Control systems that ensure robot operation during failures are necessary, particularly when manipulators are operating in hazardous or hard-to-reach environments. In such applications, fault-tolerant robot controllers should detect failures and, using fault-tolerant control methods, be able to continue operation without human intervention. Fault-tolerant control (FTC) is becoming increasingly important in all industries, including production lines in which modern robotic manipulators are used. The use of fault-tolerant systems in robotics can prevent the production line from being immobilized due to minor faults. In this paper, an overview of the current state-of-the-art methods of fault-tolerant control in robotic manipulators is provided. This review covers publications from 2003 to 2022. The article pays special attention to the use of artificial intelligence (AI), i.e., fuzzy logic and artificial neural networks, as well as sliding mode and other control methods, in the FTC of robotic manipulators. The cited and described publications were mostly found using Google Scholar.

This paper describes the task of controlling a robot to enable energy savings in the case of one- or two-axis failure. The proposed algorithms are tested in a task similar to “pick and place” but without gripping. Obstacles are present in the robot’s workspace. The goal of the algorithm is to control the robot in such a way that energy consumption is minimized while also avoiding obstacles and ensuring fault tolerance in the event of axis failures. The algorithm uses a developed torque model of the robot, which is employed to calculate the energy requirements for each possible movement step in the robot’s position. In the robot’s control system, artificial intelligence methods are also applied. Specifically, a genetic algorithm is used to generate learning data for the selection of the optimal kinematic configuration of the robot, and a multilayer perceptron is utilized to predict the parameters of the defined reward function. This function is crucial for selecting the optimal action at each time step. The study demonstrates that the application of the algorithm leads to a reduction in robot energy consumption. Studies conducted in simulation and verified on a real robot for 10 different obstacle and target positions and 22 possible kinematic configurations of the robot, consisting of all axes active, any one axis inactive, or any two axes inactive, confirm the energy-saving possibilities.