical simulations show that proposed CPHD-TBD algorithm can output the multitarget trajectories in the better precision with considerably less computational complexity compared with DP-TBD algorithm.

Effect of perturbations on debris-to-debris orbital transfers: A quantitative analysis

We investigated the applicability of the Lambert solver (Izzo, 2014) for preliminary design of Multi-Target Active Debris Removal missions. Firstly, we computed ≈25 million debris-to-debris transfers using the Lambert solver for selected sets of debris objects in Low Earth Orbit, Geostationary Transfer Orbit, and Geosynchronous Orbit. Subsequently, we propagated the departure states of the Lambert transfers below selected ΔV cut-offs using the SGP4/SDP4 propagator (Vallado et al., 2006). We recorded the arrival position and velocity error vectors incurred by neglecting perturbations and analyzed the results for each orbital regime. Our results indicate that perturbations can play a significant role in determining the feasibility of debris-to-debris transfers. By using the Lambert solver and neglecting perturbations, the errors in the arrival position and velocity for individual legs can be large. The largest errors were obtained for transfers between debris objects in Sun-Synchronous Orbit (O(100) km error in magnitude of position vector and O(0.1) km/s error in magnitude of velocity vector). Hence, solely employing the Lambert solver to rank transfer legs could lead to incorrect choices for sequencing of multi-target trajectories. This is particularly relevant for transfers in Low Earth Orbit, where the effects of perturbations are the strongest.

Multi-target tracking via hierarchical association learning

To deal with the issue of multi-target tracking, this paper proposes a hierarchical correlation multi-target tracking trajectory generation method. On the basis of target detection results, the AdaBoost algorithm combined with online discriminant analysis apparent model is first utilized to achieve initial moving object tracking trajectories; then, the Hungarian algorithm is utilized to optimize fragmented and discontinuous tracking trajectories to achieve stable and accurate trajectories fragments; finally, energy minimization based intelligent extrapolation algorithm is utilized to achieve final smoother and continuous tracking trajectories. Experimental results on PETS 2009/2010 benchmark and TUD-Stadtmitte video database demonstrate the effectiveness and efficiency of the proposed method.

Von Mises Mixture PHD Filter

This letter deals with the problem of tracking multiple targets on the unit circle, a problem that arises whenever the state and the sensor measurements are circular, i.e. angular-only, random variables. To tackle this problem, we propose a novel mixture approximation of the probability hypothesis density filter based on the von Mises distribution, thus constructing a method that globally captures the non-Euclidean nature of the state and the measurement space. We derive a closed-form recursion of the filter and apply principled approximations where necessary. We compared the performance of the proposed filter with the Gaussian mixture probability hypothesis density filter on a synthetic dataset of 100 randomly generated multitarget trajectory examples corrupted with noise and clutter, and on the PETS2009 dataset. We achieved respectively a decrease of 10.5% and 2.8% in the optimal subpattern assignement metric (notably 16.9% and 10.8% in the localization component).

A new data association algorithm using probability hypothesis density filter

Probability Hypothesis Density (PHD) filtering approach has shown its advantages in tracking time varying number of targets even when there are noise, clutter and misdetection. For linear Gaussian Mixture (GM) system, PHD filter has a closed form recursion (GMPHD). But PHD filter cannot estimate the trajectories of multi-target because it only provides identity-free estimate of target states. Existing data association methods still remain a big challenge mostly because they are computationally expensive. In this paper, we proposed a new data association algorithm using GMPHD filter, which significantly alleviated the heavy computing load and performed multi-target trajectory tracking effectively in the meantime.

A maximum likelihood approach to data association

An approach is presented to data association (DA) problems for which measurements are independent from scan to scan. It is demonstrated that maximum likelihood (ML) estimation of target parameters may be efficiently implemented by an EM iterative scheme. The algorithm is applied to multitarget trajectory estimation of constant-velocity targets from passive (bearing-only) sensors.< <ETX xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">&gt;</ETX>

Detection of target trajectories using the Hough transform

Recently developed Hough transform techniques for curved object detection are applied to the detection of target trajectories. Multitarget missile trajectories are considered with noise present and missing data.

Deterministic optimal maneuver strategy for multi-target missions

This paper presents an optimal strategy for making impulsive correction to a multi-target trajectory by a single maneuver. The concept of an optimal maneuver time is introduced. The choice of suitable weighting functions is explored to enable one to properly translate the subjective desire of mission success into an objective cost function whose minimization yields the optimal strategy. It is shown that a number of strategies previously formulated are derivable from one general expression. A number of other interesting properties of the optimal strategy are described. Numerical results are presented for a typical two-target mission. It is shown that the strategy formulated is optimal. For some perturbations, there exists an optimal maneuver time different from the time of initiation of the perturbation. That is, the physical properties of the trajectory can be exploited to select the optimal time of making a corrective maneuver.