Space Non-cooperative Target Research Articles

Intention inference for space targets using deep convolutional neural network

Intention inference for space targets is crucial for space situational awareness. This paper introduces a rapid and precise method for recognizing the intentions of non-cooperative space targets using a deep convolutional neural network (CNN). By employing a relative orbital dynamics model, an analysis of relative motion was performed, resulting in the identification of 11 distinct motion intentions for space targets. This study also describes how to generate relative motion trajectory images to create a training set for intention inference, effectively converting the problem into one of image recognition and classification. Extensive simulations were carried out to fine-tune the network hyperparameters, and the results highlight the exceptional performance of the proposed CNN-based method, which achieved an accuracy of 99.682%. This method significantly enhances recognition accuracy over other neural network-based methods for space objects and offers considerable potential for applications like spacecraft collision avoidance and strategic maneuvers among space targets.

A Space Non-Cooperative Target Recognition Method for Multi-Satellite Cooperative Observation Systems

A Space Non-Cooperative Target Recognition Method for Multi-Satellite Cooperative Observation Systems

Recognition of precession angles of non-cooperative targets based on deep learning with privileged information

With an increasing number of countries engaging in space activities worldwide, space non-cooperative target tracking and identification technology has become a prerequisite for safely conducting space operations. In order to the identify distant non-cooperative targets performing complex motions, this paper proposes a method to recognize difficult parameters by using easily available signal labels as privileged information, which is named Pi-FcResNet. The privileged information is connected to the output end of the network through a fully connected network and coupled with the linear layer of the main network. Through testing, our network achieved a recognition accuracy of 94.45 % for precession angles under high signal-to-noise ratio conditions. After incorporating the Convolutional Block Attention Module (CBAM), our method demonstrates fast fitting speed and robust performance. Testing on experimental data shows that, compared to traditional methods, our approach offers better stability and reproducibility in recognizing micro-motion parameters. This approach of using known information as additional information for deep learning networks holds great potential in the field of feature extraction for space non-cooperative targets undergoing complex motions.

Reinforcement Learning-Based Pose Coordination Planning Capture Strategy for Space Non-Cooperative Targets

Reinforcement Learning-Based Pose Coordination Planning Capture Strategy for Space Non-Cooperative Targets

Design and workspace analysis of a cable-driven space capture robot for noncooperative targets

Capturing noncooperative targets in space has garnered continuous research interest in aerospace applications. This study addresses the demands of large-scale, multifaceted activities and varied working conditions for space capture missions by designing a space capture robot composed of multiple cable-driven manipulators operating in parallel. First, single- and multi-segment cable-driven robot models were designed, and a geometric model was subsequently built. The optimal number of segments was determined by analysing the condition number of a Jacobian matrix using the Monte Carlo method. Subsequently, based on the constant-curvature assumption, a kinematic model of the cable-driven space capture robot was formulated, and capture methods for different capture targets were designed using the Monte Carlo method. Finally, an eight-segment cable-driven robot prototype was developed, and compliance and driving experiments were conducted. This robot exhibits promising application potential for space noncooperative target capture and can be feasibly manufactured using on-orbit 3D machining technology.

Adaptive optimal concurrent control for detumbling space non-cooperative target via multipoint repeated contact

Space debris generally exhibits complex tumbling motions, and its direct capture may cause damage to space manipulator and base spacecraft. Current detumbling strategies typically require continuous contact collisions with the target and do not take into account actuator limitations. Thus, this paper presents an adaptive optimal concurrent control of space free-floating multi-fingered robot (SFMR) for multipoint repeated contact detumbling of non-cooperative targets. Firstly, the multipoint repeated intermittent contact model between the SFMR and the target is established. Further, an optimal admittance control that considers manipulator actuator limits and target motion bounds is formulated to generate a compliant detumbling trajectory. Through transforming the state and input inequality constraints into extended dynamical subsystems and saturation functions, respectively, the optimal control problem (OCP) is transformed into a readily solvable equality constraint problem. Moreover, an enhanced nonsingular terminal sliding mode (ENTSM) control with radial basis function neural network (RBFNN) compensation is presented in the presence of lumped uncertainties and external disturbances, which achieves rapid finite-time convergence and low-chattering. The simulation results show that the proposed method can reduce the velocity of the space target effectively without causing base spacecraft interference while achieving accurate trajectory tracking.

Space-Based Passive Orbital Maneuver Detection Algorithm for High-Altitude Situational Awareness

Orbital maneuver detection for non-cooperative targets in space is a key task in space situational awareness. This study develops a passive maneuver detection algorithm using line-of-sight angles measured by a space-based optical sensor, especially for targets in high-altitude orbit. Emphasis is placed on constructing a new characterization for maneuvers as well as the corresponding detection method. First, the concept of relative angular momentum is introduced to characterize the orbital maneuver of the target quantitatively, and the sensitivity of the proposed characterization is analyzed mathematically. Second, a maneuver detection algorithm based on the new characterization is designed in which sliding windows and correlations are utilized to determine the mutation of the maneuver characterization. Subsequently, a numerical simulation system composed of error models, reference missions and trajectories, and computation models for estimating errors is established. Then, the proposed algorithm is verified through numerical simulations for both long-range and close-range targets. The results indicate that the proposed algorithm is effective. Additionally, the sensitivity of the proposed algorithm to the width of the sliding window, accuracy of the optical sensor, magnitude and number of maneuvers, and different relative orbit types is analyzed, and the sensitivity of the new characterization is verified using simulations.

Real-time hybrid method for maneuver detection and estimation of non-cooperative space targets

Real-time hybrid method for maneuver detection and estimation of non-cooperative space targets

Attitude Takeover Control for Noncooperative Space Targets Based on Gaussian Processes With Online Model Learning

Attitude Takeover Control for Noncooperative Space Targets Based on Gaussian Processes With Online Model Learning

An innovative inertial parameters identification method for non-cooperative space targets based on electrostatic interaction

Inertial characteristics of non-cooperative targets are crucial for space capture and subsequent on-orbit servicing. Previous methods for identifying inertial parameters involve proximity operations, which are associated with the risk of collision with non-cooperative targets. This paper introduces a long-range, contactless method for identifying the inertial parameters of a non-cooperative target during the pre-capture phase. Specifically, electrostatic interaction is used as an external excitation to alter the target’s motion. A force estimation algorithm that uses measurements from visual and potential sensors is proposed to estimate the electrostatic interaction and eliminate the need for force sensors. Furthermore, a recursive estimation–identification framework is presented to concurrently estimate the coupled motion state, weak electrostatic interaction, and inertial parameters of the target. The simulation results show that the proposed method extends the identification distance to 170 times that of the previous method while maintaining high identification precision for all parameters.

Bioinspired flexible gripper for vacuum non-cooperative target capture

With the development of space exploration activities, the proliferation of non-cooperative targets in space, such as defunct satellites and space debris, has made the development of efficient and reliable non-cooperative target capture technologies in space a priority for space exploration. In this paper, a flexible gripper inspired by the dermo-muscular sac found in flatworms is presented to address the challenges of non-cooperative target capture in the vacuum environment of space. The gripper design leverages magnetorheological fluid and a magnetic field to enable adjustable stiffness, facilitating the effective grasping of delicate target objects while ensuring a stable connection post-capture. Extensive tests demonstrate the strong potential of the gripper for space applications, showcasing its ability to adjust pre-grip contact force and increase gripping force by adjusting indentation depth. The simplicity of the design contributes to ease of manufacturing, making it a promising tool for future space missions.

An edge feature-based external calibration of monocular camera and LiDAR using in-orbit data

Multimodal perception represents a vital approach for observing non-cooperative targets in space. The accurate determination of the extrinsic parameters for monocular camera and LiDAR systems serves as the cornerstone for achieving effective space multimodal perception. However, due to factors like launch and operation, these extrinsic parameters can experience drift, thereby compromising the overall performance of the multimodal perception system. To tackle this challenge, this study introduces a novel approach: an edge feature-based external calibration method for monocular camera and LiDAR using in-orbit data. The proposed methodology involves several steps. Firstly, edges are extracted from the image, followed by distance transformation based on the edge image. The subsequent integration of the edge image and distance image yields the search scene image. Then, edge feature is extracted from the point cloud data. Finally, after constructing the objective function, genetic algorithms are used to determine precise external parameters. Simulation results underscore the effectiveness of the proposed algorithm, affirming its ability to achieve high-precision calibration results for external parameters even within intricate spatial environments.

RBFNN-based angles-only orbit determination method for non-cooperative space targets

Angles-only orbit determination during space situational awareness missions for non-cooperative targets such as space debris is subject to the well-known observability problem, that is, the orbital state is weakly observable or even unobservable because of missing range measurements. The key point to solve this problem is how to quickly capture the nonlinearity of orbit dynamics if only one space-based passive sensor is available to observe the target and translational maneuvers are not executed. To solve the short-arc angles-only problem, this study develops a simple and fast orbit determination method by exploiting the advantages of radial basis function neural network (RBFNN). Emphasis was placed on the design of the RBFNN, which was trained to construct a mapping network model from line-of-sight (LOS) measurements to the relative orbit. First, the perturbed relative orbit dynamics considering the Earth's non-spherical J2 term and air drag was established with the LOS measurement model. Second, a RBFNN-based angles-only orbit determination frame was developed, in which the generator of the training dataset, data preprocessing algorithm, and RBF network structure were designed. Finally, the proposed method was verified and tested using a set of numerical simulations of low-Earth orbit cases. The anti-noise and generalization performance of the designed network and the sensitivity of the solution accuracy to the measurement frequency and span were presented and discussed. Additionally, the advantages of the RBFNN-based method were confirmed by comparison with the results obtained using the BPNN (Back Propagation Neural Network)-based method. The simulation results show that the average orbit prediction error for LEO scenarios is approximately 0.08% using the index of initial relative distance, where only three sets of LOS angles are measured within a span of 24 s.

Force-position collaborative optimization of rope-driven snake manipulator for capturing non-cooperative space targets

With the rapid development of space activities, non-cooperative space targets increase swiftly, such as failed satellites and upper stages, threating normal spacecrafts seriously. As there are some problems in the capture process, such as excessive collision and fast tumbling of targets, manipulator with redundant Degrees of Freedom (DOFs) can be used to improve the compliance and therefore solve these problems. The Rope-Driven Snake Manipulator (RDSM) is a combination of hyper-redundant DOFs and better compliance, and therefore it is suitable for capturing mission. In this paper, a snake manipulator mechanism is designed, and the complete kinematic model and system dynamic model considering RDSM, target and contact is established. Then, to obtain the configuration of joint with hyper-redundant DOFs, an improved motion dexterity index is proposed as the joint motion optimization target. Besides, the force-position collaborative optimization index is designed to adjust active stiffness, and the impedance control method based on the modified index is used to capture the space target. Finally, the proposed force-position collaborative optimization method is verified by virtual prototype co-simulation. The results demonstrate that based on the proposed method, the collision force is reduced by about 25% compared to normal impedance control, showing higher safety.

BiGAT: A Model for Recognizing Motion Intentions of Space Non-Cooperative Targets

BiGAT: A Model for Recognizing Motion Intentions of Space Non-Cooperative Targets

Adaptive hybrid Kalman filter for attitude motion parameters estimation of space non-cooperative tumbling target

Attitude motion parameters estimation of the space non-cooperative tumbling target is the premise of the on-orbit target capture task. However, existing methods cannot balance the estimation accuracy and efficiency. In this paper, an adaptive hybrid Kalman filter is presented to estimate the attitude, angular velocity and inertia motion parameters of the space non-cooperative tumbling target. First, the dynamic model of the non-cooperative tumbling target is derived, and the nonlinear discrete state-space equation is obtained. Then, a hybrid Kalman filter is designed by combining the extended Kalman filter and the unscented Kalman filter. The adaptive technique is introduced to track time-varying uncertain measurement noise caused by complex space disturbances. After that, based on the first-order linearization technique, the sufficient condition for the local convergence of the proposed method is proved. Finally, the numerical simulation experiment was conducted to compare the proposed method with the adaptive extended Kalman filter and the adaptive unscented Kalman filter. The experimental results show that the estimation accuracy of the proposed method is much higher than that of the adaptive extended Kalman filter and slightly lower than that of the adaptive unscented Kalman filter, and the iteration-average Central-Processing-Unit time is 64.2% smaller than that of the adaptive unscented Kalman filter and slightly longer than that of the adaptive extended Kalman filter. The proposed method achieves a much higher accuracy with a slight loss of iteration-average Central-Processing-Unit time.

Spacecraft autonomous navigation using line-of-sight directions of non-cooperative targets by improved Q-learning based extended Kalman filter

Autonomous optical navigation is one of the most promising techniques to estimate the position and velocity of a spacecraft in Earth orbit without the supports of Earth-based tracking stations. To improve the navigation performance, this paper presents a novel autonomous optical navigation method, where a star camera on the spacecraft is utilized to measure the line-of-sight (LOS) directions of a number of non-cooperative space targets, whose position vectors are supposed to be not precisely known in advance, and an improved Q-learning based extended Kalman filter (IQEKF) is developed to obtain the accurate motion state estimate of both the spacecraft and the space targets based on the LOS direction measurements. The main advantage of the presented method is that the LOS directions of the space targets can be acquired with high-accuracy by using the state-of-the-art star camera, such that the superior navigation accuracy is achievable. In addition, the whole motion state of the spacecraft, such as position, velocity, and attitude, can be obtained with the star camera, in the case that the space targets and the stars are observed simultaneously. The high performance of the presented autonomous navigation method is illustrated through a representative simulation of a medium Earth orbit (MEO) satellite. Furthermore, the simulation results indicate that the IQEKF yields more accurate solutions than the traditional navigation filtering algorithms.

A Vision-Based Pose Estimation of a Non-Cooperative Target Based on a Self-Supervised Transformer Network

In the realm of non-cooperative space security and on-orbit service, a significant challenge is accurately determining the pose of abandoned satellites using imaging sensors. Traditional methods for estimating the position of the target encounter problems with stray light interference in space, leading to inaccurate results. Conversely, deep learning techniques require a substantial amount of training data, which is especially difficult to obtain for on-orbit satellites. To address these issues, this paper introduces an innovative binocular pose estimation model based on a Self-supervised Transformer Network (STN) to achieve precise pose estimation for targets even under poor imaging conditions. The proposed method generated simulated training samples considering various imaging conditions. Then, by combining the concepts of convolutional neural networks (CNN) and SIFT features for each sample, the proposed method minimized the disruptive effects of stray light. Furthermore, the feedforward network in the Transformer employed in the proposed method was replaced with a global average pooling layer. This integration of CNN’s bias capabilities compensates for the limitations of the Transformer in scenarios with limited data. Comparative analysis against existing pose estimation methods highlights the superior robustness of the proposed method against variations caused by noisy sample sets. The effectiveness of the algorithm is demonstrated through simulated data, enhancing the current landscape of binocular pose estimation technology for non-cooperative targets in space.

An Efficient Inverse Synthetic Aperture Imaging Approach for Non-Cooperative Space Targets under Low-Signal-to-Noise-Ratio Conditions

Due to the non-cooperative characteristics of space targets with complex motion, it is difficult to obtain high-quality inverse synthetic aperture (ISAR) images using conventional imaging approaches, posing a new challenge when designing novel approaches, especially under low-signal-to-noise-ratio (SNR) conditions. To overcome the obstacle above, in this work, an efficient ISAR imaging approach based on high-order synchrosqueezing transform and modified multi-scale retinex (HSTMMSR) is proposed. First, the geometry and signal model of non-cooperative space targets with complex motion are established. Second, the echoes in each range bin are modeled as multi-component polynomial phase signals (MCPPSs) after correcting the translational migration and migration through range cells (MTRCs). Additionally, the time–frequency analysis (TFA) method based on HoSST is utilized to generate the time–frequency signal along with the azimuth dimension, where the coarse ISAR image is obtained with the quality indicator, e.g., image entropy, followed by the MMSR method to enhance the result. Both the simulated and measured data experiments validate the effectiveness and robustness of the proposed method.

Deep neural network for non-cooperative space target intention recognition

Given the critical importance of intention recognition for non-cooperative space targets in enhancing spatial situational awareness and mitigating threats, this paper proposes a fast and accurate method based on a deep neural network for identifying the intentions. The proposed method takes the instantaneous single relative motion position and velocity of the non-cooperative target as input and calculates the probability of different potential intentions in real-time. To this end, the possible geometric configurations of relative motions of the targets are characterized and classified based on the Clohessy-Wiltshire (CW) equation, and intentions with respect to different types of motion are defined and grouped accordingly. To ensure the method's applicability for large range scenario, the required dataset in two-body dynamics is generated using satellite orbit extrapolation techniques. The deep neural network is trained on the dataset using back-propagation, and experiments are designed to evaluate the method's performance and the recognition accuracy reached 0.9289. The proposed method outperforms the dynamical characteristics matching-based method in terms of recognition accuracy, range of applicability, and time efficiency. The method has potential applications in spacecraft collision warning and orbital pursuit-evasion games, where rapid and accurate identification of non-cooperative target intentions is critical.