Joint Velocity Research Articles

Investigation of hip flexibility training on dancesport optimization using machine learning video analysis

Dancesport, particularly the Paso Doble, requires high agility, coordination, and flexibility, especially in the hips. This study investigates the impact of an eight-week targeted Hip Flexibility Training (HFT) program on the performance of professional Paso Doble dancers. The need for this research stems from the lack of objective, data-driven evaluations in the field, where traditional methods rely heavily on subjective assessments. Previous studies have examined general flexibility in dance, but few have focused on the direct Biomechanical Effects (BF) and Physiological Effects (PE) of specific HFT on dancers. Further, such studies could not accurately measure hip joint movements and their coordination in order to achieve dance performance efficiency. The proposed study used motion-capturing devices to collect key movement data that impacts performance efficiency. The collected data is analyzed using the hybrid receptive field block (RFB) and residual network (ResNET) ML models to study the pre- and post-HFT results. Twelve highly trained dancers were assigned to have biomechanical and physiological metrics measured after and before the training. The data analysis has shown that there has been a significant increase in hip flexion from 65.4 ± 4.5° to 75.2 ± 3.7° (P < 0.05), hip extension from 25.3 ± 2.4° to 30.1 ± 2.1° (P < 0.05), and joint velocity from 1.18 ± 0.15 m/s to 1.32 ± 0.12 m/s (P < 0.05). Physiological metrics also showed improvements, such as a reduction in Oxygen Consumption (OC) from 2.02 ± 0.21 L/min to 1.85 ± 0.18 L/min (P < 0.05) and Energy Cost (EC) from 50.1 ± 7.2 kJ/min to 45.6 ± 6.4 kJ/min (P < 0.05).

Exploring Kinematic Variations in Clear Hip Circle to Handstand: A Case Study of Performance Styles on Uneven Bars

(1) Background: This case study analyzed the successful performances of female gymnasts in the finals of the 39th and 40th World Cup in Maribor (SLO). The aim was to identify variations in their execution of the Clear Hip Circle to Handstand (CHCH) on uneven bars based on kinematic parameters. (2) Methods: This study involved elite female gymnasts from the 39th (n = 5, age: 17 ± 6 months) and 40th (n = 8, age: 17.5 ± 6 months) World Cups, totaling 13 gymnasts. Kinematic analysis was performed on 15 successful routines using the Ariel Performance Analysis System (Ariel Dynamics Inc., San Diego, CA). The analysis focused on 16 anthropometric reference points and 8 body segments, including the body mass center of gravity (CG). The main reference points analyzed were the hip joint, the shoulder joint, and the CG along the xy-axes. Trajectory, velocity, angle, and angular velocity of the hips and shoulders were calculated. Pearson correlation analysis was employed to assess the relationships between the kinematic variables. (3) Results: High intercorrelations between the reference points along the xy-axes (0.81–0.99) and optimal movement velocity were found. Dispersed results were observed for kinematic parameters of angle (0.10–0.16) and angular velocity of the hip joints (0.60–1.00), with similar dispersions for shoulder joints (0.51–1.00). Three distinct techniques were identified: (1) stretched body with minimal hip joint flexion throughout; (2) extended body with a short, quick hip joint extension during shoulder movement; and (3) hyperextension in the hip joint. (4) Conclusions: The kinematic analysis revealed three different performance styles of the CHCH among finalists. These variations in technique do not affect the success of the performance. This research contributes to a better understanding of the technique but does not prefer one style over another.

Region-Based Approach for Machining Time Improvement in Robot Surface Finishing

Traditionally, in robotic surface finishing, the entire workpiece is processed at a uniform speed, predetermined by the operator, which does not account for variations in the machinability across different regions of the workpiece. This conventional approach often leads to inefficiencies, especially given the diverse geometrical characteristics of workpieces that could potentially allow for different machining speeds. Our study introduces a region-based approach, which improves surface finishing machining time by allowing variable speeds and directions tailored to each region’s specific characteristics. This method leverages a task-oriented strategy integrating robot kinematics and workpiece surface geometry, subdivided by the clustering algorithm. Subsequently, methods for optimization algorithms were developed to calculate each region’s optimal machining speeds and directions. The efficacy of this approach was validated through numerical results on two distinct workpieces, demonstrating significant improvements in machining times. The region-based approach yielded up to a 37% reduction in machining time compared to traditional single-direction machining. Further enhancements were achieved by optimizing the workpiece positioning, which, in our case, added up to an additional 16% improvement from the initial position. Validation processes were conducted to ensure the collaborative robot’s joint velocities remained within safe operational limits while executing the region-based surface finishing strategy.

Impact of Quadriceps Muscle Fatigue on Ankle Joint Compensation Strategies During Single-Leg Vertical Jump Landing.

This study investigates the impact of quadriceps fatigue on lower limb biomechanics during the landing phase of a single-leg vertical jump (SLJ) in 25 amateur male basketball players from Ningbo University. Fatigue was induced through single-leg knee flexion and extension exercises until task failure. Kinematic and dynamic data were collected pre-fatigue (PRF) and post-fatigue (POF) using the Vicon motion capture system and the AMTI force platform and analyzed using an OpenSim musculoskeletal model. Paired sample t-tests revealed significant changes in knee and hip biomechanics under different fatigue conditions, with knee joint angle (p < 0.001), velocity (p = 0.006), moment (p = 0.006), and power (p = 0.036) showing significant alterations. Hip joint angle (p = 0.002), moment (p = 0.033), and power (p < 0.001) also exhibited significant changes. Muscle activation and joint power were significantly higher in the POF condition, while joint stiffness was lower. These findings suggest that quadriceps fatigue leads to biomechanical adjustments in the knee and hip joints, which may increase the risk of injury despite aiding in landing stability.

Joint range and velocity super-resolution estimation with Doppler effects for innovative OFDM-based RFA RadCom system

Conventional radar and communication signals face challenges when integrating for accurate sensing in dense electromagnetic environments, especially in scenarios involving high-velocity targets estimation. To address this issue, we propose the random frequency agile-orthogonal frequency division multiplexing-based radar and communication (RFA-OFDM-based RadCom) signal, a novel framework that combines RFA hopping radar signal and OFDM signal. This framework effectively handles high-velocity Doppler scenarios, enhancing electronic countermeasure capabilities. In high-velocity scenarios, achieving accurate range and velocity estimation is crucial. We introduce a comprehensive received signal model that considers intrapulse and intersubcarrier Doppler effects, often overlooked in traditional high-velocity contexts. The proposed two-phase hierarchical perceptual methodology enables joint super-resolution estimation using the shared signal. We transform the shared signal echo model into a uniform linear array-like model and employ the matrix decomposition algorithm based on bidirectional weighted frequency smoothing (BWFS-MD) for decoherence processing. Subsequently, the estimation of signal parameters via rotational invariance techniques (ESPRIT)-complementary integrated subspace fitting (E-CISF) algorithm accurately estimates joint range and velocity. Meanwhile, the contrastive analysis of the mutual impacts between radar and communication functions is conducted. Theoretical analysis and simulation results robustly validate the superior performance of the proposed BWFS-MD algorithm. Furthermore, considering the precision of joint range-velocity estimation, real-time constraints, and super-resolution capability (which is emphasized), the E-CSIF algorithm demonstrates the best overall performance from a comprehensive perspective.

Energy-Aware Hierarchical Control of Joint Velocities

Nowadays, robots are applied in dynamic environments. For a robust operation, the motion planning module must consider other tasks besides reaching a specified pose: (self) collision avoidance, joint limit avoidance, keeping an advantageous configuration, etc. Each task demands different joint control commands, which may counteract each other. We present a hierarchical control that, depending on the robot and environment state, determines online a suitable priority among those tasks. Thereby, the control command of a lower-prioritized task never hinders the control command of a higher-prioritized task. We ensure smooth control signals also during priority rearrangement. Our hierarchical control computes reference joint velocities. However, the underlying concepts of hierarchical control differ when using joint accelerations or joint torques as control signals instead. So, as a further contribution, we provide a comprehensive discussion on how joint velocity control, joint acceleration control, and joint torque control differ in hierarchical task control. We validate our formulation in an experiment on hardware.

Environmental and Economic Impact on Scenario-Based Automotive Part Replacement: Case Study of Constant Velocity (CV) Joint Replacement in Korea

The objective of this study is to comprehensively evaluate the environmental and economic impacts of remanufactured constant velocity (CV) joints using a newly proposed framework for automotive parts replacement. This framework utilizes actual vehicle sales data to accurately estimate the demand for CV joint replacements. Specific parameters are established to calculate this demand, enabling a quantitative assessment of both environmental and economic impacts associated with remanufacturing CV joints and other automotive parts. Additionally, sensitivity analyses are conducted to explore the relationship between environmental benefits and economic outcomes, particularly focusing on the preferences for remanufactured parts and their profitability. The results indicate that increasing the proportion of remanufactured CV joints significantly benefits the environment by reducing CO2 emissions, raw material usage, and energy consumption. However, this shift also leads to a decrease in total profits within the CV joint replacement market. To address this trade-off, the study suggests that financial incentives, such as subsidies or tax benefits, are necessary to support the remanufacturing industry and facilitate market expansion. These findings provide valuable insights for policymakers aiming to promote sustainable manufacturing practices through effective subsidy policies.

Heisenberg-Limited Quantum Lidar for Joint Range and Velocity Estimation.

We propose a quantum lidar protocol to jointly estimate the range and velocity of a target by illuminating it with a single beam of pulsed displaced squeezed light. In the lossless scenario, we show that the mean-squared errors of both range and velocity estimations are inversely proportional to the squared number of signal photons, simultaneously attaining the Heisenberg limit. This is achieved by engineering the multiphoton squeezed state of the temporal modes and adopting standard homodyne detection. To assess the robustness of the quantum protocol, we incorporate photon losses and detuning of the homodyne receiver. Our findings reveal a quantum advantage over the best-known classical strategy across a wide range of round-trip transmissivities. Particularly, the quantum advantage is substantial for sufficiently small losses, even when compared to the optimal-potentially unattainable-classical performance limit. The quantum advantage also extends to the practical case where quantum engineering is done on top of a strong classical coherent state with watts of power. This, together with the robustness against losses and the feasibility of the measurement with state-of-the-art technology, make the protocol highly promising for near-term implementation.

Adaptive control of bilateral teleoperators with convergent parameter estimation and guaranteed compliance

Although adaptive control has been studied for teleoperation systems in the past decades, the convergence of parameter estimation is generally difficult to claim in the existing methods, and thus only specific scenarios (e.g., free motion) and partial operation performance (e.g., synchronization) have been addressed. In this paper, we found that the convergence of parameter estimation is crucial for bilateral teleoperation systems to retain the guaranteed operation performances, including compliance in the tracking motion and transparency in the contact motion. Accordingly, this paper suggests an alternative adaptive control for bilateral teleoperation systems, where a new adaptive law with the estimation errors as leakage terms is developed to obtain finite-time convergence of the parameter estimation. This convergent property allows to compensate for the undesired dynamics (e.g., gravity) in the closed-loop system so as to achieve ideal compliance and transparency. The control system’s stability and performances under constant time delays are analyzed for three scenarios: free motion, tracking motion, and contact motion. The quantitative relationship between the joint velocities and the human torques in the tracking motion is also studied, and the transparency is addressed in the contact motion. Simulations and experiments on a Baxter robot all showcase the effectiveness and superiority of the developed approach.

A novel biomechanical model of the mouse forelimb predicts muscle activity in optimal control simulations of reaching movements.

Mice are key model organisms in genetics, neuroscience and motor systems physiology. Fine motor control tasks performed by mice have become widely used in assaying neural and biophysical motor system mechanisms, including lever or joystick manipulation, and reach-to-grasp tasks (Becker et al., 2019; Bollu et al., 2019; Conner at al., 2021). Although fine motor tasks provide useful insights into behaviors which require complex multi-joint motor control, there is no previously developed physiological biomechanical model of the adult mouse forelimb available for estimating kinematics (including joint angles, joint velocities, fiber lengths and fiber velocities) nor muscle activity or kinetics (including forces and moments) during these behaviors. Here we have developed a musculoskeletal model based on high-resolution imaging and reconstruction of the mouse forelimb that includes muscles spanning the neck, trunk, shoulder, and limbs using anatomical data. Physics-based optimal control simulations of the forelimb model were used to estimate in vivo muscle activity present when constrained to the tracked kinematics during mouse reaching movements. The activity of a subset of muscles was recorded via electromyography and used as the ground truth to assess the accuracy of the muscle patterning in simulation. We found that the synthesized muscle patterning in the forelimb model had a strong resemblance to empirical muscle patterning, suggesting that our model has utility in providing a realistic set of estimated muscle excitations over time when provided with a kinematic template. The strength of the resemblance between empirical muscle activity and optimal control predictions increases as mice performance improves throughout learning of the reaching task. Our computational tools are available as open-source in the OpenSim physics and modeling platform (Seth et al., 2018). Our model can enhance research into limb control across broad research topics and can inform analyses of motor learning, muscle synergies, neural patterning, and behavioral research that would otherwise be inaccessible.

A Comparison of Throwing Arm Kinetics and Ball Velocity in High School Pitchers With Overall Fast and Overall Slow Cumulative Joint and Segment Velocities

Background: Individual maximum joint and segment angular velocities have shown positive associations with throwing arm kinetics and ball velocity in baseball pitchers. Purpose: To observe how cumulative maximum joint and segment angular velocities, irrespective of sequence, affect ball velocity and throwing arm kinetics in high school pitchers. Study Design: Descriptive laboratory study. Methods: High school (n = 55) pitchers threw 8 to 12 fastball pitches while being evaluated with 3-dimensional motion capture (480 Hz). Maximum joint and segment angular velocities (lead knee extension, pelvis rotation, trunk rotation, shoulder internal rotation, and forearm pronation) were calculated for each pitcher. Pitchers were classified as overall fast, overall slow, or high velocity for each joint or segment velocity subcategory, or as population, with any pitcher eligible to be included in multiple subcategories. Kinematic and kinetic parameters were compared among the various subgroups using t tests with post hoc regressions and multivariable regression models created to predict throwing arm kinetics and ball velocity, respectively. Results: The lead knee extension and pelvis rotation velocity subgroups achieved significantly higher normalized elbow varus torque (P = .016) and elbow flexion torque (P = .018) compared with population, with equivalent ball velocity (P = .118). For every 1-SD increase in maximum pelvis rotation velocity (87 deg/s), the normalized elbow distractive force increased by 4.7% body weight (BW) (B = 0.054; β = 0.290; P = .013). The overall fast group was older (mean ± standard deviation, 16.9 ± 1.4 vs 15.4 ± 0.9 years; P = .007), had 8.9-mph faster ball velocity (32.7 ± 3.1 vs 28.7 ± 2.3 m/s; P = .002), and had significantly higher shoulder internal rotation torque (63.1 ± 17.4 vs 43.6 ± 12.0 Nm; P = .005), elbow varus torque (61.8 ± 16.4 vs 41.6 ± 11.4 Nm; P = .002), and elbow flexion torque (46.4 ± 12.0 vs 29.5 ± 6.8 Nm; P < .001) compared with the overall slow group. A multiregression model for ball velocity based on maximum joint and segment angular velocities and anthropometrics predicted 53.0% of variance. Conclusion: High school pitchers with higher maximum joint and segment velocities, irrespective of sequence, demonstrated older age and faster ball velocity at the cost of increased throwing shoulder and elbow kinetics. Clinical Relevance: Pitchers and coaching staff should consider this trade-off between faster ball velocity and increasing throwing arm kinetics, an established risk factor for elbow injury.

Wushu Movement Recognition System Based on DTW Attitude Matching Algorithm

Motion recognition technology is widely used in intelligent video surveillance, human-computer interaction and other fields. With the development of computer vision technology, improving the accuracy and efficiency of motion recognition has become the focus of research. The purpose of this study is to improve the performance of Wushu movement recognition through improved dynamic time warping algorithm and hierarchical model. Firstly, a high-dimensional feature vector is constructed by using the position, velocity and Angle changes of human bone joints. The actions are subdivided by the hierarchical model, and matched and recognized by the max-minimum dynamic time regularization model. Meanwhile, the K-class mean algorithm is combined to optimize the type of tree core, improve the performance of the model, reduce the interference of noise nodes, and effectively classify Wushu actions. Experimental verification was carried out on four public data sets of KTH, Olympic Sports, Hollywood2 and HMDB51. The experimental results showed that the recognition rate of the proposed model in KTH data set was 95.2%, and that in Olympic Sports data set was 91.4%. The Hollywood2 dataset was 66.7%, and the HMDB51 dataset was 61.2%. Comparing the results of different algorithms, the proposed method improved the recognition performance by 10% compared with long short-term memory network and gated cycle unit. Compared with one-dimensional convolutional neural network, the time of the proposed method was 15s longer, but the recognition rate was 1.6% higher. The results showed that the proposed method had significant performance advantages in diverse and complex action recognition tasks. Meanwhile, the results emphasized the factors to be considered in the design of the model, demonstrating its effectiveness in the application of Wushu movement recognition.

Time-optimal constrained kinematic control of robotic manipulators by recurrent neural network

Time-optimal kinematic control is a vital concern for industrial manipulators to save allocated motion task time as much as possible. This requires maximizing the end-effector velocity to minimize the time required for path tracking. Nonetheless, it remains a challenge to ensure that joint motion constraints are not violated during this process, even with the aim of maximizing end-effector velocity simultaneously. This paper introduces a novel approach, which for the first time leverages dynamic recurrent neural networks (RNNs) within a constrained optimization framework to attain time-optimal kinematic control for manipulators. The theoretical analysis of the RNN-based kinematic control solver is addressed, ensuring both its optimality and convergence for achieving time-optimal kinematic control. The proposed method enables the maximization of end-effector velocity to achieve time-optimal kinematic control without violating all joint velocity limits simultaneously. In contrast to previous kinematic control schemes, the proposed method can enhance the end-effector path tracking speed of completion by 100% around, we substantiate the effectiveness and superiority of the proposed approach via simulation and V-Rep experiment on the manipulators.

Path planning of 6-DOF free-floating space robotic manipulators using reinforcement learning

This paper presents a study on path planning for 6-DOF free-floating space robotic manipulators using Deep Deterministic Policy Gradient-based Reinforcement Learning. The focus is the development of a novel reward function tailored to address critical requirements for efficient and effective manipulation in space. These requirements include accurate pose alignment between the end-effector and the target, collision avoidance with both the target and other links of the manipulator, smoothing of joint velocities, adaptability to strong dynamic coupling between the manipulator and its base spacecraft due to high manipulator-spacecraft mass ratio, and resilience to noise in the state observations. Uniquely, the proposed reward function employs quaternions for orientation control to reduce pose misalignments and dynamic singularities, as opposed to traditional Euler angles. Our findings demonstrate that the Reinforcement Learning algorithm, when guided by this new reward function that integrates these enhancements and constraints, not only achieves the desired path planning objectives more efficiently but also exhibits faster convergence. Furthermore, the Reinforcement Learning successfully manages significant dynamic coupling effects caused by a high mass ratio between the robotic manipulator and the base spacecraft. Even under the challenge of noisy state observations, the trained agent successfully completes the path planning task, proving the Reinforcement Learning's applicability to real-space mission designs where the noise in observation is inevitable. The study highlights the critical role of reward function design in the Reinforcement Learning training process and its consequential impact on the solution quality, providing a solid foundation for future advancements in free-floating space robotic missions.

Cerebellum-Inspired Learning and Control Scheme for Redundant Manipulators at Joint Velocity Level.

Redundant manipulators, as mechanical equipments imitating human arms, have been applied to various areas in recent years from the perspective of control. Different from pure control technologies, the motion capability of a human arm is achieved by a complex and efficient neural system, with the cerebellum playing a pivotal role. Motivated by this fact, we design a cerebellum model based on an echo state network (ESN) for the learning and control of redundant manipulators. In addition, to simulate the skillful control ability of the cerebellum over movements of human arms, the proposed model is constructed at the joint velocity level. Furthermore, to improve the accuracy and applicability, we propose an ESN-based Kalman-filter-incorporated and cerebellum-inspired (KFICI) scheme for the learning and control of redundant manipulators with Kalman filter incorporated. The proposed scheme enables a redundant manipulator to track the desired trajectory at the velocity level and tolerate noises. Finally, simulations and experiments based on a physical redundant manipulator are performed to verify the effectiveness of the proposed control scheme.

Effect of changes in motor skill induced by educational video program to decrease lower-limb joint load during cutting maneuvers: based on musculoskeletal modeling

BackgroundThis study investigated the effects of changes in motor skills from an educational video program on the kinematic and kinetic variables of the lower extremity joints and knee ligament load.MethodsTwenty male participants (age: 22.2 ± 2.60 y; height: 1.70 ± 6.2 m; weight: 65.4 ± 7.01 kg; BMI: 23.32 ± 2.49 \\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$kg/{m}^{2}$$\\end{document}) were instructed to run at 4.5 ± 0.2 m/s from a 5 m distance posterior to the force plate, land their foot on the force plate, and perform the cutting maneuver on the left. The educational video program for cutting maneuvers consisted of preparatory posture, foot landing orientation, gaze and trunk directions, soft landing, and eversion angle. The measured variables were the angle, angular velocity of lower extremity joints, ground reaction force (GRF), moment, and anterior cruciate ligament (ACL) and medial collateral ligament (MCL) forces through musculoskeletal modeling.ResultsAfter the video feedback, the hip joint angles increased in flexion, abduction, and external rotation (p < 0.05), and the angular velocity increased in extension (p < 0.05). The ankle joint angles increased in dorsiflexion (p < 0.05), and the angular velocity decreased in dorsiflexion (p < 0.05) but increased in abduction (p < 0.05). The GRF increased in the anterior-posterior and medial-lateral directions and decreased vertically (p < 0.05). The hip joint moments decreased in extension and external rotation (p < 0.05) but increased in adduction (p < 0.05). The knee joint moments were decreased in extension, adduction, and external rotation (p < 0.05). The abduction moment of the ankle joint decreased (p < 0.001). There were differences in the support zone corresponding to 64‒87% of the hip frontal moment (p < 0.001) and 32‒100% of the hip horizontal moment (p < 0.001) and differences corresponding to 32‒100% of the knee frontal moment and 21‒100% of the knee horizontal moment (p < 0.001). The GRF varied in the support zone at 44‒95% in the medial-lateral direction and at 17‒43% and 73‒100% in the vertical direction (p < 0.001).ConclusionsInjury prevention feedback reduced the load on the lower extremity joints during cutting maneuvers, which reduced the knee ligament load, mainly on the MCL.

Enhancing Robotic Grasping Performance through Data-Driven Analysis

In automation, reliability in robotic grasping in dynamic environment is still a problem encountered. Further, there is the need to consider deep learning methods, as traditional approaches are not easily flexible in dealing with different objects and situations. In this work, we aim to analyze how well deep neural network models perform in predicting grasp strength based on data collected from the Smart Grasping Sandbox simulation trials. Hence, the proposed approach for analyzing the joint positions, velocities and efforts led to the design of a deep neural network for improving robot grasp performance. The question here could is if deep learning could help better predict grasp stability. To implement the method, we underwent rigorous data pre-processing such as outlier detection, and feature normalization and employed a structured neural network model for training. Our model got a training accuracy of nearly 99% and the test accuracy of nearly 96% demonstrating significant promise. These results were also better than CNN and LSTM where their accuracy rate was 94.12% and 91.81%, respectively. High deep learning performance was proven in robotic grasping, which can contribute to the creation of more flexible and sophisticated robotic platforms. This work also provides the foundation for subsequent research in robotics and automation, with emphasis on the role of data-driven methods in robotic grasping tasks.

A self-adaptive agent for flexible posture planning in robotic milling system

In recent years, industrial robots are widely used in the milling processes of the fundamental components such as aeronautic parts, aerospace cabins and blades on the marine propellers of the worships, because of their flexible structure, large operating space, and robust capacity of rapid reconfiguration. Along with the robotic machining process, multiple types of geometrical and physical constraints display the time-varying characteristics, which are difficult to be considered simultaneously by the traditional static planning methods on the robotic milling posture. Therefore, a deep reinforcement learning (DRL) enhanced virtual repulsive potential field flexible model is proposed for the robotic milling posture dynamic planning. The preliminary planning of static milling posture is realized based on the fixed setting of the virtual modal parameters in the posture planning model, which is treated as a theory preparation for training the deep reinforcement learning agent. To develop the static planning model, multiple constraints are established by considering the performances of geometric, kinematic and machining precision simultaneously. Furthermore, a reward function is constructed for the dynamic agent, comprehensively combining the long and short reward benefits in nonlinear correlation with virtual repulsive forces. By taking the virtual modal parameters as the action space of the dynamic agent, a DRL enhanced agent VRPF-SAC is created and trained under the dynamic milling environment from virtual repulsive planning field. Four tasks of large size robotic milling simulations and experiments are designed and developed to validate the effectiveness of the flexible planning model. In comparison with the static model, the flexible planning model displays the excellent global effects covering the kinematic, and precision performance, with 65.78 %, 72.04 %, and 70.25 % reduction in velocity, acceleration, and jerk of robotic joints, and ensuring the effective precision performance from −0.365 to 0.283 mm of large size workpiece with large curvature changes. The proposed flexible posture planning architecture can provide a basic for robotic dynamic milling of core parts with large size, narrow space and sharp curvatures of the aeronautic parts, aerospace cabins and worship propellers.

Observer based output feedback repetitive learning control of robotic manipulators

AbstractThis work tackles the tracking control problem of robotic manipulators where the robot dynamics contains uncertain parameters and joint velocity measurements are not available. Specifically when the robotic manipulator is required to perform a periodic task repetitively, as in most industrial applications, a repetitive learning controller is proposed that does not require joint velocity measurements and can compensate the uncertainties of the robot dynamical parameters and additive disturbances caused due to the periodic joint motion. The proposed solution is achieved via the use of a novel learning component in the controller design in conjunction with a novel model‐free joint velocity observer design. The stability of the closed‐loop system and the convergence of both the joint position tracking error and the joint velocity observation error to the origin are guaranteed via Lyapunov based arguments. Experimental results performed on a 2 degree of freedom robot manipulator are presented to demonstrate the performance of the proposed observer–controller couple.

Optimal control of the E–L dynamic systems during the actuator faults

AbstractIn this article, we deal with finite‐time optimal control of the Euler–Lagrange (E–L) multi‐body mechanism under: uncertain its kinematics and dynamics, displacement blocking of the damaged joint caused by the actuator failure, undesirable forces/torques exerted on the end‐effector and unknown friction forces originating from joints directly driven by the actuators, as well as completely unstructured forces arising from the kinematic singularities appearing on the mechanism trajectory. Based on the suitably defined task space non‐singular terminal sliding manifold and the Lyapunov stability theory, we propose a class of new fault tolerant estimated generalized Jacobian controllers, which seem to be effective in reducing (minimizing) the joint velocity jumps as well as in counteracting the unstructured forces/torques. On account of the fact, that the multi‐body mechanism is a redundant one, a useful criterion function (energy consumption manipulability measure) has been utilized in our controller to temporarily optimally track a desired trajectory. The proposed controllers' performance is demonstrated by computer simulations conducted on a redundant manipulator in conditions of unexpected actuator failure and the corresponding joint lock. Additionally, numerical comparisons are also provided with other representative controllers, found in the literature.