Accurate Trajectory Research Articles

Friction compensation control method for a typical excavator system based on the accurate friction model

Traditional identification methods make it difficult to accurately determine the parameters of the friction model. Based on the LuGre friction model, a hybrid optimization algorithm (HO) is presented to address such aspects. This algorithm combines the genetic algorithm (GA) and particle swarm optimization algorithm (PSO) to obtain the globally optimal solutions. It incorporates three main improvements: introducing selection and crossover operations into the PSO algorithm, utilizing a variable inertia weight coefficient, and applying variable learning coefficients for enhanced performance. Compared to the static optimal solutions of the GA and PSO algorithms, the HO algorithm can improve the optimal solution by 40.68 % and 35.89 % respectively. The HO algorithm can achieve the highest model accuracy: the maximum identified friction error with the HO algorithm is only 1.70 kN, compared to 3.69 kN with the GA method and 8.52 kN with the PSO algorithm. Furthermore, a novel adaptive friction compensation controller (AC) is introduced based on the identification results to improve the stability and accuracy of the electro-hydraulic proportional systems of a 23-ton robotic excavator. Comparisons with existing proportional integral differential (PID) and feedforward compensation controllers (FC) highlight the superiority of the proposed adaptive controller in terms of trajectory accuracy and robustness. In sinusoidal trajectory tracking experiments, the AC method can achieve the highest tracking performance among the three controllers, and the maximum tracking error is only 11.56 mm. Compared to the FC controller, the control accuracy with the AC controller can be improved by 43.38 %. Experiments and simulations have shown that the friction compensation controller can effectively mitigate friction and other disturbances. As a result, the phenomena of crawling and flat peak phenomena can be eliminated.

A novel approach for reliable pedestrian trajectory collection with behavior-based trajectory reconstruction for urban surveillance systems

Collecting reliable pedestrian trajectories in pedestrian behavior analysis, trajectories broken by frame sampling and trajectories crossing in multi-object conditions often hinder their performance of existing pedestrian tracking models. Despite attempts to address these issues by performing detection and tracking simultaneously using deep learning algorithms, previous methods still struggle with errors such as mistaking a single pedestrian for multiple pedestrians. We propose a novel approach to efficiently collect and correct pedestrian trajectories with minimized practical errors in multi-object conditions for urban surveillance systems. Our system utilizes a single vision sensor to automatically collects trajectories of multiple pedestrians and employ simple, low-computational algorithms, particularly the Deep simple online real-time tracking (Deep SORT) method, to calibrate the trajectories from tracking-by-detection models. Additionally, our system identifies and merges broken pedestrian trajectories, treating them as potential single trajectories, while considering their spatiotemporal ranges. We evaluate the proposed system by implementing it on real testbed video footage. Our method significantly improves practical errors and achieves more accurate pedestrian trajectories compared to existing models, and exhibits robust characteristics, effectively handling complex situations such as occlusions and crowds.

ULG-SLAM: A Novel Unsupervised Learning and Geometric Feature-Based Visual SLAM Algorithm for Robot Localizability Estimation

Indoor localization has long been a challenging task due to the complexity and dynamism of indoor environments. This paper proposes ULG-SLAM, a novel unsupervised learning and geometric-based visual SLAM algorithm for robot localizability estimation to improve the accuracy and robustness of visual SLAM. Firstly, a dynamic feature filtering based on unsupervised learning and moving consistency checks is developed to eliminate the features of dynamic objects. Secondly, an improved line feature extraction algorithm based on LSD is proposed to optimize the effect of geometric feature extraction. Thirdly, geometric features are used to optimize localizability estimation, and an adaptive weight model and attention mechanism are built using the method of region delimitation and region growth. Finally, to verify the effectiveness and robustness of localizability estimation, multiple indoor experiments using the EuRoC dataset and TUM RGB-D dataset are conducted. Compared with ORBSLAM2, the experimental results demonstrate that absolute trajectory accuracy can be improved by 95% for equivalent processing speed in walking sequences. In fr3/walking_xyz and fr3/walking_half, ULG-SLAM tracks more trajectories than DS-SLAM, and the ATE RMSE is improved by 36% and 6%, respectively. Furthermore, the improvement in robot localizability over DynaSLAM is noteworthy, coming in at about 11% and 3%, respectively.

Enhanced Hybrid Robust Fuzzy-PID Controller for Precise Trajectory Tracking Electro-Hydraulic Actuator System

The Electro-Hydraulic Actuator (EHA) system integrates electrical and hydraulic elements, enabling it to generate a rapid reaction, a high power-to-weight ratio, and significant stiffness. Nevertheless, EHA systems demonstrate non-linear characteristics and modeling uncertainties, such as friction and parametric uncertainty. Designing a controller for accurate trajectory tracking is greatly challenging due to these limitations. This paper introduces a hybrid robust fuzzy proportional-integral-derivative (HFPID) and (HF+PID) controller. The controller is designed to effectively control a third-order model of an EHA system for trajectory tracking. It is a significant contribution to the development of an intelligent robust controller that can perform well in different environments. Initially, a mathematical model for the EHA system was created using a first-principle approach. Subsequently, the Ziegler-Nichols method was employed to fine-tune the PID controller, while a conventional Fuzzy Logic Controller (FLC) was constructed in MATLAB Simulink utilizing linguistic variables and rule-based control. Without further tuning, the FL and PID controller are combined as a hybrid controller with different structures: Hybrid Fuzzy-PID (HFPID) and Hybrid Fuzzy+PID (HF+PID) controller. The Mean Square Error (MSE) and Root Mean Square Error (RMSE) are utilized as indices to assess the tracking accuracy and robustness of the four controllers. A greater value of MSE and RMSE indicates poorer performance of the controller. The results demonstrate that the HF+PID controller surpasses the other controllers by reaching the lowest MSE and RMSE values. It showcases the efficacy and accuracy in monitoring sinusoidal, multi-sinusoidal, and point-to-point trajectory tracking. Future work should focus on implementing the designed controller on hardware for real-time performance and experimenting with various types of FLC or Hybrid controllers, such as self-tuning fuzzy-PID, to further explore their potential.

A time-varying shockwave speed model for reconstructing trajectories on freeways using Lagrangian and Eulerian observations

Inference of detailed vehicle trajectories is crucial for applications such as traffic flow modeling, energy consumption estimation, and traffic flow optimization. Static sensors can provide only aggregated information, posing challenges in reconstructing individual vehicle trajectories. Shockwave theory is used to reproduce oscillations that occur between sensors. However, as the emerging of connected vehicles grows, probe data offers significant opportunities for more precise trajectory reconstruction. Existing methods rely on Eulerian observations (e.g., data from static sensors) and Lagrangian observations (e.g., data from connected vehicles) incorporating shockwave theory and car-following modeling. Despite these advancements, a prevalent issue lies in the static assignment of shockwave speed, which may not be able to reflect the traffic oscillations in a short time period caused by varying response times and vehicle dynamics. Moreover, driver dynamics while reconstructing the trajectories are ignored. In response, this paper proposes a novel framework that integrates Eulerian and Lagrangian observations for trajectory reconstruction on freeways. The approach introduces a calibration algorithm for time-varying shockwave speed. The shockwave speed calibrated by the CV is then utilized for trajectory reconstruction of other non-connected vehicles based on shockwave theory. Additionally, vehicle and driver dynamics are introduced to optimize the trajectory and estimate energy consumption by applying a vehicle movement model. The proposed method is evaluated using real-world datasets, demonstrating superior performance in terms of trajectory accuracy, reproducing traffic oscillations, and estimating energy consumption.

Transportation Simulation Modeling and Location-Based Services Data Completion Based on a Data and Model Dual-Driven Approach

The evolving economic and technological landscape has brought about significant changes in travel behaviors and traffic patterns. These changes have led to the emergence of complex, multi-modal travel demands that interact with transportation networks, posing new challenges in transportation analysis and control. The primary objective of this study is to address these challenges by improving transportation modeling and data completeness using advanced modeling tools and transportation big data. We propose a dual-driven simulation model that integrates transportation simulation and big data. The approach begins by utilizing initial Location-Based Services (LBS) data to establish a mesoscopic multi-modal simulation model, which is then calibrated. This calibrated model is then employed to complete the missing trajectories of the LBS data. The innovative aspect of this dual-driven simulation model lies in its novel approach to constructing transportation models and completing LBS data, thereby enhancing both the simulation accuracy and the results of missing path completion. We conduct tests using the urban area of Hangzhou as an example, and the results show that the Normalized Root Mean Square Error (NRMSE) between the average link speeds in the simulation model and in real world observation is reduced to 24.1%. In the LBS data completion process, our proposed method achieves a travel mode identification accuracy of 95.3% for private car travel. Compared to the two baseline methods, the average accuracy of completed trajectories increases by 6.31% and 2.46%, respectively.

Design Method of Cam Steering Mechanism Based on Path Fitting

In order to improve the accuracy of a solar-powered punch card car’s movement on a designated route and reduce positional deviations during its operation, a solar-powered punch card car with a single cam as the steering guidance mechanism was designed. The car adopts a three-wheel structure. The transmission mechanism, steering mechanism, driving mechanism, and regulating mechanism of the car were analyzed. The kinematics model of the car was established and the motion characteristics of the car were obtained. By analyzing the relationship between the steering angle of the car and the curvature radius of its travel route, the front wheel angle of the car at each position was calculated using MATLAB R2020a. This allowed us to establish the relationship between the front wheel angle and the displacement of the steering push rod, which was further converted into the theoretical contour line of the cam. Subsequently, the theoretical contour line of the cam was completed and envelope correction was performed. Finally, through mechanical analysis and experimental verification using a prototype, the results indicated that the single-cam steering guidance mechanism calculated using this fast path fitting method exhibited excellent mechanical performance and a smooth and accurate trajectory, and the traveling path of the theoretical cam contour curve was basically consistent with the actual trajectory route.

Multiple enhanced synchrosqueezing in the time–frequency–chirprate space

It is challenging to analyze multi-component signals with crossover instantaneous frequencies (IFs), both in producing high-resolution time–frequency representations and disentangling intrinsic modes. One of the most promising attempts is lifting the two-dimensional TFRs to three-dimensional time–frequency–chirprate (TFC) representations. However, the strong “blurring” effect in the chirp rate (CR) axis makes it rather challenging to estimate accurate IF and CR trajectories. Driven by this need, a method to provide highly energy-concentrated TFC representation, called multiple enhanced synchrosqueezing chirplet transform (MESCT), is proposed in this paper. MESCT is an enhanced iterative framework that combines multi-synchrosqueezing and multi-taper techniques. MESCT estimates IF and CR using phase information from different chirplet transform results with different windows, which provides more accurate estimates for reassignment. Then, three-dimensional multi-synchrosqueezing operations subsequently concentrate the ambiguous energy. As a result, MESCT accurately sharpens the TFC representations, even around the crossing points. Thus, accurate IF and CR trajectories can be jointly estimated by the three-dimensional ridge detection algorithm. Finally, crossover modes can be retrieved with high precision based on accurate trajectory estimation. A series of numerical experiments, both simulations and real-world cases, are considered to demonstrate the effectiveness and advantages of the proposed method.

Towards environment perception for walking-aid robots: an improved staircase shape feature extraction method

This paper introduces an innovative staircase shape feature extraction method for walking-aid robots to enhance environmental perception and navigation. We present a robust method for accurate feature extraction of staircases under various conditions, including restricted viewpoints and dynamic movement. Utilizing depth camera-mounted robots, we transform three-dimensional (3D) environmental point cloud into two-dimensional (2D) representations, focusing on identifying both convex and concave corners. Our approach integrates the Random Sample Consensus algorithm with K-Nearest Neighbors (KNN)-augmented Iterative Closest Point (ICP) for efficient point cloud registration. The results show an improvement in trajectory accuracy, with errors within the centimeter range. This work overcomes the limitations of previous approaches and is of great significance for improving the navigation and safety of walking assistive robots, providing new possibilities for enhancing the autonomy and mobility of individuals with physical disabilities.

An accurate trajectory tracking method for low-speed unmanned vehicles based on model predictive control

Trajectory tracking on a low-speed vehicle using the model predictive control (MPC) algorithm usually assumes a simple road terrain. This assumption does not correspond to the actual road situation, leading to low tracking accuracy. Therefore, a trajectory tracking method considering road curvature based on MPC is proposed in this paper. In this method, the controller can automatically switch between MPC types. Linear model predictive control (LMPC) is selected for small road curvatures, while nonlinear model predictive control (NMPC) is employed for large road curvatures. In addition, the NMPC algorithm in this work considers the effect of road curvature on tracking accuracy, making it suitable for tracking time-varying curvature roads. To verify the feasibility of the algorithm, simulation comparisons with the basic MPC model were carried out at different testing roads and vehicle longitudinal speeds. The results indicate that the method significantly improves trajectory tracking accuracy, all while ensuring real-time calculations. The intelligent switching capability of control models based on road curvature allows its application to track trajectories on arbitrarily complex roads.

Multi-Camera Multi-Vehicle Tracking Guided by Highway Overlapping FoVs

Multi-Camera Multi-Vehicle Tracking (MCMVT) is a critical task in Intelligent Transportation Systems (ITS). Differently to in urban environments, challenges in highway tunnel MCMVT arise from the changing target scales as vehicles traverse the narrow tunnels, intense light exposure within the tunnels, high similarity in vehicle appearances, and overlapping camera fields of view, making highway MCMVT more challenging. This paper presents an MCMVT system tailored for highway tunnel roads incorporating road topology structures and the overlapping camera fields of view. The system integrates a Cascade Multi-Level Multi-Target Tracking strategy (CMLM), a trajectory refinement method (HTCF) based on road topology structures, and a spatio-temporal constraint module (HSTC) considering highway entry–exit flow in overlapping fields of view. The CMLM strategy exploits phased vehicle movements within the camera’s fields of view, addressing such challenges as those presented by fast-moving vehicles and appearance variations in long tunnels. The HTCF method filters static traffic signs in the tunnel, compensating for detector imperfections and mitigating the strong lighting effects caused by the tunnel lighting. The HSTC module incorporates spatio-temporal constraints designed for accurate inter-camera trajectory matching within overlapping fields of view. Experiments on the proposed Highway Surveillance Traffic (HST) dataset and CityFlow dataset validate the system’s effectiveness and robustness, achieving an IDF1 score of 81.20% for the HST dataset.

Lagrangian characterization of the southwestern Atlantic from a dense surface drifter deployment

The Southwestern Atlantic (SWA) is characterized by its large Eddy Kinetic Energy as the result of the confluence of two major western boundary currents, the northward flowing Malvinas Current (MC) and the southward flowing Brazil Current. The SWA study was addressed in the literature based on altimetry data, in situ measurements, regional models and ocean reanalysis. The present study constitutes the first effort to sample a portion of the SWA, with a dense drifter array (N = 62) deployment. The drifters, drogued at 15 m depths, were deployed across the MC and the Argentine Continental Shelf along two zonal transects located at 47°S and 47.25°S, between the 8th and the September 9, 2021. Drifters were set to deliver their position every 10 and 60 min, providing accurate Lagrangian trajectories that provide information on a large range of space and time scales of the surface currents. Three regions are clearly identified based on the analysis of the speed of the drifters, of their trajectories and of the spectral density of their velocities: the continental shelf, the slope and the open ocean. The comparison of the trajectories of the drifters with satellite altimetry images shows that, in general, drifters follow mesoscale features that are detectable in satellite altimetry maps. The analysis of the drifter trajectories also allowed us the study of submesoscale features of the flow (1–10 km) that are not observable in satellite altimetry data. Comparison with cloud-free, high-resolution color images, shows that drifter trajectories organized by the mesoscale flow might also locally follow sub-mesoscale features. In frontal regions it was found that drifter velocities double satellite altimetry geostrophic velocities, which suggests that the dynamics at those regions is largely dominated by ageostrophic components. The ageostrophic Ekman component might explain the direction of the drifters when strong winds from a given direction prevail for several days and the drifters are not in a region with large sea surface height (SSH) gradients. The joint analysis of drifters’ trajectory and SSH clearly depicts that mesoscale features on the open ocean region control the cross-shelf exchanges between the MC and open ocean regions as well as the strength and width of the MC. Finally, the spatial density distribution of the drifters during the first hours after deployment and within a small eddy also allowed us to characterize the flow in terms of its divergence, vorticity and strain, indicating that the MC is geostrophic and has a jet-like behavior while the eddy is largely ageostrophic and has a dominant vorticity component over strain. We conclude observing that the analysis of a dense array of drifters provides valuable information of the flow that cannot be attained solely based on satellite data.

Trajectory optimization of B-splines interpolation based on dynamic error adjustment

In this paper, we propose a motion planning algorithm based on the five-fold B-spline curve for multi-axis motion control systems with non-smooth trajectories, acceleration, plus acceleration over the limit, etc. We construct a smooth transition model for the micro-line segment G3 of the continuous five-fold B-spline curve. A derivation of the corresponding theoretical equation is given. Using the transition model, we propose an optimization method for dynamic adjustment of motion trajectory errors based on the velocity forward planning constraints by smoothing the transition after the trajectory of the micro-line segment for the forward planning velocity. Finally, the design flow for the forward planning of the velocity is given. Finally, the above algorithm is used to perform simulation experiments for the optimization algorithm. Experimental results show that the proposed optimization improves the accuracy of fitting motion trajectories under the constraints of acceleration and deceleration addition, which validates the proposed algorithm.

MTR++: Multi-Agent Motion Prediction With Symmetric Scene Modeling and Guided Intention Querying.

Motion prediction is crucial for autonomous driving systems to understand complex driving scenarios and make informed decisions. However, this task is challenging due to the diverse behaviors of traffic participants and complex environmental contexts. In this paper, we propose Motion TRansformer (MTR) frameworks to address these challenges. The initial MTR framework utilizes a transformer encoder-decoder structure with learnable intention queries, enabling efficient and accurate prediction of future trajectories. By customizing intention queries for distinct motion modalities, MTR improves multimodal motion prediction while reducing reliance on dense goal candidates. The framework comprises two essential processes: global intention localization, identifying the agent's intent to enhance overall efficiency, and local movement refinement, adaptively refining predicted trajectories for improved accuracy. Moreover, we introduce an advanced MTR++ framework, extending the capability of MTR to simultaneously predict multimodal motion for multiple agents. MTR++ incorporates symmetric context modeling and mutually-guided intention querying modules to facilitate future behavior interaction among multiple agents, resulting in scene-compliant future trajectories. Extensive experimental results demonstrate that the MTR framework achieves state-of-the-art performance on the highly-competitive motion prediction benchmarks, while the MTR++ framework surpasses its precursor, exhibiting enhanced performance and efficiency in predicting accurate multimodal future trajectories for multiple agents.

MFACNet: A Multi-Frame Feature Aggregating and Inter-Feature Correlation Framework for Multi-Object Tracking in Satellite Videos

Efficient multi-object tracking (MOT) in satellite videos is crucial for numerous applications, ranging from surveillance to environmental monitoring. Existing methods often struggle with effectively exploring the correlation and contextual cues inherent in the consecutive features of video sequences, resulting in redundant feature inference and unreliable motion estimation for tracking. To address these challenges, we propose the MFACNet, a novel multi-frame features aggregating and inter-feature correlation framework for enhancing MOT in satellite videos with the idea of utilizing the features of consecutive frames. The MFACNet integrates multi-frame feature aggregation techniques with inter-feature correlation mechanisms to improve tracking accuracy and robustness. Specifically, our framework leverages temporal information across the features of consecutive frames to capture contextual cues and refine object representations over time. Moreover, we introduce a mechanism to explicitly model the correlations between adjacent features in video sequences, facilitating a more accurate motion estimation and trajectory associations. We evaluated the MFACNet using benchmark datasets for satellite-based video MOT tasks and demonstrated its superiority in terms of tracking accuracy and robustness over state-of-the-art performance by 2.0% in MOTA and 1.6% in IDF1. Our experimental results highlight the potential of precisely utilizing deep features from video sequences.

An Obstacle Avoidance Strategy for AUV Based on State-Tracking Collision Detection and Improved Artificial Potential Field

This paper proposes a fusion algorithm based on state-tracking collision detection and the simulated annealing potential field (SCD-SAPF) to address the challenges of obstacle avoidance for autonomous underwater vehicles (AUVs) in dynamic environments. Navigating AUVs in complex underwater environments requires robust autonomous obstacle avoidance capabilities. The SCD-SAPF algorithm aims to accurately assess collision risks and efficiently plan avoidance trajectories. The algorithm introduces an SCD model for proactive collision risk assessment, predicting collision risks between AUVs and dynamic obstacles. Additionally, it proposes a simulated annealing (SA) algorithm to optimize trajectory planning in a simulated annealing potential field (SAPF), integrating the SCD model with the SAPF algorithm to guide AUVs in obstacle avoidance by generating optimal heading and velocity outputs. Extensive simulation experiments demonstrate the effectiveness and robustness of the algorithm in various dynamic scenarios, enabling the early avoidance of dynamic obstacles and outperforming traditional methods. This research provides an accurate collision risk assessment and efficient obstacle avoidance trajectory planning, offering an innovative approach to the field of underwater robotics and supporting the enhancement of AUV autonomy and reliability in practical applications.

Combined Observer-Based State Feedback and Optimized P/PI Control for a Robust Operation of Quadrotors

This paper deals with a discrete-time observer-based state feedback control design by taking into consideration bounded parameter uncertainty, actuator faults, and stochastic noise in an inner control loop which is extended in a cascaded manner by outer PI- and P-control loops for velocity and position regulation. The aim of the corresponding subdivision of the quadrotor model is the treatment of the control design in a systematic manner. In the inner loop, linear matrix inequality techniques are employed for the placement of poles into a desired area within the complex z-plane. A robustification of the design towards noise is achieved by optimizing both control and observer gains simultaneously guaranteeing stability in a predefined bounded state domain. This procedure helps to reduce the sensitivity of the inner control loop towards changes induced by the outer one. Finally, a model-based optimization process is employed to tune the parameters of the outer P/PI controllers. To allow for the validation of accurate trajectory tracking, a comparison of the novel approach with the use of a standard extended Kalman filter-based linear-quadratic regulator synthesis is presented to demonstrate the superiority of the new design.

Enhancing accuracy and convenience of golf swing tracking with a wrist-worn single inertial sensor

In this study, we address two technical challenges to enhance golf swing trajectory accuracy using a wrist-worn inertial sensor: orientation estimation and drift error mitigation. We extrapolated consistent sensor orientation from specific address-phase signal segments and trained the estimation with a convolutional neural network. We then mitigated drift error by applying a constraint on wrist speed at the address, backswing top, and finish, and ensuring that the wrist's finish displacement aligns with a virtual circle on the 3D swing plane. To verify the proposed methods, we gathered data from twenty male right-handed golfers, including professionals and amateurs, using a driver and a 7-iron. The orientation estimation error was about 60% of the baseline, comparable to studies requiring additional sensor information or calibration poses. The drift error was halved and the single-inertial-sensor tracking performance across all swing phases was about 17 cm, on par with multimodal approaches. This study introduces a novel signal processing method for tracking rapid, wide-ranging motions, such as a golf swing, while maintaining user convenience. Our results could impact the burgeoning field of daily motion monitoring for health care, especially with the increasing prevalence of wearable devices like smartwatches.

High‐Speed Wide‐Angle Sensing and Imaging by WideBand Metasurfaces with Joint Frequency, Polarization, and Spatial Diversities

AbstractHigh‐speed wide‐angle radio detection is crucial for intelligent wireless systems, autonomous vehicles, rescue operations in urgent situations, and security in various fields. This can be achieved through diverse controls of electromagnetic waves. Currently, multidimensional manipulations of electromagnetic waves are determined by dynamic antennas like phased arrays, mechanical beam‐steering radars, and programmable metasurface imagers. However, these methods face challenges in achieving rapid responses and large data collection intervals for high‐speed sensing and imaging, due to limitations in the speedy explication of analog‐to‐digital (AD) converters, electronic switches, phase shifters, and stepped motors for radiation beam reconfigurations. To address these challenges, advanced microwave‐to‐millimeter‐wave metasurfaces are introduced, designed to offer joint frequency, polarization, and spatial diversities. The metasurface with a disordered atom permutation enables wide‐angle sensing for accurate trajectory tracking of moving objects. On the other hand, a dispersion‐engineered atom arrangement allows the metasurfaces to facilitate wide‐angle through‐wall imaging, effective in detecting objects of varied shapes and positions. The experiments reveal that these metasurfaces can reconstruct objects at 100 frames per second (fps) from a single‐shot measurement, allowing 0.3x speed playback for detailed analysis. This demonstrates their potential in high‐speed sensing and imaging. Such a breakthrough is pivotal in unveiling new modalities and expanding possibilities in real‐time radio applications, including smart transportation, all‐condition surveillance, perspective radio, and integrated sensing and communication (ISAC) systems, especially relevant to technologies of 6G and beyond.

Compliant Contact Force Control for Aerial Manipulator of Adaptive Neural Network-Based Robust Control.

Aerial manipulators expand the application scenarios of manipulators into the air. To complete various operations, the contact force between the aerial manipulator and the target must be precisely controlled. In this study, we first established the mathematical models of the multirotor and the manipulator separately. Their mutual influence is regarded as each other's disturbance, and the overall linkage mechanism is established through analysis. Then, a robust sliding mode control strategy is developed for accurate trajectory tracking. The controller is derived from Lyapunov theory, which can ensure the stability of the closed-loop system. To compensate for the effect of system uncertainty, an adaptive radial basis function neural network is devised to approximate the part of the controller containing the model information. In addition, an impedance controller is designed to convert force control into position control to make the manipulator contact with the target compliantly. Finally, the simulation and experimental results indicate that the proposed method can guarantee the accuracy of the contact force and has good robustness.