CERES :: Browsing by Author "He, Shaoming"

Browsing by Author "He, Shaoming"

Now showing 1 - 20 of 31

Open Access
Behavior monitoring using learning techniques and regular-expressions-based pattern matching
(IEEE, 2018-08-02) Shin, Hyosang; Turchi, Dario; He, Shaoming; Tsourdos, Antonios
This paper addresses the problem of maneuver recognition and behavior anomaly detection for generic targets by means of pattern matching techniques. The problem analysis is performed making specific reference to moving vehicles in a multi-lane road scenario, but the proposed technique can be easily extended to significantly different monitoring contexts. The potential extensions include, but are not limited to, public surveillance in train station or airport, road incidents and relative precursors detection, and vehicle trajectories monitoring. The overall proposed solution consists of a trajectory analysis tool and a string-matching method. This allows the integration of two different approaches, to detect both a priori defined patterns of interest and generic maneuver/behavior standing out from those regularly exhibited. The proposed string matching algorithm is newly developed in this paper, based on Regular Expressions. For generating reference patterns, a technique for the automatic definition of a dictionary of regular expressions matching the commonly observed target maneuvers is developed. The advantages of the proposed approach are extensively analyzed and tested by means of numerical simulations and experiments.
Open Access
Composite finite‐time convergent guidance law for maneuvering targets with second‐order autopilot lag
(Wiley, 2018-09-21) Wu, Junxiong; Wang, Hui; He, Shaoming; Lin, Defu
This paper aims to develop a new finite‐time convergent guidance law for intercepting maneuvering targets accounting for second‐order autopilot lag. The guidance law is applied to guarantee that the line of sight (LOS) angular rate converges to zero in finite time and results in a direct interception. The effect of autopilot dynamics can be compensated based on the finite‐time backstepping control method. The time derivative of the virtual input is avoided, taking advantage of integral‐type Lyapunov functions. A finite‐time disturbance observer (FTDOB) is used to estimate the lumped uncertainties and high‐order derivatives to improve the robustness and accuracy of the guidance system. Finite‐time stability for the closed‐loop guidance system is analyzed using the Lyapunov function. Simulation results and comparisons are presented to illustrate the effectiveness of the guidance strategy.
Open Access
Computational guidance using sparse Gauss-Hermite quadrature differential dynamic programming
(Elsevier, 2019-11-25) He, Shaoming; Shin, Hyo-Sang; Tsourdos, Antonios
This paper proposes a new computational guidance algorithm using differential dynamic programming and sparse Gauss-Hermite quadrature rule. By the application of sparse Gauss-Hermite quadrature rule, numerical differentiation in the calculation of Hessian matrices and gradients in differential dynamic programming is avoided. Based on the new differential dynamic programming approach developed, a three-dimensional computational algorithm is proposed to control the impact angle and impact time for an air-to-surface interceptor. Extensive numerical simulations are performed to show the effectiveness of the proposed approach.
Open Access
Computational missile guidance: a deep reinforcement learning approach
(AIAA, 2021-06-28) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios;
This paper aims to examine the potential of using the emerging deep reinforcement learning techniques in missile guidance applications. To this end, a Markovian decision process that enables the application of reinforcement learning theory to solve the guidance problem is formulated. A heuristic way is used to shape a proper reward function that has tradeoff between guidance accuracy, energy consumption, and interception time. The state-of-the-art deep deterministic policy gradient algorithm is used to learn an action policy that maps the observed engagements states to a guidance command. Extensive empirical numerical simulations are performed to validate the proposed computational guidance algorithm.
Open Access
Constrained multiple model bayesian filtering for target tracking in cluttered environment
(Elsevier, 2017-10-18) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This paper proposes a composite Bayesian filtering approach for unmanned aerial vehicle trajectory estimation in cluttered environments. More specifically, a complete model for the measurement likelihood function of all measurements, including target-generated observation and false alarms, is derived based on the random finite set theory. To accommodate several different manoeuvre modes and system state constraints, a recursive multiple model Bayesian filtering algorithm and its corresponding Sequential Monte Carlo implementation are established. Compared with classical approaches, the proposed method addresses the problem of measurement uncertainty without any data associations. Numerical simulations for estimating an unmanned aerial vehicle trajectory generated by generalised proportional navigation guidance law clearly demonstrate the effectiveness of the proposed formulation.
Open Access
Convexification in energy optimization of a hybrid electric propulsion system for aerial vehicles
(Elsevier, 2022-03-30) Xie, Ye; He, Shaoming; Savvaris, Al; Tsourdos, Antonios; Zhang, Dan; Xie, Anhuan
This paper concerns the energy management of a hybrid electric propulsion system for aerial vehicles, using convex optimization. The main contribution of this paper is the proposal of a new convexification, which simplifies the formation of the convexified problem, and the proof of equality between the original problem and the convexified problem. The primary energy management is formulated from first principles and using experimental data. The convexity of the original problem is clarified via investigating the approximation to the experimental data. Then, change of variables and equality relaxation are implemented to convexify the concave constraints. The introduced variable—battery internal energy, is proposed to convexify the battery model. The relaxation of a non-affine equality yields to new convex inequality constraints. Numerical examples and forward simulations were carried out to validate the convexified problem. The first test case verifies that the convex relaxation does not sacrifice the optimality of the solution nor does the variable change lose the original bounds. Also, the optimal control from convex optimization is demonstrated to be robust to a disturbance in power demand. Comparison with the benchmark optimization—dynamic programming, shows that convex optimization achieves a minimal objective value with less fluctuation of the optimal control value. Most significant is that the convexification reduces the optimization computation time to a level compatible with implementation in practical application.
Open Access
Distributed estimation over a low-cost sensor network: a review of state-of-the-art
(Elsevier, 2019-06-23) He, Shaoming; Shin, Hyosang; Xu, Shuoyuan; Tsourdos, Antonios
Proliferation of low-cost, lightweight, and power efficient sensors and advances in networked systems enable the employment of multiple sensors. Distributed estimation provides a scalable and fault-robust fusion framework with a peer-to-peer communication architecture. For this reason, there seems to be a real need for a critical review of existing and, more importantly, recent advances in the domain of distributed estimation over a low-cost sensor network. This paper presents a comprehensive review of the state-of-the-art solutions in this research area, exploring their characteristics, advantages, and challenging issues. Additionally, several open problems and future avenues of research are highlighted.
Open Access
Distributed joint probabilistic data association filter with hybrid fusion strategy
(IEEE, 2019-02-20) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This paper investigates the problem of distributed multitarget tracking (MTT) over a large-scale sensor network, consisting of low-cost sensors. Each local sensor runs a joint probabilistic data association filter to obtain local estimates and communicates with its neighbors for information fusion. The conventional fusion strategies, i.e., consensus on measurement (CM) and consensus on information (CI), are extended to MTT scenarios. This means that data association uncertainty and sensor fusion problems are solved simultaneously. Motivated by the complementary characteristics of these two different fusion approaches, a novel distributed MTT algorithm using a hybrid fusion strategy, e.g., a mix of CM and CI, is proposed. A distributed counting algorithm is incorporated into the tracker to provide the knowledge of the total number of sensor nodes. The new algorithm developed shows advantages in preserving boundedness of local estimates, guaranteeing global convergence to the optimal centralized version and being implemented without requiring no global information, compared with other fusion approaches. Simulations clearly demonstrate the characteristics and tracking performance of the proposed algorithm.
Open Access
Distributed multiple model joint probabilistic data association with Gibbs sampling-aided implementation
(Elsevier, 2020-05-15) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This paper proposes a new distributed multiple model multiple manoeuvring target tracking algorithm. The proposed tracker is derived by combining joint probabilistic data association (JPDA) with consensus-based distributed filtering. Exact implementation of the JPDA involves enumerating all possible joint association events and thus often becomes computationally intractable in practice. We propose a computationally tractable approximation of calculating the marginal association probabilities for measurement-target mappings based on stochastic Gibbs sampling. In order to achieve scalability for a large number of sensors and high tolerance to sensor failure, a simple average consensus algorithm-based information JPDA filter is proposed for distributed tracking of multiple manoeuvring targets. In the proposed framework, the state of each target is updated using consensus-based information fusion while the manoeuvre mode probability of each target is corrected with measurement probability fusion. Simulations clearly demonstrate the effectiveness and characteristics of the proposed algorithm. The results reveal that the proposed formulation is scalable and much more efficient than classical JPDA without sacrificing tracking accuracy
Open Access
Distributed target tracking over a low-cost sensor network.
(2019-09) He, Shaoming; Shin, Hyo-Sang; Tsourdos, Antonios
Proliferation of low-cost, lightweight, and power efficient sensors and advances in networked systems enable the employment of multiple sensors. Distributed estimation provides a scalable and fault-robust fusion framework with a peer-to-peer communication architecture. This thesis investigates the problem of distributed target(s) tracking over a low-cost sensor network and proposes several efficient and reliable algorithms to address the aforementioned problem. The primary issue of using low-cost sensors in distributed target tracking is how to balance between communication cost and convergence performance. To overcome this difficulty, we develop a new sample greedy gossip distributed Kalman filter for distributed single-target tracking over a low-cost sensor network. The proposed algorithm leverages the information weighted fusion concept and a new sample greedy gossip process. Instead of finding the optimal path of each node in a greedy manner, the proposed approach utilises a suboptimal communication path by performing greedy selection among randomly selected active sensor nodes. Theoretical convergence analysis and uniform boundedness are also performed to support the proposed algorithm. The main feature of the new algorithm is that it provides fast convergence rate with relatively low communication overload. In distributed multi-target tracking, each sensor node runs a local multi-target tracking filter for multi-target state and identity estimation. The issue of current multi-target tracking algorithms is that they usually suffer from exponential complexity and require prior knowledge on the environment, e.g., target detection probability and clutter rate. This hinders the application of low-cost sensors in multi-target tracking as these sensors usually have limited computational capability and offline calibration is also not cost-effective. To address these sensor-related practical issues, we propose a polynomial-time joint probabilistic data association filter using stochastic Gibbs sampling technique and incorporate it with a multi-Bernoulli filter to accommodate the unknown environmental parameters. It is theoretically proved that the proposed solution provides a performance-guaranteed approximation and is demonstrated to show promising performance in a dynamic environment. We then consider the problem of accurate Gaussian mixture approximation for implementing joint probabilistic data association filter when targets are moving closely and propose a novel information-driven approach to tackle this problem. The proposed information-driven joint probabilistic data association algorithm is obtained from the minimisation of a weighted Kullback-Leibler divergence to approximate the posterior Gaussian mixture probability density function. The resulting approximation approach turns out to show similar structure as the generalised covariance intersection in sensor fusion. Theoretical analysis reveals that the proposed approach with ideal detection probability guarantees boundedness of the error covariance and yields unbiased estimation. Different from single-target tracking, local multi-target estimations contain data association uncertainty and therefore this issue requires careful adjustment in sensor fusion. Through an equivalent information form, we extend conventional fusion strategies, i.e., consensus on measurement and consensus on information, to multi-target tracking scenarios using joint probabilistic data association filter. This means that data association uncertainty and sensor fusion problems are solved simultaneously. Motivated by the complementary characteristics of these two different fusion approaches, a novel distributed multi-target tracking algorithm using a hybrid fusion strategy, e.g., a mix between consensus on measurement and consensus on information, is proposed. A distributed counting algorithm is incorporated into the tracker to provide the knowledge of the total number of sensor nodes. The new algorithm developed shows advantages in preserving boundedness of local estimates, guaranteeing global convergence to the optimal centralised version and being implemented without requiring global information, compared with other fusion approaches. To support the implementation of distributed multi-target tracking, we finally investigate the problem of practical implementation of multi-dimensional assignment. To address this problem, we propose two efficient implementation algorithms using Tabu search and Gibbs sampling. As the rst step, we formulate the problem of generating the best global hypothesis in multi-dimensional assignment as the problem of finding a maximum weighted independent set of a weighted undirected graph. Then, the meta-heuristic Tabu search with two basic movements is designed to find the global optimal solution of the problem formulated. To improve the computational efficiency, we also develop a sampling based algorithm using Gibbs sampling. The problem formulated for the Tabu search based algorithm is reformulated as a max product problem to enable implementation of Gibbs sampling. The detailed algorithm is then designed and the convergence is also theoretically analysed. The performance of the two algorithms proposed are verified through nu-merical simulations and compared with that of a mainstream Lagrangian relaxation implementation algorithm.
Open Access
Dynamic knowledge-based tracking and autonomous anomaly detection
(IEEE, 2023-11-28) Chai, Jianduo; He, Shaoming; Shin, Hyo-Sang; Tsourdos, Antonios
This paper presents a study on the problem of region surveillance in complex terrain using an unmanned aerial vehicle (UAV), and proposes a novel framework for on-road ground target tracking and detection of anomalous driving behavior with the assistance of domain-constrained information. In order to improve the accuracy of ground target tracking, terrain information is extracted and incorporated as constraints into the tracking process. To account for the dynamic changes in terrain-constrained information, a sliding window approach leveraging a dynamic programming algorithm is employed for domain-constrained knowledge inference. To improve the autonomy and intelligence of the monitoring UAV, a mechanism for recognizing suspicious driving patterns is seamlessly integrated into the target tracking process with the aid of domain knowledge. The effectiveness of proposed method is validated using extensive numerical simulations.
Open Access
Energy-optimal waypoint-following guidance considering autopilot dynamics
(IEEE, 2019-11-28) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios; Lee, Chang-Hun
This paper addresses the problem of energy-optimal waypoint-following guidance for an Unmanned Aerial Vehicle with the consideration of a general autopilot dynamics model. The proposed guidance law is derived as a solution of a linear quadratic optimal control problem in conjunction with a linearized kinematics model. The algorithm developed integrates path planning and following into a single step and is able to be applied to a general waypoint-following mission. Theoretical analysis reveals that previously suggested optimal point-to-point guidance laws are special cases of the proposed approach. Nonlinear numerical simulations clearly demonstrate the effectiveness of the proposed formulations.
Open Access
Game-theoretic flexible-final-time differential dynamic programming using Gaussian quadrature
(AIAA, 2022-11-28) Zheng, Xiaobo; Guan, Haodong; Lin, Defu; He, Shaoming; Shin, Hyosang
Open Access
Gravity-turn-assisted optimal guidance law
(AIAA, 2017-07-31) He, Shaoming; Lee, Chang-Hun
This paper proposes a new optimal guidance law that directly uses (instead of compensating for) gravity for accelerating missiles. The desired collision triangle that considers both gravity and the vehicle’s axial acceleration is analytically derived based on geometric conditions. The concept of instantaneous zero-effort-miss is introduced to allow for analytical guidance command derivation. By formulating a finite time instantaneous zero-effort-miss regulation problem, the proposed optimal guidance law is derived through Schwarz’s inequality approach. The relationships of the proposed formulation with conventional proportional navigation guidance and guidance-to-collision are analyzed, and the results show that the proposed guidance law encompasses previously suggested approaches. The significant contribution of the proposed guidance law lies in that it ensures zero final guidance command and enables energy saving with the aid of using gravity turn. Nonlinear numerical simulations clearly demonstrate the effectiveness of the proposed approach.
Open Access
Information-theoretic joint probabilistic data association filter
(IEEE, 2021-03-03) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This article proposes a novel information-theoretic joint probabilistic data association filter for tracking unknown number of targets. The proposed information-theoretic joint probabilistic data association algorithm is obtained by the minimization of a weighted reverse Kullback–Leibler divergence to approximate the posterior Gaussian mixture probability density function. Theoretical analysis of mean performance and error covariance performance with ideal detection probability is presented to provide insights of the proposed approach. Extensive empirical simulations are undertaken to validate the performance of the proposed multitarget tracking algorithm.
Open Access
Integral global sliding mode guidance for impact angle control
(IEEE, 2018-10-18) He, Shaoming; Lin, Defu; Wang, Jiang
This Correspondence proposes a new guidance law based on integral sliding mode control (ISMC) technique for maneuvering target interception with impact angle constraint. A time-varying function weighted line-of-sight (LOS) error dynamics, representing the nominal guidance performance, is introduced first. The proposed guidance law is derived by utilizing ISMC to follow the desired error dynamics. The convergence of the guidance law developed is supported by Lyapunov stability. Simulations with extensive comparisons explicitly demonstrate the effectiveness of the proposed approach.
Open Access
Joint probabilistic data association filter with unknown detection probability and clutter rate
(MDPI, 2018-01-18) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This paper proposes a novel joint probabilistic data association (JPDA) filter for joint target tracking and track maintenance under unknown detection probability and clutter rate. The proposed algorithm consists of two main parts: (1) the standard JPDA filter with a Poisson point process birth model for multi-object state estimation; and (2) a multi-Bernoulli filter for detection probability and clutter rate estimation. The performance of the proposed JPDA filter is evaluated through empirical tests. The results of the empirical tests show that the proposed JPDA filter has comparable performance with ideal JPDA that is assumed to have perfect knowledge of detection probability and clutter rate. Therefore, the algorithm developed is practical and could be implemented in a wide range of applications
Open Access
Learning prediction-correction guidance for impact time control
(Elsevier, 2021-10-28) Liu, Zichao; Wang, Jiang; He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This paper investigates the problem of impact-time-control and proposes a learning-based computational guidance algorithm to solve this problem. The proposed guidance algorithm is developed based on a general prediction-correction concept: the exact time-to-go under proportional navigation guidance with realistic aerodynamic characteristics is estimated by a deep neural network and a biased command to nullify the impact time error is developed by utilizing the emerging reinforcement learning techniques. To deal with the problem of insufficient training data, a transfer-ensemble learning approach is proposed to train the deep neural network. The deep neural network is augmented into the reinforcement learning block to resolve the issue of sparse reward that has been observed in typical reinforcement learning formulation. Extensive numerical simulations are conducted to support the proposed algorithm.
Open Access
Minimum-effort waypoint-following guidance
(AIAA, 2019-01-30) He, Shaoming; Lee, Changhun; Shin, Hyosang; Tsourdos, Antonios
This paper addresses the problem of minimum-effortwaypoint-following guidance with/without arrival angle constraints of an Unmanned Aerial Vehicle. By utilizing a linearized kinematics model, the proposed guidance laws are derived as the solutions of a linear quadratic optimal control problem with an arbitrary number of terminal boundary constraints. Theoretical analysis reveals that both optimal proportional navigation guidance and trajectory shaping guidance are special cases of the proposed guidance laws. The key feature of the proposed algorithms lies in their generic property. For this reason, the guidance laws developed can be applied to general waypoint-following missions with an arbitrary number of waypoints and an arbitrary number of arrival angle constraints. Nonlinear numerical simulations clearly demonstrate the effectiveness of the proposed formulations.
Open Access
Multi-sensor multi-target tracking using domain knowledge and clustering
(IEEE, 2018-08-03) He, Shaoming; Shin, Hyosang; Tsourdos, Antonios
This paper proposes a novel joint multi-target tracking and track maintenance algorithm over a sensor network. Each sensor runs a local joint probabilistic data association (JPDA) filter using only its own measurements. Unlike the original JPDA approach, the proposed local filter utilises the detection amplitude as domain knowledge to improve the estimation accuracy. In the fusion stage, the DBSCAN clustering in conjunction with statistical test is proposed to group all local tracks into several clusters. Each generated cluster represents the local tracks that are from the same target source and the global estimation of each cluster is obtained by the generalized covariance intersection (GCI) algorithm. Extensive simulation results clearly confirms the effectiveness of the proposed multisensor multi-target tracking algorithm.