Target Trajectory Research Articles

Dynamic surface control for formation control of quadrotors with input constraints and disturbances

In this paper, a novel formation control scheme is presented by integrating the dynamic surface control for multi-quadrotor subject with model uncertainties and external disturbances. First, according to requirements of formation control, the target trajectories of followers are obtained by the designed virtual quadrotors. Then, the formation control problem is transformed into the trajectory tracking control problem. Second, the saturation function and the auxiliary system are developed to make up for nonlinear terms arising from input saturation. A nonlinear extended state observer (ESO) is proposed to estimate and compensate for model uncertainties and external disturbances, and a dynamic surface controller based on the nonlinear ESO is constructed for the desired formation performance. In addition, the amount of communications between the quadrotors is decreased by the constructed distributed speed estimator. And the uniformly ultimately bounded is proved by using the Lyapunov method. Finally, the numerical example is used to demonstrate that the designed controller is effective.

Deep reinforcement learning for cognitive active-sonar employment

We introduce a framework to leverage deep reinforcement learning (RL) for active sonar employment, wherein we train an RL agent to select waveform parameters, which maximize the probability of single-target detection. We first simulate raw sonar returns of targets and clutter in reverberation and noise using a physics-based sonar-simulation model, the Sonar Simulation Toolkit (SST), then process the resulting signatures into network inputs via an in-house signal and information processing model of an archetypal antisubmarine warfare (ASW) processing chain. We demonstrate that the trained RL agent is able to appropriately select between continuous wave (CW) and hyperbolic frequency modulated (HFM) waveforms depending on target trajectory, as well as select an optimal bandwidth and pulse length trade-off (when constrained by a constant time-bandwidth product), when presented with sonar returns from a reverb-limited or noise-limited environment.

A Two-Stage Mass-to-drag Ratio Estimation Algorithm for Reentry Vehicles

Abstract Ballistic target tracking and identification is a key task for missile defense systems. A vital problem in ballistic target identification is how to estimate the target mass-to-drag ratio fast and accurately. The reentry phase of a ballistic missile is the last stage of its flight, and the reentry trajectory is significantly affected by the atmospheric drag. Based on the constraints of space flight dynamics, this paper proposes a two-stage algorithm to estimate the mass-to-drag ratio. This algorithm first estimates the position and velocity of the target in the free flight stage by using the least-squares method, and then estimates the mass-to-drag ratio of the target by using the radial range measurements from the reentry stage. Several trajectories of a ballistic target under different mass-to-drag ratios are simulated, and the proposed algorithm is verified using these simulated trajectories.

A control architecture to coordinate energy management with trajectory tracking control for fuel cell/battery hybrid unmanned aerial vehicles

Fuel cell/battery hybrid energy storage system (HESS) powered unmanned aerial vehicle (UAV) has the outstanding advantage of long endurance time. Trajectory tracking motion is a commonly used task execution mode of UAVs, especially in autonomous UAVs. This study aims at developing a control architecture to coordinate energy management with trajectory tracking control for fuel cell/battery hybrid UAVs. Its position tracking control adopts model predictive control (MPC) and an extended state observer to eliminate the modeling errors and effect of interference. The attitude tracking control adopts an auto-disturbance rejection controller having a quick response. The obtained control parameters are given as an input to the energy management block. Energy management strategies (EMSs) based on online dynamic programming and hierarchical MPC have been proposed. The results obtained from a simulation show that the proposed trajectory tracking control architecture can track the target trajectory stably with a small tracking error. The tracking performance is stable under interference. Experimental results show that dynamic programming is solved online with good control performance. Compared to ordinary EMSs, dynamic programming and hierarchical MPC can increase endurance time by 2.69% and 1.27%, respectively. The proposed control architecture verifies the coordination of energy management and trajectory tracking control, and prospected the advantages of the combination of fuel cell and autonomous driving for long endurance UAVs in the future.

Target depth estimation by deep neural network based on acoustic interference structure in deep water

Automatic and robust target depth estimation is an important issue of an active detection system working in the reliable acoustic path (RAP) environment. In this paper, the target depth-sensitive acoustic interference structure is used as input, and a deep neural network (DNN) method is proposed to realize automatic depth estimation. Furthermore, to improve the robustness of the network, both the sound speed profile (SSP) uncertainty and the target trajectory uncertainty are considered in the training dataset. The former is modelled as a random weighted sum of the empirical orthogonal function (EOF), and the latter is modelled by the partial-data-lacking of the network input. The method was evaluated through simulated data and compared with the conventional method of matching the measured interference structure with the replicas. The presented method exhibits a higher accuracy of depth estimate in uncertain environments when the signal-to-noise ratio (SNR) is higher than −6 dB, but its performance deteriorates rapidly as the SNR decreases further. The method is also verified by semi-simulation with experimental data in deep water.

Nuclear Reactor Power Level Model Predictive Control: A Consideration of Coolant Outlet Temperature Relaxation Tracking Method

Nuclear reactor core power level control and the average coolant temperature usually adopt independent control strategies, but tracking only one single core power makes the coolant temperature control risky in a disturbance situation. To solve this problem, a reference trajectory calculation based on the coolant outlet temperature under the steady state of the reactor power is designed; then, a model predictive controller with a dual objective optimization function, which also includes a relaxation factor, is constructed. By setting the tracking weight matrix in the controller, the tendency setting of dual target trajectory tracking can be realized. Simulation experiments verify the effectiveness of core power level control considering the coolant outlet temperature trajectory tracking. Furthermore, the tracking effect of different weight matrices is simulated and analyzed. The results show that the developed control strategy is more flexible than a single control scheme.

One-DOF six-bar space gripper with multiple operation modes and force adaptability

For complex space tasks, the gripper is expected to adapt to items of different shapes and sizes; it has the advantages of simple control and acceptable force adaptability. Therefore, a one degree of freedom (DOF) six-bar space gripper with good task adaptability is developed. Design constraints are analyzed on the basis of typical grasping task analysis. A design method based on proportional coefficients is proposed, considering that the constraints are complex and the six-bar mechanism has many design parameters. The design efficiency can be improved by reducing the target trajectory according to proportional coefficients. The one-DOF six-bar mechanism that satisfies the final constraints has multiple operation modes with only one drive. On this basis, the elastic element is added as part of the mechanism rather than outside the mechanism, and a rigid-flexible coupling mechanical model is established to further analyze the effect of elastic element on the force adaptability. Experiments show that the designed one-DOF gripper can grasp cylinders with different diameters and grasp and move items of different sizes with fingertips under different space constraints; it also has good force adaptability. This finding provides a reference for reducing the complexity of gripper and improving the diversity of grasping task.

Autonomous Navigation and Control System for Capturing A Moving Drone

This paper describes an autonomous navigation and control system for capturing the maneuvering drones. A vision-based navigation method seeks and detects the intruding drone, then, the target trajectory is predicted by fusing onboard vision and inertial-measurement resources. The target’s relative position, velocity and acceleration are also obtained at the same time. Then, we present a modified proportional-derivative (PD) algorithm based on the estimated target states. In addition, the boundary constraints of the protected area are considered to avoid a collision. The proposed capture navigation and control system has demonstrated its efficiency both in simulation, flight experiments, and MBZIRC 2020, where our team won the Challenge I competition.

Pseudo-spectral optimization and data-driven control of vehicle start process with dual-clutch transmission

In this study, a dual-clutch transmission start control strategy based on pseudo-spectral optimization and data-driven control is proposed to respond to the time-varying start intentions, to reduce friction and jerk, and to improve the start quality. First, taking the jerk, start time, and friction work as the optimization indexes, the adaptive pseudo-spectral method is used to accurately determine the optimal clutch engagement target trajectory. Then, a real-time planning method for the target clutch engagement trajectory is proposed based on a dual deep gated recurrent unit network. Second, through partial least squares identification, a data-driven predictive control (DDPC) method based on the autoregressive with exogenous model is proposed. The model parameters are updated online by a multi-model filtering algorithm based on input and output data, allowing real-time adaptation to the system uncertainty and nonlinear characteristics. Simulations and experiments show that the proposed target clutch trajectory planning method can effectively respond to time-varying start intentions in real-time. In addition, the DDPC controller can adapt to the uncertainty and nonlinear characteristics of the system and, hence, improve the control accuracy.

Restored Action Generative Adversarial Imitation Learning from observation for robot manipulator

In this paper, a new imitation learning algorithm is proposed based on the Restored Action Generative Adversarial Imitation Learning (RAGAIL) from observation. An action policy is trained to move a robot manipulator similar to a demonstrator’s behavior by using the restored action from state-only demonstration. To imitate the demonstrator, the trajectory is generated by Recurrent Generative Adversarial Networks (RGAN), and the action is restored from the output of the tracking controller constructed by the state and the generated target trajectory. The proposed imitation learning algorithm is not required to access the demonstrator’s action (internal control signal such as force/torque command) and provides better learning performances. The effectiveness of the proposed method is validated through the experimental results of the robot manipulator.

Adaptive integration of self-motion and goals in posterior parietal cortex.

SUMMARYRats readily switch between foraging and more complex navigational behaviors such as pursuit of other rats or prey. These tasks require vastly different tracking of multiple behaviorally significant variables including self-motion state. To explore whether navigational context modulates self-motion tracking, we examined self-motion tuning in posterior parietal cortex neurons during foraging versus visual target pursuit. Animals performing the pursuit task demonstrate predictive processing of target trajectories by anticipating and intercepting them. Relative to foraging, pursuit yields multiplicative gain modulation of self-motion tuning and enhances self-motion state decoding. Self-motion sensitivity in parietal cortex neurons is, on average, history dependent regardless of behavioral context, but the temporal window of self-motion integration extends during target pursuit. Finally, many self-motion-sensitive neurons conjunctively track the visual target position relative to the animal. Thus, posterior parietal cortex functions to integrate the location of navigationally relevant target stimuli into an ongoing representation of past, present, and future locomotor trajectories.

Fusion Siamese network with drift correction for target tracking in ultrasound sequences

Motion tracking techniques can revise the bias arising from respiration-caused motion in radiation therapy. Tracking key structures accurately and at a real-time speed is necessary for effective motion tracking. In this work, we propose a fusion Siamese network with drift correction for target tracking in ultrasound sequences. Specifically, the network fuses four response maps generated by the cross-correlation between convolution layers at different resolutions to reduce up-sampling error. A correction strategy combining local structural similarity and target trajectory is proposed to revise the target drift predicted by the network. Moreover, a coarse-to-fine strategy is proposed to train the network with a limited number of annotated images, in which an augmented dataset is generated by corner points to learn network features with high generalizability. The proposed method is evaluated on the basis of the public dataset of the MICCAI 2015 Challenge on Liver UltraSound Tracking (CLUST) and our ultrasound image dataset, which is provided by the Chinese People’s Liberation Army General Hospital (CPLAGH). A tracking error of 0.80 ± 1.16 mm is observed for 85 targets across 39 ultrasound sequences in the CLUST dataset. A tracking error of 0.61 ± 0.36 mm is observed for 20 targets across 10 ultrasound sequences in the CPLAGH dataset. The effectiveness of the proposed fusion and correction strategies is verified via two ablation experiments. Overall, the experimental results demonstrate the effectiveness of the proposed fusion Siamese network with drift correction and reveal its potential in clinical practice.

Online hierarchical recognition method for target tactical intention in beyond-visual-range air combat

Online accurate recognition of target tactical intention in beyond-visual-range (BVR) air combat is an important basis for deep situational awareness and autonomous air combat decision-making, which can create pre-emptive tactical opportunities for the fighter to gain air superiority. The existing methods to solve this problem have some defects such as dependence on empirical knowledge, difficulty in interpreting the recognition results, and inability to meet the requirements of actual air combat. So an online hierarchical recognition method for target tactical intention in BVR air combat based on cascaded support vector machine (CSVM) is proposed in this study. Through the mechanism analysis of BVR air combat, the instantaneous and cumulative feature information of target trajectory and relative situation information are introduced successively using online automatic decomposition of target trajectory and hierarchical progression. Then the hierarchical recognition model from target maneuver element, tactical maneuver to tactical intention is constructed. The CSVM algorithm is designed for solving this model, and the computational complexity is decomposed by the cascaded structure to overcome the problems of convergence and timeliness when the dimensions and number of training samples are large. Meanwhile, the recognition result of each layer can be used to support the composition analysis and interpretation of target tactical intention. The simulation results show that the proposed method can effectively realize multi-dimensional online accurate recognition of target tactical intention in BVR air combat.

Dynamic Programming Ring for Point Target Detection

To improve the detection efficiency of a long-distance dim point target based on dynamic programming (DP), this paper proposes a multi-frame target detection algorithm based on a merit function filtering DP ring (MFF-DPR). First, to reduce the influence of noise on the pixel state estimation results, a second-order DP named the MFF-DP is proposed. The current states of pixels on an image plane are estimated by maximizing the addition of the merit functions of the previous two frames and the observation data of the current frame. In addition, to suppress the diffusion of the merit function, the sequential and reverse observation data are connected in a head-to-tail manner to form a ring structure. The MFF-DP is applied to the ring structure, and the merit function of the MFF-DPR is obtained by averaging the merit functions of the sequential and reverse MFF-DPs. Finally, the target trajectory is obtained by correlating the extreme points of the merit functions of the MFF-DPR. The simulation and analysis results show that by merely adding a ring structure, the detection probability of the traditional DP can be improved by up to 40% when detecting point targets under the SNR of 1.8. The point target detection algorithm based on the MFF-DPR can achieve significantly better performance in point target detection compared with the traditional DPs with or without a ring structure. The proposed algorithm is suitable for radars and infrared point target detection systems.

Prescribed performance control of Euler–Lagrange systems tracking targets with unknown trajectory

The problem of tracking uncertain target is interesting and challenging. This paper studies the target tracking control problem of Euler–Lagrange system with unknown target trajectory. Fourier series and neural network are utilized to reconstruct the target trajectory, which is mathematically linked with the actual camouflaged target trajectory and facilitates the design and analysis. An error transformation function is introduced and embedded with the Lyapunov function, with which an adaptive tracking control scheme is developed. It is shown that such strategy is able to ensure the tracking error converging to a prescribed compact set containing the origin at a self-defined convergence rate. The simulation results verify the effectiveness of the proposed control method.

Cross-border acquisitions and R&D: Unpacking the impact on acquirers and targets

We study the post acquisition R&D of both targets and acquirers involved in cross-border acquisitions by developing and estimating a two equation model that explicitly accounts for cross-border knowledge flows. We employ a sample of 3,243 firm-year observations, representing 299 cross-border deals between 28 home and 34 host markets over 15 years. Results suggest that while the acquisition disrupts the R&D trajectory of both acquirers and targets, R&D complementarities result in more R&D in both acquirers and targets. However, these effects are asymmetrical: post-acquisition R&D increases are higher in the acquirer than in the target. The overall outcome of acquisitions appears to favor R&D in the acquirer.

Maneuvering target state estimation based on separate modeling with high-order polynomials

In some target tracking scenarios, the target motion is usually subject to various constraints. For a road-constrained target, the corresponding trajectory shape is independent to its dynamic characteristics due to the one-dimensional space of road. To exploit the knowledge of independence, this paper proposes a state estimation algorithm based on the separate modeling of target trajectory shape and dynamic characteristics, in which two versions based on different polynomials are considered. The idea of a sliding window is introduced, where a unique third- or second-degree polynomial with the coefficients to be estimated is used to model the target trajectory of each window. The unknown polynomial coefficients are augmented into the base state in the one-dimensional mileage coordinates and are estimated along with the base state. At every sampling period except the initial time, the proposed estimation algorithm starts the interaction stage with the previous updated base state of each filter and the modified parameter vector. The latter is determined by a least squares (LS) technique. Simulation results show that the two versions of the proposed algorithm achieve better performance than conventional estimation algorithms with coupled modeling.

Data Mining Algorithm for Moving Object Trajectory

Aiming at the poor effect and long recognition time of data mining algorithm for moving target trajectory recognition, a data mining algorithm based on improved Hausdorff distance is proposed. The position and angle of abnormal trajectory data are detected by calculating the distance between trajectory classification and sub trajectory line segments, and the trajectory unit is established by using the improved Hausdorff distance algorithm to optimize the similarity matching structure. Experimental results show that the algorithm has low error pruning rate in identifying moving target trajectory, improves the detection efficiency of moving target trajectory recognition data, and ensures the quality of moving target trajectory recognition data mining

Adaptive neural decentralised control for switched interconnected nonlinear systems with backlash-like hysteresis and output constraints

This paper considers the issue of adaptive neural decentralised tracking control for a class of output-constraint switched interconnected nonlinear systems with unknown backlash-like hysteresis control input. First, neural networks (NNs) are applied to approximate unknown nonlinear functions, and an NNs switched state observer is designed to estimate unmeasured system states. Then, the dynamic surface control technique is used to avoid the influence of explosion of complexity. In addition, the problem of output constraints is solved by introducing the barrier Lyapunov functions. Based on the Lyapunov stability theory, all signals in the switched closed-loop system can be verified to be uniformly ultimately bounded under the proposed control method. Moreover, the system output can track the target trajectory well within a small bounded error. Finally, a numerical simulation result is given to illustrate the effectiveness of the adaptive decentralised control scheme.

Bayesian Nonparametric Modeling for Predicting Dynamic Dependencies in Multiple Object Tracking.

The paper considers the problem of tracking an unknown and time-varying number of unlabeled moving objects using multiple unordered measurements with unknown association to the objects. The proposed tracking approach integrates Bayesian nonparametric modeling with Markov chain Monte Carlo methods to estimate the parameters of each object when present in the tracking scene. In particular, we adopt the dependent Dirichlet process (DDP) to learn the multiple object state prior by exploiting inherent dynamic dependencies in the state transition using the dynamic clustering property of the DDP. Using the DDP to draw the mixing measures, Dirichlet process mixtures are used to learn and assign each measurement to its associated object identity. The Bayesian posterior to estimate the target trajectories is efficiently implemented using a Gibbs sampler inference scheme. A second tracking approach is proposed that replaces the DDP with the dependent Pitman–Yor process in order to allow for a higher flexibility in clustering. The improved tracking performance of the new approaches is demonstrated by comparison to the generalized labeled multi-Bernoulli filter.