Trajectory Tracking Control of Transformer Inspection Robot Using Distributed Model Predictive Control

To overcome the difficulty in tracking the trajectory of an inspection robot inside a transformer, this paper proposes a distributed model predictive control method. First, the kinematics and dynamics models of a robot in transformer oil are established based on the Lagrange equation. Then, by using the nonlinear model predictive control method and following the distributed control theory, the motion of a robot in transformer oil is decoupled into five independent subsystems. Based on this, a distributed model predictive control (DMPC) method is then developed. Finally, the simulation results indicate that a robot motion control system based on DMPC achieves high tracking accuracy and robustness with reduced computing complexity, and it provides an effective solution for the motion control of robots in narrow environments.

Dynamic event-driven neural network-based adaptive fault-attack-tolerant control for wheeled mobile robot system

In this article, the fault-attack control problem is investigated for wheeled mobile robot (WMR) systems subjected to actuator faults, disturbances, communication attacks, and limited communication resources. An event-observer based compensation controller is presented. With the help of the observer estimation values and the attack sleep/active instant trigger information, the tracking control performance is realized for the robot system with the assistance of the neural network approximation technology. Concretely, first, the robot system dynamic model with actuator faults, disturbances, and attacks is established. Then, an event-based proportional-integral observer (PIO) is established. In the observer framework, a state estimator, an actuator fault efficiency estimator, and a disturbance estimator are embedded. Based on the observer outputs, a second-order adaptive sliding mode fault-compensation reliable controller is presented. In this controller framework, the fault compensation, disturbance attenuation, and the attack sleep/active time instant information are contained to guarantee the reliability and performance recoverability of the robot system. Furthermore, a dynamic even condition and an adaptive trigger scheme are constructed in the sensor and actuator channel to achieve the communication-efficient purpose. Finally, two cases of the robot system are performed to verify the system recoverability of the presented approach.

Semantic-Structure-Aware Multi-Level Information Fusion for Robust Global Orientation Optimization of Autonomous Mobile Robots

Multi-camera-based simultaneous localization and mapping (SLAM) has been widely applied in various mobile robots under uncertain or unknown environments to accomplish tasks autonomously. However, the conventional purely data-driven feature extraction methods cannot utilize the rich semantic information in the environment, which leads to the performance of the SLAM system being susceptible to various interferences. In this work, we present a semantic-aware multi-level information fusion scheme for robust global orientation estimation. Specifically, a visual semantic perception system based on the synthesized surround view image is proposed for the multi-eye surround vision system widely used in mobile robots, which is used to obtain the visual semantic information required for SLAM tasks. The original multi-eye image was first transformed to the synthesized surround view image, and the passable space was extracted with the help of the semantic segmentation network model as a mask for feature extraction; moreover, the hybrid edge information was extracted to effectively eliminate the distorted edges by further using the distortion characteristics of the reverse perspective projection process. Then, the hybrid semantic information was used for robust global orientation estimation; thus, better localization performance was obtained. The experiments on an intelligent vehicle, which was used for automated valet parking both in indoor and outdoor scenes, showed that the proposed hybrid multi-level information fusion method achieved at least a 10-percent improvement in comparison with other edge segmentation methods, the average orientation estimation error being between 1 and 2 degrees, much smaller than other methods, and the trajectory drift value of the proposed method was much smaller than that of other methods.

Variational Information Bottleneck Regularized Deep Reinforcement Learning for Efficient Robotic Skill Adaptation

Deep Reinforcement Learning (DRL) algorithms have been widely studied for sequential decision-making problems, and substantial progress has been achieved, especially in autonomous robotic skill learning. However, it is always difficult to deploy DRL methods in practical safety-critical robot systems, since the training and deployment environment gap always exists, and this issue would become increasingly crucial due to the ever-changing environment. Aiming at efficiently robotic skill transferring in a dynamic environment, we present a meta-reinforcement learning algorithm based on a variational information bottleneck. More specifically, during the meta-training stage, the variational information bottleneck first has been applied to infer the complete basic tasks for the whole task space, then the maximum entropy regularized reinforcement learning framework has been used to learn the basic skills consistent with that of basic tasks. Once the training stage is completed, all of the tasks in the task space can be obtained by a nonlinear combination of the basic tasks, thus, the according skills to accomplish the tasks can also be obtained by some way of a combination of the basic skills. Empirical results on several highly nonlinear, high-dimensional robotic locomotion tasks show that the proposed variational information bottleneck regularized deep reinforcement learning algorithm can improve sample efficiency by 200-5000 times on new tasks. Furthermore, the proposed algorithm achieves substantial asymptotic performance improvement. The results indicate that the proposed meta-reinforcement learning framework makes a significant step forward to deploy the DRL-based algorithm to practical robot systems.

Robust tracking control for magnetic wheeled mobile robots using adaptive dynamic programming

To handle the tracking control problem of the magnetic wheeled mobile robot (MWMR), this paper developed an online robust tracking control scheme by adaptive dynamic programming (ADP). The problem, that how to achieve optimal tracking control of continuous-time (CT) MWMR system with the time-varying unknown uncertainty, can be solved indirectly through matching the optimal tracking control of the associated nominal system . A single critic NN-based actor-critic structure is tailored for simpler controller architecture. By minimizing the Bellman error with gradient descending and least-squares updating laws, the critic NN weights can be optimized online. Thus the optimal cost function and the optimal control signal can be approximated with high precision. Using the Lyapunov stability theorem, the convergence of the critic NN weights, and the stability of the closed-loop system is provided. Simulations, in comparison with robust PD control and adaptive control, are presented to illustrate the effectiveness of the proposed tracking control method for the MWMR.

Multi-robot path planning based on improved artificial potential field and fuzzy inference system1

In this paper, we propose a method to assess the collision risk and a strategy to avoid the collision for solving the problem of dynamic real-time collision avoidance between robots when a multi-robot system is applied to perform a given task collaboratively and cooperatively. The collision risk assessment method is based on the moving direction and position of robots, and the collision avoidance strategy is based on the artificial potential field (APF) and the fuzzy inference system (FIS). The traditional artificial potential field (TAPF) has the problem of the local minimum, which will be optimized by improving the repulsive field function. To adjust the speed of the robot adaptively and improve the security performance of the system, the FIS is used to plan the speed of robots. The hybridization of the improved artificial potential field (IAPF) and the FIS will make each robot safely and quickly find a collision-free path from the starting position to the target position in a completely unknown environment. The simulation results show that the strategy is effective and useful for collision avoidance in multi-robot systems.

Fuzzy dynamic output feedback H∞ control for continuous-time T-S fuzzy systems under imperfect premise matching

This paper addresses a fuzzy dynamic output feedback H_∞ control design problem for continuous-time nonlinear systems via T-S fuzzy model. The stability of the fuzzy closed-loop system which is formed by a T-S fuzzy model and a fuzzy dynamic output feedback H_∞ controller connected in a closed loop is investigated with Lyapunov stability theory. The proposed fuzzy controller does not share the same membership functions and number of rules with T-S fuzzy systems, which can enhance design flexibility. A line-integral fuzzy Lyapunov function is utilized to derive the stability conditions in the form of linear matrix inequalities (LMIs). The boundary information of membership functions is considered in the stability analysis to reduce the conservativeness of the imperfect premise matching design technique. Two simulation examples are provided to demonstrate the effectiveness of the proposed approach.

Improvement in a Surface Motor-Driven Planar Motion Stage

We report a surface motor-driven planar motion stage with an XYθZsurface encoder. The surface motor consists of two pairs of linear motors. Magnetic arrays are installed on the platen and stator windings of linear motors on the stage base. The platen is moved in the X and Y directions by X and Y linear motors. It is rotated around the Z axis by moment generated by the X or Y linear motors. The surface encoder consists of two two-dimensional (2D) angle sensors and an angle grid with 2D sinusoidal surface waves. The angle grid is installed on the platen. Sensors onside make the stage compact. The surface encoder is improved for higher positioning accuracy. Measurement errors of the surface encoder using two detectors – a quadrant PD and 2D PSD – are determined by simulation. The surface motor for increasing stage speed is modified. We conducted experiments comparing the previous prototype stage (Prototype I) and the improved stage (Prototype II).