This paper aims to resolve the three major issues of fault tolerant control (FTC) for robot manipulators: (i) the faster response, lower tracking errors, lower chattering and higher robustness of the FTC, (ii) the requirement of partial or full knowledge of robot dynamics for the design of model-based FTC, and (iii) the global fixed-time convergence of the system. First, a fixed-time controller based on a backstepping control is designed and its disadvantages are analysed. Then, an adaptive fuzzy backstepping control is developed to enhance the tracking performance of the system. The proposed approach does not require the full prior knowledge of robot dynamic model, thus facilitating implementation of the controller in practical applications. In addition, the tracking errors of the system will be practically convergent within a fixed-time, which provides additional system information in advance. The fixed time convergence of the system is mathematically proved and the performance of the system is demonstrated for FTC of a PUMA560 robot.

This study proposes a new distributed control method based on an adaptive fuzzy control for multiple collaborative autonomous underwater vehicles (AUVs) to track a desired formation shape within a fixed time. First, a formation control protocol based on a fixed-time backstepping sliding mode control is designed, in which the consensus cooperative tracking errors for each AUV will be formulated. Then, to compensate for the saturated control torques, an adaptive auxiliary variable is introduced. Finally, a fixed-time adaptive fuzzy logic control (FLC) is derived to approximate the unknown dynamics, in which the adaptive laws of the FLC is derived such that the adaptive signals and errors can be convergent within a fixed time. The fixed-time convergence is desired in practice because it provides an exciting property that the global convergence of the whole system is independent with the initial states of the AUVs. The computer simulation results for a consensus formation control of four AUVs show that the proposed formation control can provide higher tracking performance with lower and smoother control efforts.

Within the context of Nonlinear Model Predictive Control (NMPC) design for autonomous mobile robots, which face challenges such as parametric uncertainty and measurement inaccuracies, focusing on dynamic modelling and parameter identification becomes crucial. This paper presents a novel safety-critical control framework for a mobile robot system that utilises NMPC with a prediction model derived entirely from noisy measurement data. The Sparse Identification of Nonlinear Dynamics (SINDY) is employed to predict the system's state under actuation effects. Meanwhile, the Control Barrier Function (CBF) is integrated into the NMPC as a safety-critical constraint, ensuring obstacle avoidance even when the robot's planned path is significantly distant from these obstacles. The closed-loop system demonstrates Input-to-State Stability (ISS) with respect to the prediction error of the learned model. The proposed framework undergoes exhaustive analysis in three stages, training, prediction, and control, across varying noise levels in the state data. Additionally, validation in Matlab and Gazebo illustrates that the NMPC-SINDY-CBF approach enables smooth, accurate, collision-free movement, even with measurement noise and short prediction times. Our findings, supported by tests conducted with the Husky A200 robot, confirm the approach's applicability in real-time scenarios.

An electrohydraulic elastic manipulator (EEM) is a kind of variable stiffness system (VSS). The equilibrium position and stiffness controller are the two main problems which must be considered in the VSS. When the system stiffness is changed for a specific application, the system dynamics are significantly altered, which is a challenge in controlling equilibrium position. This paper presents adaptive robust control for controlling the equilibrium position of the EEM under the presence of the variable stiffness. The proposed control includes sliding mode controls (SMCs), radial basis function neural network (RBFNN), and backstepping technique. The RBFNN is employed to compensate for the uncertainties and the variant stiffness in mechanical dynamics and hydraulic dynamics. The Lyapunov approach and projection algorithm are used to derive the adaptive laws of the RBFNN and to prove the stability and robustness of the entire EEM. Finally, some experiments are implemented and compared with other controllers to prove the effectiveness of the proposed method with the variant stiffness.

Over the years, deep reinforcement learning (DRL) has shown great potential in mapless autonomous robot navigation and path planning. These DRL methods rely on robots equipped with different light detection and range (LiDAR) sensors with a wide field of view (FOV) configuration to perceive their environment. These types of LiDAR sensors are expensive and are not suitable for small-scale applications. In this paper, we address the performance effect of the LiDAR sensor configuration in DRL models. Our focus is on avoiding static obstacles ahead. We propose a novel approach that determines an initial FOV by calculating an angle of view using the sensor’s width and the minimum safe distance required between the robot and the obstacle. The beams returned within the FOV, the robot’s velocities, the robot’s orientation to the goal point, and the distance to the goal point are used as the input state to generate new velocity values as the output action of the DRL. The cost function of collision avoidance and path planning is defined as the reward of the DRL model. To verify the performance of the proposed method, we adjusted the proposed FOV by ±10° giving a narrower and wider FOV. These new FOVs are trained to obtain collision avoidance and path planning DRL models to validate the proposed method. Our experimental setup shows that the LiDAR configuration with the computed angle of view as its FOV performs best with a success rate of 98% and a lower time complexity of 0.25 m/s. Additionally, using a Husky Robot, we demonstrate the model’s good performance and applicability in the real world.