Adaptive Robot Control Research Articles

A new tracking walking adaptive control of uncertain biped robot by state feedback and output feedback

In this paper, a walking algorithm of a biped robot with unknown dynamics has been addressed by proposing a new adaptive control based on the Modified Function Approximation Technique (MFAT) augmented with backstepping control, using state feedback and output feedback. The classical ZMP, the preview controller on the 3- Dimensional Linear Inverted Pendulum Model (3D-LIPM), is a stable walking algorithm but does not allow high accuracy, high speed, and robustness due to the ground environment, and also due to the dynamics uncertainties caused by the complex structure of these kinds of robots. To improve the accuracy of the walking tracking performance of the biped robot and its robustness against dynamics uncertainty and external perturbations, a combination of backstepping control and MFAT strategy have been intended. Recursive Lyapunov function is developed to ensure the closed-loop system stability. Experiment simulation and comparative study were carried out with biped robot to verify the performance and the robustness of the developed control strategy.

Robust adaptive PD-like control of lower limb rehabilitation robot based on human movement data.

The combination of biomedical engineering and robotics engineering brings hope of rehabilitation to patients with lower limb movement disorders caused by diseases of the central nervous system. For the comfort during passive training, anti-interference and the convergence speed of tracking the desired trajectory, this paper analyzes human body movement mechanism and proposes a robust adaptive PD-like control of the lower limb exoskeleton robot based on healthy human gait data. In the case of bounded error perturbation, MATLAB simulation verifies that the proposed method can ensure the global stability by introducing an S-curve function to make the design robust adaptive PD-like control. This control strategy allows the lower limb rehabilitation robot to track the human gait trajectory obtained through the motion capture system more quickly, and avoids excessive initial output torque. Finally, the angle similarity function is used to objectively evaluate the human body for wearing the robot comfortably.

Adaptive control of parallel robots with uncertain kinematics and dynamics

One of the most challenging issues in adaptive control of robot manipulators with kinematic uncertainties is the requirement of inverse Jacobian matrix in regressor form. This requirement is inevitable in the case of the control of parallel robots, whose dynamics formulation are derived in the task space. In this paper, an adaptive controller is proposed for parallel robots based on representation of Jacobian matrix in regressor form with asymptotic trajectory tracking. The main idea of this paper is separation of determinant and adjugate of Jacobian matrix in order to represent them into a new regressor forms. Simulation and experimental results on a 2-DOF RPR and a 3-DOF redundant cable driven robot, respectively, verify promising performance of the proposed method in practice.

Development of an Adaptive Trajectory Tracking Control of Wheeled Mobile Robot

Classical modeling and control methods applied to differential locomotion mobile robots generate mathematical equations that approximate the dynamics of the system and work relatively well when the system is linear in a specific range. However, they may have low accuracy when there are many variations of the dynamics over time or disturbances occur. To solve this problem, we used a recursive least squares (RLS) method that uses a discrete-time structure first-order autoregressive model with exogenous variable (ARX). We design and modify PID adaptive self-adjusting controllers in phase margin and pole allocation. The main contribution of this methodology is that it allows the permanent and online update of the robot model and the parameters of the adaptive self-adjusting PID controllers. In addition, a Lyapunov stability analysis technique was implemented for path and trajectory tracking control, this makes the errors generated in the positioning and orientation of the robot when performing a given task tend asymptotically to zero. The performance of the PID adaptive self-adjusting controllers is measured through the implementation of the criteria of the integral of the error, which allows to determine the controller of best performance, being in this case, the PID adaptive self-adjusting type in pole assignment, allowing the mobile robot greater precision in tracking the trajectories and paths assigned, as well as less mechanical and energy wear, due to its smooth and precise movements.

Application of Sensor Data Information Cognitive Computing Algorithm in Adaptive Control of Wheeled Robot

The four-wheel drive robot has a coupling relationship between the four wheels due to the characteristics of the wheel train distribution. During the operation, there are problems with the stability and control accuracy of the robot’s overall motion. To solve this problem, this paper constructs an adaptive control algorithm based on cognitive computing. We use real-time sensor data as learning samples for online learning, and obtain new sample averages, new feature values, feature vectors, and new subspaces. This information is stored in the semantic long-term memory by projecting the newly read sample into the subspace obtained in the previous calculation. In addition, fuzzy control and partial discharge control are combined to correct the stored information online. Taking into account the distribution characteristics of the wheel system structure, we reasonably allocate the overall error to a single wheel, which will convert the overall error correction into a single wheel error correction. The simulation experiment in the Matlab-Simulink environment shows that after using the fuzzy adaptive controller for error correction, the error value of the robot’s linear velocity and angular velocity is between −1 and 1.5. In addition, the followability and the performance of tracking the target are obviously improved, and the accuracy of robot motion control is improved.

Preliminary Evaluation of Composite Learning Tracking Control on 7-DoF Collaborative Robots

Abstract With the increase of computational power, adaptive control becomes more and more attractive for industrial robots due to the ability to handle parametric uncertainty and the potential to achieve higher tracking accuracy. This paper implements a recently developed adaptive control scheme termed composite learning robot control (CLRC) for tracking control of a 7-degree-of-freedom industrial collaborative robot named Franka Emika Panda. The desired trajectory is specifically designed to evaluate the performance of the CLRC compared with the standard adaptive robot control and composite adaptive robot control via both simulations and experiments. Comparative results demonstrate that the CLRC meets the requirement of real-time computation and outperforms the other two control schemes with respect to tracking accuracy and parameter convergence.

Leveraging multimodal data for intuitive robot control towards human-robot collaborative assembly

In human-robot collaborative assembly, robots help human operators complete complex assembly tasks. However, controlling these robots is not intuitive given the constraints posed by the close proximity of the operator. In response to this need, a novel approach using multimodal data is developed for human-centred robot control in human-robot collaborative assembly. An interface design is developed to fuse multimodal communication channels for robust and adaptive robot control and then multimodal data are defined as control input for assembly task execution. This control scheme offers human operators symbiotic multimodal tools for proactive HRC with enhanced flexibility and adaptability.

A multizone cerebellar chip for bioinspired adaptive robot control and sensorimotor processing.

The cerebellum is a neural structure essential for learning, which is connected via multiple zones to many different regions of the brain, and is thought to improve human performance in a large range of sensory, motor and even cognitive processing tasks. An intriguing possibility for the control of complex robotic systems would be to develop an artificial cerebellar chip with multiple zones that could be similarly connected to a variety of subsystems to optimize performance. The novel aim of this paper, therefore, is to propose and investigate a multizone cerebellar chip applied to a range of tasks in robot adaptive control and sensorimotor processing. The multizone cerebellar chip was evaluated using a custom robotic platform consisting of an array of tactile sensors driven by dielectric electroactive polymers mounted upon a standard industrial robot arm. The results demonstrate that the performance in each task was improved by the concurrent, stable learning in each cerebellar zone. This paper, therefore, provides the first empirical demonstration that a synthetic, multizone, cerebellar chip could be embodied within existing robotic systems to improve performance in a diverse range of tasks, much like the cerebellum in a biological system.

Adaptive Control of Soft Robots Based on an Enhanced 3D Augmented Rigid Robot Matching

Despite having proven successful in generating precise motions under dynamic conditions in highly deformable soft-bodied robots, model based techniques are also prone to robustness issues connected to the intrinsic uncertain nature of the dynamics of these systems. This letter aims at tackling this challenge, by extending the augmented rigid robot formulation to a stable representation of three dimensional motions of soft robots, under Piecewise Constant Curvature hypothesis. In turn, the equivalence between soft-bodied and rigid robots permits to derive effective adaptive controllers for soft-bodied robots, achieving perfect posture regulation under considerable errors in the knowledge of system parameters. The effectiveness of the proposed control design is demonstrated through extensive simulations.

Adaptive control of a two-link robot using batch least-square identifier

We design a regulation-triggered adaptive controller for robot manipulators to efficiently estimate unknown parameters and to achieve asymptotic stability in the presence of coupled uncertainties. Robot manipulators are widely used in telemanipulation systems where they are subject to model and environmental uncertainties. Using conventional control algorithms on such systems can cause not only poor control performance, but also expensive computational costs and catastrophic instabilities. Therefore, system uncertainties need to be estimated through designing a computationally efficient adaptive control law. We focus on robot manipulators as an example of a highly nonlinear system. As a case study, a 2-DOF manipulator subject to four parametric uncertainties is investigated. First, the dynamic equations of the manipulator are derived, and the corresponding regressor matrix is constructed for the unknown parameters. For a general nonlinear system, a theorem is presented to guarantee the asymptotic stability of the system and the convergence of parameters' estimations. Finally, simulation results are discussed for a two-link manipulator, and the performance of the proposed scheme is thoroughly evaluated.

Adaptive Dynamic Surface Control of a Flexible Robot Based on the K-State Observer

Adaptive Dynamic Surface Control of a Flexible Robot Based on the K-State Observer

A state augmented adaptive backstepping control of wheeled mobile robots

The present paper aims to design an integrated kinematic/dynamic-based tracking controller for wheeled mobile robots (WMRs) considering motors’ dynamics. By defining a reference WMR, the role of kinematic controller is to not only minimize the posture error which indicates the difference between the reference and actual WMRs, but also to generate a desired path for the actual WMR. The kinematic tracking control problem of WMRs is so challenging if motors’ dynamics, parametric and nonparametric uncertainties and external disturbances are considered. Thus, proposing a dynamic control law alongside a kinematic control is unavoidable. In this study, we propose a new dynamic controller, namely, a state augmented adaptive backstepping such that the desired path is asymptotically tracked. Several numerical results accompanied by 3D simulations of trajectory tracking control of a WMR in ‘Simscape Multibody’ environment and comparisons with two well-designed controllers in the literature are reported to show the high performance of proposed control structure.

RBF Network Adaptive Control of SCARA Robot Based on Fuzzy Compensation

Facing the requirements of high-precision control of SCARA robot systems in assembly and handling, RBF network adaptive control method based on fuzzy compensated SCARA robots is proposed. First, a SCARA robot dynamics model is established and theoretically analyzed based on Newton’s Euler equations. Second, the RBF network is used to approximate the ideal nominal model. Then, the fuzzy compensator is used to modify the friction, disturbance, load of the system and other external factors to compensate; finally, MATLAB/Simulink software was used to simulate the effect of SCARA robot system with and without fuzzy compensator. Experimental research shows that the control accuracy of SCARA robot joints with fuzzy compensators has been improved by 43.42%, 67.47% and 65.41%, respectively. The research results can provide some guidance for the precise assembly and handling of SCARA robots in production.

Invariant Transform Experience Replay: Data Augmentation for Deep Reinforcement Learning

Deep Reinforcement Learning (RL) is a promising approach for adaptive robot control, but its current application to robotics is currently hindered by high sample requirements. To alleviate this issue, we propose to exploit the symmetries present in robotic tasks. Intuitively, symmetries from observed trajectories define transformations that leave the space of feasible RL trajectories invariant and can be used to generate new feasible trajectories, which could be used for training. Based on this data augmentation idea, we formulate a general framework, called Invariant Transform Experience Replay that we present with two techniques: (i) Kaleidoscope Experience Replay exploits reflectional symmetries and (ii) Goal-augmented Experience Replay which takes advantage of lax goal definitions. In the Fetch tasks from OpenAI Gym, our experimental results show significant increases in learning rates and success rates. Particularly, we attain a 13, 3, and 5 times speedup in the pushing, sliding, and pick-and-place tasks respectively in the multi-goal setting. Performance gains are also observed in similar tasks with obstacles and we successfully deployed a trained policy on a real Baxter robot. Our work demonstrates that invariant transformations on RL trajectories are a promising methodology to speed up learning in deep RL.

Robust Adaptive Terminal Sliding Mode Control of an Omnidirectional Mobile Robot for Aircraft Skin Inspection

In this paper, an adaptive terminal sliding mode control scheme for an omnidirectional mobile robot is proposed as a robust solution to the trajectory tracking control problem. The omnidirectional mobile robot has a double-frame structure, which adsorbes on the aircraft surface by suction cups. The major difficulties lie in the existence of nonholonomic constraints, system uncertainty and external disturbance. To overcome these difficulties, the kinematic model is established, the dynamic model is derived by using Lagrange method. Then, a robust adaptive terminal sliding mode (RATSM) control scheme is proposed to solve the problem of state stabilization and trajectory tracking. In order to enhance the robustness of the system, an adaptive online estimation law is designed to overcome the total uncertainty. Subsequently, the asymptotic stability of the system without total uncertainty is proved with basis on Lyapunov theory, and the system considering total uncertainty can converge to the domain containing the origin. Simulation results are given to show the verification and validation of the proposed control scheme.

Observer-based adaptive fractional-order control of flexible-joint robots using the Fourier series expansion: theory and experiment

In this paper, fractional-order observer/controller design for flexible-joint robots is developed. In order to eliminate the need for obtaining the regressor matrix, the Fourier series expansion is applied for uncertainty estimation. Voltage saturation nonlinearities are compensated in the control law; hence, knowledge of the actuator/manipulator dynamics model is not required in the proposed method. Uniformly ultimately boundedness of observer estimation error and joint position tracking error are guaranteed through Lyapunov stability concept. The case study is a single-link flexible-joint robot actuated by permanent magnet DC motors. Experimental results are presented to emphasize the successful practical implementation of the proposed algorithm. Based on the experimental results, the proposed controller considerably outperforms some previous related works using various criteria.

Control System for Vertical Take-Off and Landing Vehicle’s Adaptive Landing Based on Multi-Sensor Data Fusion

Vertical take-off and landing unmanned aerial vehicles (VTOL UAV) are widely used in various fields because of their stable flight, easy operation, and low requirements for take-off and landing environments. To further expand the UAV’s take-off and landing environment to include a non-structural complex environment, this study developed a landing gear robot for VTOL vehicles. This article mainly introduces the adaptive landing control of the landing gear robot in an unstructured environment. Based on the depth camera (TOF camera), IMU, and optical flow sensor, the control system achieves multi-sensor data fusion and uses a robotic kinematical model to achieve adaptive landing. Finally, this study verifies the feasibility and effectiveness of adaptive landing through experiments.

Adaptive Synchronization Control of Cable-Driven Parallel Robots With Uncertain Kinematics and Dynamics

Cable-driven parallel robots (CDPRs) are a new type of parallel robots with a mobile platform driven by several cables. The flexibility of the structure not only helps them perform better than traditional parallel robots, but also brings about the issues of model uncertainty and multicable coordination. To handle these problems, a novel adaptive synchronization control (ASC) scheme is proposed to suppress the uncertainties of kinematics and dynamics simultaneously, regulate the coordination motion of multiple cables, and finish high-precision tracking tasks. In the proposed scheme, apart from tracking error, a new synchronization error is introduced to describe the coordination motion relationship between adjacent cables. According to these defined errors, the kinematic and dynamic adaptation laws are designed through the linear expressions of kinematic and dynamic models, respectively. Finally, the ASC scheme is presented as well as a tension distribution algorithm. The tracking experiments are implemented on a redundantly actuated 3-degree-of-freedom CDPR with four cables. The proposed ASC scheme can effectively complete the correction of the model parameters by using the feedback of errors and enhance the tracking accuracy of each cable and the synchronization accuracy between all the cables significantly, thereby ultimately improving the control performance of the mobile platform.

Exponentially convergence for the regressor-free adaptive fuzzy impedance control of robots by gradient descent algorithm

Having the capability to estimate parametric and non-parametric uncertainties, this paper investigates a regressor-free adaptive model-reference scheme for impedance control of robotic systems interacting with an environment. Using the gradient descent algorithm for designing a fuzzy estimator makes the tune of controller’s parameters possible in different physical situations and uncertainties. Thanks to the voltage control strategy and fuzzy systems, there is no need for designers to have the knowledge of robots and actuators’ dynamics. In addition, the force feedback is not employed in the structure of control law. Using the Lyapunov-like stability analysis, not only the exponential convergence of error signal and its time derivative to zero are guaranteed in the decentralised form but also the boundedness of all signals is ensured. To confirm the efficiency of proposed control algorithm, several simulations as well as a comparison with a positioned-based impedance controller and a regressor-based adaptive impedance controller are conducted on a two-link planar robot manipulator considering a tunable desired trajectory and different stiffness of environment. Additionally, the proposed adaptive impedance controller is applied to a six degree of freedom revolute-joint manipulator to provide better evaluation.

Neural approximation-based adaptive variable impedance control of robots

Variable impedance control improves compliance and robustness in robot-environment interaction through variation of the desired stiffness and the desired damping. This paper proposes neural approximation-based variable impedance controllers for robots in robot-environment interaction. Constraints on variable impedance parameters are given to ensure the exponential stability of the desired first- and second-order variable impedance dynamics. Adaptive neural network controllers are proposed to ensure the achievement of the desired first- and second-order variable impedance dynamics through convergence of variable impedance errors. In the neural networks, deadzone modifications are utilized to enhance robustness by turning off adaptation when auxiliary tracking errors enter the constructed small neighbourhoods of zero. The proposed variable impedance control methods in this paper guarantee the stability and achievement of the desired variable impedance dynamics. Theoretical analysis and simulation results validate the effectiveness of the proposed variable impedance control methods.