Manipulator Trajectory Research Articles

Adaptive nonsingular fixed-time sliding mode control for uncertain robotic manipulators under actuator saturation

This paper describes an adaptive nonsingular fixed-time sliding mode control (ANFSMC) scheme under actuator saturation that can track the trajectory of a robotic manipulator under external disturbances and inertia uncertainties. First, a novel NFSMC that offers rapid convergence and avoids singularities is proposed for ensuring robotic manipulators global approximate fixed-time convergence. An ANFSMC is then developed for which the bound of the coupling uncertainty is not necessary to know in advance. The controller exhibits small absolute tracking errors and consumes little energy. An actuator saturation compensator is designed and shown to minimize the chattering of the system while accelerating the trajectory tracking. The proposed schemes are analyzed using Lyapunov stability theory, and their effectiveness and superiority are demonstrated through numerical simulations.

Demonstration of the EMPATHIC Framework for Task Learning from Implicit Human Feedback

Reactions such as gestures, facial expressions, and vocalizations are an abundant, naturally occurring channel of information that humans provide during interactions. An agent could leverage an understanding of such implicit human feedback to improve its task performance at no cost to the human. This approach contrasts with common agent teaching methods based on demonstrations, critiques, or other guidance that need to be attentively and intentionally provided. In this work, we demonstrate a novel data-driven framework for learning from implicit human feedback, EMPATHIC. This two-stage method consists of (1) mapping implicit human feedback to relevant task statistics such as reward, optimality, and advantage; and (2) using such a mapping to learn a task. We instantiate the first stage and three second-stage evaluations of the learned mapping. To do so, we collect a dataset of human facial reactions while participants observe an agent execute a sub-optimal policy for a prescribed training task. We train a deep neural network on this data and demonstrate its ability to (1) infer relative reward ranking of events in the training task from prerecorded human facial reactions; (2) improve the policy of an agent in the training task using live human facial reactions; and (3) transfer to a novel domain in which it evaluates robot manipulation trajectories. In the video, we focus on demonstrating the online learning capability of our instantiation of EMPATHIC.

Accelerating trajectory manipulation of symmetric Pearcey Gaussian beam in a uniformly moving parabolic potential.

We derive analytical solutions that describe the one-dimensional displaced and chirped symmetric Pearcey Gaussian beam in a uniformly moving parabolic potential. The multiple effective manipulations of the beam, which are originated from the diverse configurations of the dynamic parabolic potential, are demonstrated. On the whole, the accelerating trajectory can transform into a linear superposition form of the oblique straight line and the simple harmonic motion. Meanwhile, we discuss the further modulation of the accelerating trajectory characteristics such as slope, amplitude and phase shift. Additionally, the extension into a two-dimensional scenario is also proposed. Our results theoretically improve the practical value of the Pearcey beam, and lead to potential applications in trajectory manipulation and particle manipulation.

Robust Controller for Pursuing Trajectory and Force Estimations of a Bilateral Tele-Operated Hydraulic Manipulator

In hazardous/emergency situations, public safety is of the utmost concern. In areas where human access is not possible or is restricted due to hazardous situations, a system or robot that can be distantly controlled is mandatory. There are many applications in which force cannot be applied directly while using physical sensors. Therefore, in this research, a robust controller for pursuing trajectory and force estimations while deprived of any signals or sensors for bilateral tele-operation of a hydraulic manipulator is suggested to handle these hazardous, emergency circumstances. A terminal sliding control with a sliding perturbation observer (TSMCSPO) is considered as the robust controller for a coupled leader and hydraulic follower system. The ultimate use of this controller is as a sliding perturbation observer (SPO) that can estimate the reaction force without any physical force sensors. Robust and perfect position tracking is attained with terminal sliding mode control (TSMC) in addition to control of the hydraulic follower manipulator. The force estimation and pursuing trajectory for the leader–follower system is built upon a bilateral tele-operation control approach. The difference between the reaction forces (caused by the remote environment) and the operating forces (applied by the human operator) required the involvement of an impedance model. The impedance model is implemented in the leader manipulator to provide human operators with an actual sense of the reaction force while the manipulator connects with the remote environment. A camera is used to ensure the safety of the workplace through visual feedback. The experimental results showed that the controller was robust at pursuing trajectory and force estimations for the bilateral tele-operation control of a hydraulic manipulator.

Shape-Preserving and Reactive Adaptation of Robot End-Effector Trajectories

Variation in task requirements and operation in uncertain environments require robots that can continuously adapt their motions during execution. To do this successfully, the original motion characteristics must be preserved. This paper presents an approach for on-line adaptation of end-effector trajectories for robot manipulators. The trajectory generator aims to preserve the shape of a given model trajectory through its coordinate-invariant shape description. In addition, this trajectory generator is coupled to a task specification and control framework that enables reactive behavior of the robot. Simulation results on the UR10 robot indicate the capability of the developed approach to generalize end-effector trajectories towards new targets while preserving the original trajectory shape. The controller's reactivity is shown towards moving targets and obstacles in the environment. The combination of shape preservation and reactive control may endow robots with better on-line motion generalization capabilities.

A Robotic grinding station based on an industrial manipulator and vision system.

Due to ever increasing precision and automation demands in robotic grinding, the automatic and robust robotic grinding workstation has become a research hot-spot. This work proposes a grinding workstation constituting of machine vision and an industrial manipulator to solve the difficulty of positioning rough metal cast objects and automatic grinding. Faced with the complex characteristics of industrial environment, such as weak contrast, light nonuniformity and scarcity, a coarse-to-fine two-step localization strategy was used for obtaining the object position. The deep neural network and template matching method were employed for determining the object position precisely in the presence of ambient light. Subsequently, edge extraction and contour fitting techniques were used to measure the position of the contour of the object and to locate the main burr on its surface after eliminating the influence of burr. The grid method was employed for detecting the main burrs, and the offline grinding trajectory of the industrial manipulator was planned with the guidance of the coordinate transformation method. The system greatly improves the automaticity through the entire process of loading, grinding and unloading. It can determine the object position and target the robotic grinding trajectory by the shape of the burr on the surface of an object. The measurements indicate that this system can work stably and efficiently, and the experimental results demonstrate the high accuracy and high efficiency of the proposed method. Meanwhile, it could well overcome the influence of the materials of grinding work pieces, scratch and rust.

Method of Supervisory Control of Manipulator Mounted on Underwater Vehicle

The report describes the new supervisory control method for a multi-link manipulator mounted on an underwater vehicle, providing visual control of manipulation operations. The proposed method allows to build complex spatial movement trajectories of a multi-link manipulator working tool along a work object surface, using data obtained from onboard multibeam sonars or technical vision systems. Target designations of the operator determine the trajectory type, its position and orientation in a work area. To form target designations and visual observation of manipulator working tool movements along a given trajectory, a TV camera is used that changes its optical axis spatial orientation. The developed method is implemented in the C++ programming language, as well as numerical simulation of a multi-link underwater manipulator supervisory control in the virtual V-REP environment. To visualize the method, the graphical shell is written using "OpenGL Core".

Loos, a Better Tool to Analyze Molecular Dynamics Simulations

The enormous improvements in computational power in recent years means that we can routinely runs simulations of biologically interesting systems out to the microsecond scale or longer. However, in many cases their scientific impact is limited by an inability to extract useful information from this wealth of data. We created LOOS to unlock this previously unrealized potential. Molecular dynamics is unique among biophysical techniques in that the raw data can be interrogated in a multitude of ways; getting the most out of the data usually requires exploration and iterative refinement. LOOS is designed to make this process easy and efficient, to minimize the friction between a user and her data. LOOS can be viewed in two ways: 1) It is a suite of well-validated, easy-to-use tools for analyzing molecular dynamics simulations. These tools include common tasks, such as trajectory manipulation, as well as more advanced techniques such as analysis of simulation convergence, 3D histograms, and Voronoi decomposition, with a particular focus on membranes and membrane-bound proteins. 2) It is a tool for making tools. At its heart, LOOS is a C++ library covered with a Python interface, for the optimal mix of high performance and ease of development. LOOS is designed for rapid application development, so that most common tasks (reading files, selecting atoms, aligning structures, computing distances, etc) are one-line operations. LOOS is licensed under the GPLv3 license and available via GitHub (https://github.com/GrossfieldLab/loos).

A generalized varying-parameter recurrent neural network for super solution of quadratic programming problem

To obtain superior convergent speed, a generalized varying-parameter recurrent neural network (GVP-RNN) is established and analyzed for solving quadratic programming (QP) problems. Different from the classical fix-parameter neural network, such as Zhang neural network (ZNN) and finite-time convergent differential neural network (FT-CDNN), GVP-RNN dynamics can achieve exponential convergent results and possess high precision. By Lagrange theorem, QP problems can be transformed to a time-varying matrix equation, which is prepared for the GVP-RNN model. Theoretical analysis has shown the GVP-RNN model takes a super-exponential convergence comparing the corresponding simulated results of ZNN and FT-CDNN. Simulation comparisons are presented to evaluate the theoretical performance of the GVP-RNN with three types of activation functions. Furthermore, the proposed GVP-RNN model is analyzed and applied to control kinematic trajectory of redundant manipulators.

Dynamically Feasible Task Space Planning for Underactuated Aerial Manipulators

In this work, we address the problem of planning dynamically feasible trajectories for underactuated aerial manipulators to achieve a desired trajectory for the end effector. We consider a quadrotor equipped with an arbitrary n-joint articulated arm. We show that the combined underactuated system is differentially flat, however the flat outputs do not correspond directly to the motion of the end effector. We therefore develop a method which determines the family of flat output trajectories which will exactly produce any desired task trajectory, even in the case of dynamic maneuvers. We also give criteria on the manipulator geometry which will ensure certain important stability properties, informing hardware design. The entire approach is demonstrated in simulation for systems of varying geometry and number of joints. The simultaneous resolution of the kinematic and dynamic constraints allows these tasks to be performed dynamically without sacrificing accuracy.

Research on Space Motion Trajectory Optimization of the Industrial Robot

In this paper, an online iterative learning planning method is proposed for industrial robot joint space manipulator to capture moving objects. The dynamic mathematical model of the robot is established, and the trajectory of the robot manipulator is tracked and adjusted through the path planning algorithm to change the visual impedance of the robot and optimize the system parameters. It makes the velocity direction of the end effector of the manipulator consistent with the tangent direction of the weld, and realizes the tracking and recognition of the weld trajectory at the end of the manipulator, so as to improve the accuracy and reliability of the robot in capturing moving objects. The simulation results show that the algorithm has good convergence and robustness.

Finite-Time Tracking Controller Design of Perturbed Robotic Manipulator Based on Adaptive Second-Order Sliding Mode Control Method

This article presents an adaptive finite time second-order sliding mode tracking control scheme for robotic manipulators. A new control law is suggested to force the trajectories of the robot manipulator to move from all initial conditions to proportional-integral-derivative switching surface in the finite time and stay on it. Moreover, the adaptation law rejects the requirement of knowledge about upper bound of the external perturbations. It is difficult to exactly determine the upper bound of the perturbations in the practical systems, such as robot manipulators. Unlike the existing methods, the new adaptive finite time second-order sliding mode tracker for $n$ -link robot manipulators enables accurate tracking control, robust performance and parameter tuning. The suggested approach presents the design of a robust controller such that the tracking errors of robot manipulator can reach the equilibrium in the finite time. Through the combination of the finite time tracker and disturbance observer, the position tracking purpose of manipulator joints is accurately performed not only in the nominal environment, but also in the existence of different types of perturbations. The robustness performance and effectiveness of the offered technique are studied in simulation and experimental results.

基于精准碰撞检测算法的机械臂避障轨迹规划

基于精准碰撞检测算法的机械臂避障轨迹规划

Research on trajectory tracking control of 7-DOF picking manipulator.

In order to solve the problem of poor robustness of the traditional method of calculating torque in the mechanical model of 7-DOF picking manipulator, this paper proposes a control strategy of calculating torque plus fuzzy compensation by using adaptive fuzzy logic system to compensate the uncertain part of the mechanical model of 7-DOF picking manipulator. By using Lagrange method, the dynamic model of 7-DOF manipulator is established, and the relationship between joint motion and applied torque (force) is obtained. Using ADAMS and MATLAB to establish a co-simulation platform, the manipulator and trajectory tracking control system are simulated. The results show that the trajectory tracking error of each joint in the algorithm is obviously reduced and the convergence trend is obvious. The average trajectory tracking accuracy of joint 1 to joint 7 was improved by 70.22%, 94.78%, 0.62%, 74.23%, 89.78%, 86.45%, and 67.15%, respectively. In this control scheme, the control force (moment) of each joint changes regularly, and the output force (moment) does not appear chattering and mutation when the disturbance signal is added. The research results can provide support for the further study of picking manipulator trajectory tracking control system.

Novel adaptive backstepping control of uncertain electrically driven haptic robot for surgical training systems

The following paper presents the design, implementation, and validation of a new adaptive control system based on the Modified Function Approximation Technique (MFAT) augmented with backstepping control for a haptic robot with unknown dynamic and actuator parameters, employed in a spinal surgical simulator. The combination of backstepping control and the MFAT policy ensures the continuous performance tracking of the haptic manipulator's trajectories using state and output feedback. Contrary to the conventional FAT, the use of basis functions in dynamic and actuator parameter approximations is completely eliminated. Besides, the proposed control scheme was improved by integrating a high order sliding mode observer to eliminate the need for velocity measurements. Consequently, offline simulation and comparative studies were carried out to validate the effectiveness of the proposed control scheme, and controlled experimental cases were conducted using the haptic manipulator (Entact W3C) for validating the system in real time.

Trajectory via-point generation for autonomous mobile manipulation using 3D LiDAR data

In this work, an approach to generating a set of via points for use in manipulator trajectory path planning is presented. The approach was developed for use on a robotic underground mining system, particularly for the task of autonomous application of a sprayable concrete called shotcrete. A LiDAR (light detection and ranging) scanner on a nodding head produces point clouds that are used as the input for the via-point selection algorithm. The algorithm generates a set of position and orientation via points that the manipulator must follow to perform the shotcreting task. The developed algorithm has been successfully tested on an autonomous mobile-manipulator system in a scaled mock-up of an underground mine. The main advantage of this algorithm is the ability to generate via points for any section of an underground mine in any position relative to the robot.

Analysis of Dynamics Targeting CNT-Based Drug Delivery through Lung Cancer Cells: Design, Simulation, and Computational Approach.

Nowadays, carbon nano (CN) structures and specifically carbon nanotubes (CNTs), because of the nanotube’s nanoscale shape, are widely used in carrier and separation applications. The conjugation of CNTs with polysaccharide, proteins, drugs, and magnetic nanoparticles provides a chance for smart targeting and trajectory manipulation, which are used in the crucial field of life science applications, including for cancer disease diagnostics and treatments. Providing an optimal procedure for delivering a drug to a specific area based on mathematical criteria is key in systemic delivery design. Trajectory guidance and applied force control are the main parameters affected by systemic delivery. Moreover, a better understanding of the tissue parameters and cell membrane molecular behaviour are other factors that can be indirectly affected by the targeted delivery. Both sides are an essential part of successful targeting. The lung is one of the challenging organs for drug delivery inside the human body. It has a large surface area with a thin epithelium layer. A few severe diseases directly involve human lung cells, and optimal and successful drug delivery to the lung for the treatment procedure is vital. In this paper, we studied functionalized CNTs’ targeted delivery via crossing through the lung cell membrane. Molecular dynamics (MD) software simulated all the interaction forces. Mathematical modelling of the cell membrane and proposed delivery system based on the relation of velocity and force has been considered. Dynamics equations for CNTs were defined in the time and frequency domain using control theory methods. The proposed delivery system consists of two main parts: crossing through the cell membrane and targeting inside the cell. For both steps, a mathematical model and a proper magnetic field profile have been proposed. The designed system provides criteria for crossing through the cell membrane within 30 s to 5 min and a translocation profile of 1 to 100 Å.

Recent Advances on Manipulator Trajectory Planning Methods

Background: Traditional manipulator requires professionals to write control programs for specific job requirements so that the end-effector of the manipulator can work following the control instructions. However, the flexibility of the manipulator is not high under the control of off-line programming. With the diversification of the job requirements, the complexity of the work environment has gradually increased. Therefore, the relevant scholars focused their research on the automatic trajectory planning method of the manipulator. They used some algorithms to plan optimal trajectories for the manipulator to automatically avoid obstacles in the complex environment. Researches show that the hybrid optimal trajectory with parameter optimization such as time, energy and impact can be planned by automated programming under some constraint conditions. The trajectory planning is helpful to improve the automation and working efficiency of manipulators for the development of intelligent manufacturing. Objective: Providing references for researchers from related fields by reviewing recent advances of the manipulator trajectory planning. Methods: This paper reviews the latest patents and current representative articles related to the manipulator trajectory planning. The key methods of some references are introduced in several aspects of the algorithm, innovation and principle. Results: Researches on the manipulator trajectory planning in recent 10 years are reviewed. The differences between algorithms in latest patents and current articles are introduced and analyzed and the future developments and potential problems of the manipulator trajectory optimization are discussed. Conclusion: The manipulator trajectory planning reduces complicated operator and hard programming tasks, improving the intelligence of robots and the work efficiency. Current researches focus on collision- free, parameter-optimized and high-efficiency solution which can be used to solve the problem of the end-trajectory planning of the manipulator in the complicated space with obstacles. The aspects that need to be improved in the future include: algorithm reliability, operational security and intelligence, human-computer interaction, efficient simulation, and so on. More patents on manipulator trajectory planning should be invented.

Neural Control of Robot Manipulators With Trajectory Tracking Constraints and Input Saturation.

This article presents a control scheme for the robot manipulator's trajectory tracking task considering output error constraints and control input saturation. We provide an alternative way to remove the feasibility condition that most BLF-based controllers should meet and design a control scheme on the premise that constraint violation possibly happens due to the control input saturation. A bounded barrier Lyapunov function is proposed and adopted to handle the output error constraints. Besides, to suppress the input saturation effect, an auxiliary system is designed and emerged into the control scheme. Moreover, a simplified RBFNN structure is adopted to approximate the lumped uncertainties. Simulation and experimental results demonstrate the effectiveness of the proposed control scheme.

Cross-entropy based stochastic optimization of robot trajectories using heteroscedastic continuous-time Gaussian processes

High dimensional robot motion planning has recently been approached with trajectory optimization methods that efficiently minimize a suitable objective function in order to generate robot trajectories that are both optimal and feasible. However, finding a globally optimal solution is often an insurmountable problem in practice and state-of-the-art trajectory optimization methods are thus prone to local minima, mainly in cluttered environments. In this paper, we propose a novel trajectory planning algorithm that employs stochastic optimization in order to find a collision-free trajectory generated from a continuous-time Gaussian process (GP). The contributions of the proposed motion planning method stem from introducing the heteroscedasticity of the GP, together with exploited sparsity for efficient covariance estimation, and a cross-entropy based stochastic optimization for importance sampling based trajectory optimization. We evaluate the proposed method on three simulated scenarios: a maze benchmark, a 7DOF robot arm planning benchmark and a 10DOF mobile manipulator trajectory planning example and compare it to a state-of-the-art GP trajectory optimization method, namely the Gaussian process motion planner 2 algorithm (GPMP2). Our results demonstrate the following: (i) the proposed method yields a more thorough exploration of the solution space in complex environments than GPMP2, while having comparable execution time, (ii) the introduced heteroscedasticity generates GP priors better suited for collision avoidance and (iii) the proposed method has the ability to efficiently tackle high-dimensional trajectory planning problems.