Path Tracking Task Research Articles

A robust path tracking algorithm for connected and automated vehicles under i-VICS

Connected and automated vehicle (CAV) can obtain the precise vehicle location information via vehicle to infrastructure (V2I) communication to achieve the path tracking task under the intelligent vehicle-infrastructure cooperative system (i-VICS). However, in some special scenarios, the location information of vehicles might become inaccurate or lost, e.g., the vehicle loses contact with the road-side unit (RSU). To improve the reliability of vehicle location information, we concentrate on solving two kinds of tracking problems, i.e., vehicle location information is inaccurate and lost in this paper. First, a predicted method using vehicle dynamics is presented to recognize the scenarios in which the vehicle location information becomes inaccurate when the vehicle moves. Then, a modified Kalman filter is employed to adapt to a more complex scenario with variable position error. After that, a multilayer perceptron (MLP) model is designed to predict vehicle location information when vehicle location information is lost. At last, simulation results demonstrate that the proposed methods have a marked influence on handling the driving scenario and make our path tracking algorithm more robust.

Deep reinforcement learning based path tracking controller for autonomous vehicle

Path tracking is an essential task for autonomous vehicles (AV), for which controllers are designed to issue commands so that the AV will follow the planned path properly to ensure operational safety, comfort, and efficiency. While solving the time-varying nonlinear vehicle dynamic problem is still challenging today, deep neural network (NN) methods, with their capability to deal with nonlinear systems, provide an alternative approach to tackle the difficulties. This study explores the potential of using deep reinforcement learning (DRL) for vehicle control and applies it to the path tracking task. In this study, proximal policy optimization (PPO) is selected as the DRL algorithm and is combined with the conventional pure pursuit (PP) method to structure the vehicle controller architecture. The PP method is used to generate a baseline steering control command, and the PPO is used to derive a correction command to mitigate the inaccuracy associated with the baseline from PP. The blend of the two controllers makes the overall operation more robust and adaptive and attains the optimality to improve tracking performance. In this paper, the structure, settings and training process of the PPO are described. Simulation experiments are carried out based on the proposed methodology, and the results show that the path tracking capability in a low-speed driving condition is significantly enhanced.

Development of a Hybrid Path Planning Algorithm and a Bio-Inspired Control for an Omni-Wheel Mobile Robot.

This research presents a control structure for an omni-wheel mobile robot (OWMR). The control structure includes the path planning module and the motion control module. In order to secure the robustness and fast control performance required in the operating environment of OWMR, a bio-inspired control method, brain limbic system (BLS)-based control, was applied. Based on the derived OWMR kinematic model, a motion controller was designed. Additionally, an optimal path planning module is suggested by combining the advantages of A* algorithm and the fuzzy analytic hierarchy process (FAHP). In order to verify the performance of the proposed motion control strategy and path planning algorithm, numerical simulations were conducted. Through a point-to-point movement task, circular path tracking task, and randomly moving target tracking task, it was confirmed that the suggesting motion controller is superior to the existing controllers, such as PID. In addition, A*–FAHP was applied to the OWMR to verify the performance of the proposed path planning algorithm, and it was simulated based on the static warehouse environment, dynamic warehouse environment, and autonomous ballet parking scenarios. The simulation results demonstrated that the proposed algorithm generates the optimal path in a short time without collision with stop and moving obstacles.

Design and Application of A Robust Zeroing Neural Network to Kinematical Resolution of Redundant Manipulators Under Various External Disturbances

Zeroing neural network (ZNN), as an effective solution tool for time-varying problems, has been widely applied to the kinematical resolution of redundant manipulators. Most of work is devoted to modifying the convergence speed of ZNN in an ideal environment. However, external disturbances are unavoidable in practical solution process of ZNN for the kinematical resolution of redundant manipulators. In this paper, by proposing a robust ZNN (RZNN) model for real-time kinematical resolution, redundant manipulators are capable of achieving path-tracking tasks with high accuracy, even in a noise-disturbed environment. The theoretical analyses about robustness and finite-time convergence are provided to guarantee the superior property of the RZNN model. A numerical example abstracted from the nonlinear mapping of redundant manipulators is first given to demonstrate the effectiveness and advantages of the RZNN model under various external disturbances, by comparing existing two ZNN models. Then, two multi-link robot manipulator-tracking examples are presented to show the applicability of the RZNN model in a noise-disturbed environment, while the existing ZNN model is no longer effective in the same condition. Comparative results validate the effectiveness, high accuracy, and advantages of the RZNN model for the kinematical resolution of redundant manipulators even in a noise-disturbed environment.

Event-triggered zeroing dynamics for motion control of Stewart platform

Zeroing dynamics (ZD) was originally proposed and investigated for solving time-varying problems. Due to its advantages in convergence and accuracy, ZD has been successfully extended to various areas, including automatic control, robotics and numerical computation. In this paper, we further propose a novel one called event-triggered zeroing dynamics (ETZD) by incorporating the event-triggered strategy to improve the practicability of ZD. Absorbing the advantages of event-triggered strategy, ETZD can not only significantly reduce the consumption on computation but also maintain the original advantages of ZD. For better understanding, we employ ETZD to design a specific motion controller of a popular type of robot manipulators (i.e., Stewart platform). The stability of the motion controller is presented and analyzed via Lyapunov analysis. Furthermore, two different shaped path tracking tasks are executed in numerical experiments, and compared with conventional ZD controllers, to illustrate the advantage in convergence, accuracy and practicability of ETZD controller.

A novel adaptive control approach for path tracking control of autonomous vehicles subject to uncertain dynamics

Autonomous ground vehicles are constantly exposed to matched/mismatched uncertainties and disturbances and different operating conditions. Consequently, robustness to resist the undesirable effect of changes in the nominal parameters of the vehicle is a significant provision for satisfactory path-tracking control of these vehicles. The accomplishment of lateral path-tracking control is an essential task expectable from autonomous ground vehicles, particularly during critical maneuvers, abrupt cornering, and lane changes at high speeds. This paper presents a new control approach based on immersion and invariance control theorem. The asymptotic stability of the proposed method is ensured and the adaptation laws for the parameters are derived based on the I&I stability theorem. The effectiveness of the proposed control method is confirmed for autonomous ground vehicles systems while making a double-lane-change at various forward speeds. The robustness of the proposed control method is evaluated under parametric uncertainties related to the autonomous ground vehicle and different road conditions. The obtained results suggest that the proposed control method holds the capacity to be applied effectively to the path-tracking task of autonomous ground vehicles under a broad range of operating conditions, parametric uncertainness, and external disturbances.

Unified Virtual Guides Framework for Path Tracking Tasks

Unified Virtual Guides Framework for Path Tracking Tasks

Unified Virtual Guides Framework for Path Tracking Tasks

Unified Virtual Guides Framework for Path Tracking Tasks

M-FABRIK: A New Inverse Kinematics Approach to Mobile Manipulator Robots Based on FABRIK

The inverse kinematics of mobile manipulators is a challenging problem due to the high degree of kinematic redundancy added by the coupling of the mobile platform and the manipulator. Some different approaches have been proposed to solve this problem, but most of them are either complex in terms of modelling and matrix calculation, with high computational cost and even with singularity problems, or slow in terms of convergence. This paper proposes a new approach for inverse kinematics of mobile manipulators based on the algorithm FABRIK. This new method, named M-FABRIK, has as main advantages the simplicity to implement, a fast convergence and a low computational cost, allowing real-time applications. Furthermore, this solution allows the robot to be positioned according to various criteria, such as decreasing convergence time, avoiding contact with obstacles, avoiding joint angle limits, increasing robot manipulability or even decreasing joint effort, besides avoiding matrix inversion and being robust to singularities. The proposed approach is illustrated by simulation considering a 5 DOF manipulator mounted on an omnidirectional base for a path-tracking task in different environments, including obstacles. A comparison between the proposed approach and classical methods is also presented.

Unified Virtual Guides Framework for Path Tracking Tasks

SUMMARYIn this paper, we propose a novel unified framework for virtual guides. The human–robot interaction is based on a virtual robot, which is controlled by the admittance control. The unified framework combines virtual guides, control of the dynamic behavior, and path tracking. Different virtual guides and active constraints can be realized by using dead-zones in the position part of the admittance controller. The proposed algorithm can act in a changing task space and allows selection of the tasks-space and redundant degrees-of-freedom during the task execution. The admittance control algorithm can be implemented either on a velocity or on acceleration level. The proposed framework has been validated by an experiment on a KUKA LWR robot performing the Buzz-Wire task.

Two Hybrid End-Effector Posture-Maintaining and Obstacle-Limits Avoidance Schemes for Redundant Robot Manipulators

To fulfill path tracking tasks with the end-effector posture controlled in a complex environment, maintaining the robot manipulator end-effector posture and avoiding obstacles are two important issues needed to be considered. In this paper, two hybrid end-effector posture-maintaining and obstacle-limits avoidance (hybrid PM-OLA) schemes are proposed and investigated for motion planning of redundant robot manipulators, which are based on the quadratic programming (QP) framework. The end-effector posture-maintaining, obstacle-avoidance, and the joint-angular-limits are formulated as an equality constraint, inequality constraint, and bound constraint into the QP problem. With these hybrid PM-OLA schemes, the robot manipulator can avoid the obstacle and joint physical limits when executing end-effector tasks. The hybrid PM-OLA schemes are finally transformed into linear variational inequalities and solved by a recurrent neural network. Computer simulations and physical experiments substantiate the effectiveness, accuracy, safety, and the practicability of the proposed hybrid PM-OLA schemes. Comparisons with other schemes show that the proposed hybrid PM-OLA schemes are more suitable for applications.

Acceleration-Level Multi-Criteria Optimization for Remedying Joint-Angle Drift of Redundant Manipulators on Complex Path Tracking

In this paper, to remedy the joint-angle drift problem of redundant manipulators at the acceleration level, a multi-criteria optimization motion planning (MCOMP) scheme is proposed and investigated for redundant manipulators. In addition, the proposed scheme considers physical constraints and guarantees values of the joint-velocity and joint-acceleration to approach zero at the end of the path-tracking task. The proposed scheme is reformed into one standard quadratic program problem, which is then solved by the simplified linear variational inequalities-based primal-dual neural network (S-LVI-PDNN). Furthermore, three tracking path computer simulations (i.e., “Nut line” pattern, “Peach” pattern, and Chinese character “tu” pattern) are illustrated, which verify the validity and advantage of the proposed scheme. Finally, the physical experiment based on the JACO2 manipulator further verifies the practicability of the proposed scheme for solving the joint-angle drift of redundant manipulators.

Paper-cutting operations using scissors in Drury's law tasks

Human performance modeling is a core topic in ergonomics. In addition to deriving models, it is important to verify the kinds of tasks that can be modeled. Drury's law is promising for path tracking tasks such as navigating a path with pens or driving a car. We conducted an experiment based on the observation that paper-cutting tasks using scissors resemble such tasks. The results showed that cutting arc-like paths (1/4 of a circle) showed an excellent fit with Drury's law (R2 > 0.98), whereas cutting linear paths showed a worse fit (R2 > 0.87). Since linear paths yielded better fits when path amplitudes were divided (R2 > 0.99 for all amplitudes), we discuss the characteristics of paper-cutting operations using scissors.

Skill-based human–robot cooperation in tele-operated path tracking

This work proposes a shared-control tele-operation framework that adapts its cooperative properties to the estimated skill level of the operator. It is hypothesized that different aspects of an operator's performance in executing a tele-operated path tracking task can be assessed through conventional machine learning methods using motion-based and task-related features. To identify performance measures that capture motor skills linked to the studied task, an experiment is conducted where users new to tele-operation, practice towards motor skill proficiency in 7 training sessions. A set of classifiers are then learned from the acquired data and selected features, which can generate a skill profile that comprises estimations of user's various competences. Skill profiles are exploited to modify the behavior of the assistive robotic system accordingly with the objective of enhancing user experience by preventing unnecessary restriction for skilled users. A second experiment is implemented in which novice and expert users execute the path tracking on different pathways while being assisted by the robot according to their estimated skill profiles. Results validate the skill estimation method and hint at feasibility of shared-control customization in tele-operated path tracking.

Analysis of reaction torque-based control of a redundant free-floating space robot

Owing to the dynamics coupling between a free-floating base and a manipulator, the non-stationary base of a space robot will face the issue of base disturbance due to a manipulator’s motion. The reaction torque acted on the satellite base’s centroid is an important index to measure the satellite base’s disturbance. In this paper, a comprehensive analysis of the reaction torque is made, and a novel way to derive the analytical form of the reaction torque is proposed. In addition, the reaction torque null-space is derived, in which the manipulator’s joint motion is dynamically decoupled from the motion of the satellite base, and its novel expression demonstrates the equivalence between the reaction torque null-space and the reaction null-space. Furthermore, the reaction torque acted as an optimization index can be utilized to achieve satellite base disturbance minimization in the generalized Jacobian-based end-effector Cartesian path tracking task. Besides, supposing that the redundant degrees of freedom are abundant to achieve reaction torque-based active control, the reaction torque can be used to realize satellite base attitude control, that is, base attitude adjustment or maintenance. Moreover, because reaction torque-based control is a second-order control scheme, joint torque minimization can be regarded as the optimization task in reaction torque-based active or in-active control. A real-time simulation system of a 7-DOF space robot under Linux/RTAI is developed to verify and test the feasibility and reliability of the proposed ideas. Our extensive empirical results demonstrate that the corresponding analysis about the reaction torque is correct and the proposed methods are feasible.

Device-Free Localization via Dictionary Learning with Difference of Convex Programming

In this paper, we consider a method to solve the device-free localization (DFL) problem that is able to detect spatial obstruction via wireless network. A dictionary learning approach with difference of convex (DC) programming and DC algorithm is proposed to indicate target location based on learning data. By measuring the variation in the received signal strength of the wireless links indicating the locations of the obstructions, the physical target in the monitoring area can be estimated through a learned dictionary. We show that the DFL problem can be efficiently formulated as a non-convex optimization problem. We adopt a penalty function called the minimax concave penalty, which possesses good properties in terms of seeking sparsity, and solve the non-convex optimization problem using DC programming. Furthermore, the localization accuracy achieved during the path-tracking task is further improved by the proposed tracking neighborhood rule. The rule provides a solution for increasing the localization accuracy under time-varying conditions generated by sampling channels of sensor networks under noisy conditions. The proposed approach is validated on a real-world dataset and has the potential to be adopted flexibly in DFL applications.

冗長マニピュレータの冗長性を利用した高手先加速度出力実現のためのGAを用いた動作計画

We have proposed motion planning method to speeding up tracking hand speed for path tracking task with constant hand speed. The conventional methods have problems that the methods cannot apply to generalized manipulators and need long calculation time. In this paper, we propose a motion planning method to adopt genetic algorithm. In order to adopt genetic algorithm, we must resolve a new problem. The new problem is a lag between to be required output timing and output timing having genes. We resolved the new problem by estimating output of required timing using fuzzy estimation. The proposal method can apply to generalized manipulators and became calculation time short.

A dual-mode online optimization method for trajectory tracking of redundant manipulators

Purpose – The purpose of this paper is to present a dual-mode online optimization method (OOM) for trajectory tracking of the redundant manipulators. This method could be used to resolve the problem of the kinematics redundancy effectively when the manipulator moves in a limited space or its movements go through a singular point. Design/methodology/approach – In the proposed method, the physical limits of the manipulator in the torque level is considered as inequality constraints for the optimal scheme. Besides, a dual-mode optimal scheme is developed to yield a feasible input in each control period during the path tracking task of the manipulator, especially when it moves under the limited space or around the singular point. Then, the scheme is formulated as a quadratic programming; the computationally efficient quadratic programming solver based on interior method is formulated to solve the kinematic redundancy problem. Findings – The traditional pseudo inverse method (PIM) for the kinematic resolution to the redundant manipulator has some limitations, such as slow computation speed, unable to take joint physical limits into consideration, etc. Relatively, the OOM could be used to conquer the deficits of the PIM method. Combining with the dual-mode optimal scheme and considering the physical constraints in the torque level, the online method proposed in this paper is more robust and efficient than the existing method. Originality/value – In this paper, dual-mode OOM is first proposed for the resolution of the kinematics redundancy problem. Specific design of its model and the discussion of its performance are also presented in this paper.

A PD path-tracking controller plus inner velocity loops for a wheeled mobile robot

In this paper, we present a controller to solve the path-tracking task in a wheeled mobile robot. We show that a linear PD controller, driven by the tracking error, can be used to generate the desired profiles to be tracked by the motor velocities by means of two linear inner proportional-integral loops. We formally prove that an ultimate bound exists which can be rendered small by a suitable selection of the controller gains. This is the first time that such a result is presented in the literature when considering, simultaneously, both the kinematic and the dynamic models of the wheeled mobile robot.

Fast Motion of Path Tracking Task with Constant Hand Speed Using Redundant Manipulator

<div class=""abs_img""><img src=""[disp_template_path]/JRM/abst-image/00270001/09.jpg"" width=""300"" />Limits and a motion in state space</div> We propose a motion planning method for accelerating path-tracking task with constant hand speed using redundant manipulator. Tracking-speed should be increased to satisfy the joint torque and joint velocity limits. We propose a method using the state space of redundant manipulators to analyze these limits and to operate motion planning. This state space has a position on a trajectory, redundant pose, and redundant velocity axes. These limits are projected on state space. We consider, motion planning is path-finding problem on state space at a constant hand speed. To plan a faster motion, a constant hand speed is examined by finding a path with limits in state space. We use computer simulation to test and evaluate our proposed method on 3-link planar manipulator. Results demonstrated motion faster than a motion minimizing joint acceleration norm and a motion minimizing driving torque norm. We also verified a problem when our method was applied to an actual manipulator. </span>