A boundary control approach is used to control a two-link rigid-flexible wing in this article. Its design is based on the principle of bionics to improve the mobility and the flexibility of aircraft. First, a series of partial differential equations (PDEs) and ordinary differential equations (ODEs) are derived through the Hamilton's principle. These PDEs and ODEs describe the governing equations and the boundary conditions of the system, respectively. Then, a control strategy is developed to achieve the objectives including restraining the vibrations in bending and twisting deflections of the flexible link of the wing and achieving the desired angular position of the wing. By using Lyapunov's direct method, the wing system is proven to be stable. The numerical simulations are carried out with the finite difference method to prove the effectiveness of designed boundary controllers.

Dynamical Modeling and Boundary Vibration Control of a Rigid-Flexible Wing System

In this article, an admittance-based controller for physical human–robot interaction (pHRI) is presented to perform the coordinated operation in the constrained task space. An admittance model and a soft saturation function are employed to generate a differentiable reference trajectory to ensure that the end-effector motion of the manipulator complies with the human operation and avoids collision with surroundings. Then, an adaptive neural network (NN) controller involving integral barrier Lyapunov function (IBLF) is designed to deal with tracking issues. Meanwhile, the controller can guarantee the end-effector of the manipulator limited in the constrained task space. A learning method based on the radial basis function NN (RBFNN) is involved in controller design to compensate for the dynamic uncertainties and improve tracking performance. The IBLF method is provided to prevent violations of the constrained task space. We prove that all states of the closed-loop system are semiglobally uniformly ultimately bounded (SGUUB) by utilizing the Lyapunov stability principles. At last, the effectiveness of the proposed algorithm is verified on a Baxter robot experiment platform. Note to Practitioners —This work is motivated by the neglect of safety in existing controller design in physical human–robot interaction (pHRI), which exists in industry and services, such as assembly and medical care. It is considerably required in the controller design for rigorously handling constraints. Therefore, in this article, we propose a novel admittance-based human–robot interaction controller. The developed controller has the following functionalities: 1) ensuring reference trajectory remaining in the constrained task space: a differentiable reference trajectory is shaped by the desired admittance model and a soft saturation function; 2) solving uncertainties of robotic dynamics: a learning approach based on radial basis function neural network (RBFNN) is involved in controller design; and 3) ensuring the end-effector of the manipulator remaining in the constrained task space: different from other barrier Lyapunov function (BLF), integral BLF (IBLF) is proposed to constrain system output directly rather than tracking error, which may be more convenient for controller designers. The controller can be potentially applied in many areas. First, it can be used in the rehabilitation robot to avoid injuring the patient by limiting the motion. Second, it can ensure the end-effector of the industrial manipulator in a prescribed task region. In some industrial tasks, dangerous or damageable tools are mounted on the end-effector, and it will hurt humans and bring damage to the robot when the end-effector is out of the prescribed task region. Third, it may bring a new idea to the designed controller for avoiding collisions in pHRI when collisions occur in the prescribed trajectory of end-effector.

Admittance-Based Controller Design for Physical Human–Robot Interaction in the Constrained Task Space

This article discusses the control design and experiment validation of a flexible two-link manipulator (FTLM) system represented by ordinary differential equations (ODEs). A reinforcement learning (RL) control strategy is developed that is based on actor–critic structure to enable vibration suppression while retaining trajectory tracking. Subsequently, the closed-loop system with the proposed RL control algorithm is proved to be semi-global uniform ultimate bounded (SGUUB) by Lyapunov’s direct method. In the simulations, the control approach presented has been tested on the discretized ODE dynamic model and the analytical claims have been justified under the existence of uncertainty. Eventually, a series of experiments in a Quanser laboratory platform are investigated to demonstrate the effectiveness of the presented control and its application effect is compared with PD control.

Reinforcement Learning Control of a Flexible Two-Link Manipulator: An Experimental Investigation

In this paper, we address simultaneous control of a flexible spacecraft’s attitude and vibrations in a three-dimensional space under input disturbances and unknown actuator failures. Using Hamilton’s principle, the system dynamics is modeled as an infinite dimensional system captured using partial differential equations. Moreover, a novel adaptive fault tolerant control strategy is developed to suppress the vibrations of the flexible panel in the course of the attitude stabilization. To determine whether the system energies, angular velocities and transverse deflections, remain bounded and asymptotically decay to zero in the case wherein the number of actuator failures is infinite, a Lyapunov-based stability analysis is conducted. Finally, extensive numerical simulations are performed to demonstrate the performance of the proposed adaptive control strategy.

Modeling and adaptive control for a spatial flexible spacecraft with unknown actuator failures

In this article, we propose a hybrid framework using visual and force sensing for human-robot co-carrying tasks. Visual sensing is utilized to obtain human motion and an observer is designed for estimating control input of human, which generates robot's desired motion toward human's intended motion. An adaptive impedance-based control strategy is proposed for trajectory tracking with neural networks used to compensate for uncertainties in robot's dynamics. Motion synchronization is achieved and this approach yields a stable and efficient interaction behavior between human and robot, decreases human control effort and avoids interference to human during the interaction. The proposed framework is validated by a co-carrying task in simulations and experiments.

/pdf/human-robot-co-carrying-using-visual-and-force-sensing-22ivghipcb.pdf

Human-Robot Co-Carrying Using Visual and Force Sensing

Accurate monitoring the surrounding environment is an important research direction in the field of unmanned systems such as bio-robotics, and has attracted much research attention in recent years. The trajectories of surrounding vehicles should be predicted accurately in space and time to realize active defense and running safety of an unmanned system. However, there is uncertainty and uncontrollability in the process of trajectory prediction of surrounding obstacles. In this study, we propose a trajectory prediction method based on a sequential model, that fuses two neural networks of a convolutional neural network (CNN) and a long short-term memory network (LSTM). First, a box plot is used to detect and eliminate abnormal values of vehicle trajectories, and valid trajectory data are obtained. Second, the trajectories of surrounding vehicles are predicted by merging the characteristics of CNN space expansion and LSTM time expansion; the hyper-parameters of the model are optimized according to a grid search algorithm, which satisfies the double-precision prediction requirement in space and time. Finally, data from next generation simulation (NGSIM) and Creteil roundabout in France are taken as test cases; the correctness and rationality of the method are verified by prediction error indicators. Experimental results demonstrate that the proposed CNN-LSTM method is more accurate and features a shorter time cost, which meets the prediction requirements and provides an effective method for the safe operation of unmanned systems.

Motion trajectory prediction based on a CNN-LSTM sequential model

Train wheel degradation generation and prediction based on the time series generation adversarial network

Traffic accidents occurred frequently on roads, which bring huge losses to society. The purpose of this article is to extract the important influence factors of traffic accidents, reduce the probability of road traffic accidents, and support the basis for the decision-making of unmanned vehicles. For all this, an improved artificial neural network method is proposed to predict and analyze the severity of vehicle accidents. The impact of different factors, such as road, weather, road surface, time, etc., on the traffic accident is huge. Hence, the factors of traffic accidents are quantified and the redundancy between factors is reduced. To obtain the relationship between influence factors and severity, a multiple-input and multiple-output neural network prediction model is constructed. The hyperparameters of the network model are optimized, and the model prediction efficiency is improved. Besides, the correlation between factors and severity is also calculated, through which the impact of factors on the accuracy of the accident model is explored. To verify the validity of the method, the accuracy of the proposed method is counted and analyzed based on the data of more than 10 000 traffic accidents. The results show that the accuracy of the proposed method is higher than other traditional methods and model has high stability. The findings provide effective support to improve safety for unmanned system.

Unmanned System Safety Decision-Making Support: Analysis and Assessment of Road Traffic Accidents

In this paper, a method for calculating vehicle collision probability is proposed. The vehicle running state and the relationship between the velocity and displacement are determined by analyzing the vehicle running speed sequence. Using the Monte Carlo simulation method, the frequency histogram of vehicle running time that arrived at collision point is obtained. In order to get the vehicle running time distribution function, the vehicle running time probability corresponding to the frequency histogram is fitted by the Gaussian fitting method. At last, the collision probability of two vehicles at intersection is calculated by the collision formula. The experiment results show that this method can calculate the collision probability of vehicles exactly, which can provide correct operate decision and environment information for autonomous vehicles, and also make the whole autonomous technology more reliable.

Analyzing the collision probability changed over time at intersections for autonomous vehicle

It is essential to assess the autonomous vehicle operation safety during driving, which can avoid or reduce the collision risk by evaluating the drive safety. In this paper, a collision risk assessment algorithm is proposed, that is quantifies the auto-drive vehicle collision risk by the Time to Collision (TTC) frequency. Firstly, the Long Short Time Memory network (LSTM) is used to predict the surrounding vehicle trajectory; Moreover, the collision point between the auto-drive vehicle and the surrounding vehicle is determined, and the frequency distribution result of TTC is calculated by the Monte Carlo simulation method; Finally, the running speed & hazard probability is obtained by changing the running speed of auto-drive vehicle, and the running speed & safety probability is obtained further. It can be seen from the result that the proposed method can provide an effective evidence for decision-making layer of auto-drive vehicle, improve the running safety of vehicle, and reduce the operation risk of auto-drive vehicle.

Anqi Shangguan

Papers

Motion trajectory prediction based on a CNN-LSTM sequential model

Train wheel degradation generation and prediction based on the time series generation adversarial network

Unmanned System Safety Decision-Making Support: Analysis and Assessment of Road Traffic Accidents

Analyzing the collision probability changed over time at intersections for autonomous vehicle

Analyzing the Collision Probability of Autonomous Vehicle at Crossroad