Neural-Learning-Based Control for a Constrained Robotic Manipulator With Flexible Joints

He, Wei; Yan, Zichen; Sun, Yiming; Ou, Yongsheng; Sun, Changyin

doi:10.1109/tnnls.2018.2803167

Cited by 143 publications

(93 citation statements)

References 60 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Candidate NNs, including radial basis function (RBF) NN, RNN, and multi-layer feedforward NN, have been explored to approximate the robot forward dynamics model for adaptive trajectory tracking controller design [12]- [16]. In [17], an adaptive controller designed using RBF NN producing joint torque input was proposed to compensate the unknown dynamics and a payload for a Baxter robot.…”

Section: Related Workmentioning

confidence: 99%

Neural-Learning Trajectory Tracking Control of Flexible-Joint Robot Manipulators with Unknown Dynamics

Chen

Wen

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Fast and precise motion control is important for industrial robots in manufacturing applications. However, some collaborative robots sacrifice precision for safety, particular for high motion speed. The performance degradation is caused by the inability of the joint servo controller to address the uncertain nonlinear dynamics of the robot arm, e.g., due to joint flexibility. We consider two approaches to improve the trajectory tracking performance through feedforward compensation. The first approach uses iterative learning control, with the gradient-based iterative update generated from the robot forward dynamics model. The second approach uses dynamic inversion to directly compensate for the robot forward dynamics. If the forward dynamics is strictly proper or is nonminimum-phase (e.g., due to time delays), its stable inverse would be non-causal. Both approaches require robot dynamical models. This paper presents results of using recurrent neural networks (RNNs) to approximate these dynamical modelsforward dynamics in the first case, inverse dynamics (possibly non-causal) in the second case. We use the bi-directional RNN to capture the noncausality. The RNNs are trained based on a collection of commanded trajectories and the actual robot responses. We use a Baxter robot to evaluate the two approaches. The Baxter robot exhibits significant joint flexibility due to the series-elastic joint actuators. Both approaches achieve sizable improvement over the uncompensated robot motion, for both random joint trajectories and Cartesian motion. The inverse dynamics method is particularly attractive as it may be used to more accurately track a user input as in teleoperation.

show abstract

Section: Related Workmentioning

confidence: 99%

Neural-Learning Trajectory Tracking Control of Flexible-Joint Robot Manipulators with Unknown Dynamics

Chen

Wen

2019

2019 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

show abstract

“…The study was focused on an aerospace application but similar models can be adopted for flexible robotic surgery. Furthermore, a neural-learning-based control model was proposed for constraints control robotic systems with flexible joints in He et al [47]. A drawback of intelligent-based control systems is a requirement of training that hinders behavioral cloning.…”

Section: Literature Reviewmentioning

confidence: 99%

Motion and Trajectory Constraints Control Modeling for Flexible Surgical Robotic Systems

et al. 2020

View full text Add to dashboard Cite

Success of the da Vinci surgical robot in the last decade has motivated the development of flexible access robots to assist clinical experts during single-port interventions of core intrabody organs. Prototypes of flexible robots have been proposed to enhance surgical tasks, such as suturing, tumor resection, and radiosurgery in human abdominal areas; nonetheless, precise constraint control models are still needed for flexible pathway navigation. In this paper, the design of a flexible snake-like robot is presented, along with the constraints model that was proposed for kinematics and dynamics control, motion trajectory planning, and obstacle avoidance during motion. Simulation of the robot and implementation of the proposed control models were done in Matlab. Several points on different circular paths were used for evaluation, and the results obtained show the model had a mean kinematic error of 0.37 ± 0.36 mm with very fast kinematics and dynamics resolution times. Furthermore, the robot's movement was geometrically and parametrically continuous for three different trajectory cases on a circular pathway. In addition, procedures for dynamic constraint and obstacle collision detection were also proposed and validated. In the latter, a collision-avoidance scheme was kept optimal by keeping a safe distance between the robot's links and obstacles in the workspace. Analyses of the results showed the control system was optimal in determining the necessary joint angles to reach a given target point, and motion profiles with a smooth trajectory was guaranteed, while collision with obstacles were detected a priori and avoided in close to real-time. Furthermore, the complexity and computational effort of the algorithmic models were negligibly small. Thus, the model can be used to enhance the real-time control of flexible robotic systems.

show abstract

“…where, u 0 (t) is the control command. The control law based on precise model is given by (25) where, k 1 , k 2 , k 3 k p , α and β are positive constants; u a (t) is an auxiliary signal; B(t) and ζ(t) are auxiliary functions that handle the effect of the multiple constraints. u a (t), B(t) and the time derivative of ζ(t) are given by…”

Section: Model-based Boundary Controlmentioning

confidence: 99%

“…To avoid collisions between the sinking platform and other obstacles, the output constraint is considered in safety specifications of the MPSLS. In Reference [25], full-state feedback NN control combining with Barrier Lyapunov Function (BLF) is proposed for a serial mechanism with state constraints and no prior knowledge of the uncertainties. Adaptive fuzzy NN control is designed for a robot with unknown part, where a tan-type BLF is applied to ensure the boundedness of the output signal [26].…”

Section: Introductionmentioning

confidence: 99%

Modeling and Control for a Multi-Rope Parallel Suspension Lifting System under Spatial Distributed Tensions and Multiple Constraints

et al. 2018

View full text Add to dashboard Cite

The modeling and control of the multi-rope parallel suspension lifting system (MPSLS) are investigated in the presence of different and spatial distributed tensions; unknown boundary disturbances; and multiple constraints, including time varying geometric constraint, input saturation, and output constraint. To describe the system dynamics more accurately, the MPSLS is modelled by a set of partial differential equations and ordinary differential equations (PDEs-ODEs) with multiple constraints, which is a nonhomogeneous and coupled PDEs-ODEs, and makes its control more difficult. Adaptive boundary control is a recommended method for position regulation and vibration degradation of the MPSLS, where adaptation laws and a boundary disturbance observer are formulated to handle system uncertainties. The system stability is rigorously proved by using Lyapunov's direct method, and the position and vibration eventually diminish to a bounded neighborhood of origin. The original PDEs-ODEs are solved by finite difference method, and the multiple constraints problem is processed simultaneously. Finally, the performance of the proposed control is demonstrated by both the results of ADAMS simulation and numerical calculation.

show abstract

Neural-Learning-Based Control for a Constrained Robotic Manipulator With Flexible Joints

Cited by 143 publications

References 60 publications

Neural-Learning Trajectory Tracking Control of Flexible-Joint Robot Manipulators with Unknown Dynamics

Neural-Learning Trajectory Tracking Control of Flexible-Joint Robot Manipulators with Unknown Dynamics

Motion and Trajectory Constraints Control Modeling for Flexible Surgical Robotic Systems

Modeling and Control for a Multi-Rope Parallel Suspension Lifting System under Spatial Distributed Tensions and Multiple Constraints

Contact Info

Product

Resources

About