Optimal trajectory tracking control of robotic manipulator system added by discrete-time fast terminal sliding mode predictive approach.

Design of a control system for a diseased pig carcass transport robot based on laser slam and machine vision

Cooperative active disturbance rejection motion control of multi-manipulator based on mechanical-electrical-hydraulic joint simulation.

The tracking performance of robotic teleoperation systems is constrained by limited communication resources. To improve the communication efficiency and tracking accuracy, an integral adaptive event-triggered predefined-time control strategy is proposed. The integral adaptive event-triggered mechanism determines whether the master and slave robots need to update their data by evaluating the error integral between the current and previously triggered data, thereby reducing the communication network access frequency. Using the transmitted data at triggering moments, a predefined-time sliding mode controller is designed to ensure accurate position tracking between the master and slave. The stability of the overall system is proven and the superiority of the proposed strategy is verified via simulations. The proposed approach can significantly reduce information transmission and ensure that the position tracking error between the master and slave converges within a predefined time.

Image Formation in the Environment of a Mobile Robot''''s Choice and Their Classification Using Neural Networks and Logical-Linguistic Classification Algorithms. The article investigates the task of improving the accuracy and speed of image classification for mobile robot and UAV control systems under conditions of data uncertainty. An integrated approach combining fuzzy logic methods (logical-linguistic classification (LLC)) and neural network technologies is proposed. A mathematical model for image representation using attribute membership functions has been developed, allowing it to work with noisy and incomplete data. An algorithm for generating test data based on etalon images with an adjustable noise level (0 − 100%) was created. A comparative testing of the neural network approach and the LLC algorithm was conducted on sample sizes ranging from 680 to 68 000 images. It was experimentally established that the neural network demonstrates high efficiency with large data volumes and high noise levels (> 80%), while the LLC algorithm is more effective with small samples and moderate noise levels (50 − 60%). The minimum training sample size for stable operation of the neural network was determined to be 6 800 images. The practical significance of the work lies in the development of an adaptive classification system capable of operating in real-world conditions of robotic complexes with variable levels of informational uncertainty.

This article presents a proportional integral derivative (PID) control system for lower-limb rehabilitation robot that not only features satisfactory control performance for the pedal angle but also provides a function for pedal torque estimation. Nonlinear state feedback simplifies the stability analysis and control system design. The stability condition of the closed-loop system is derived based on a Lyapunov function. The PID controller ensures that the pedal angle tracks the reference trajectory. The equivalent input disturbance (EID) method in the control system was compared with the disturbance observer (DOB) and extended state observer (ESO) methods in terms of pedal torque estimation performance. The simulation results indicated that the EID method achieved a root mean square error of 0.37 N·m with 47.6% and 51.8% improvements over the DOB and ESO methods.

Biological quadrupeds exhibit diverse gaits optimised for speed and stability, but robotic counterparts struggle to match this versatility. Deep reinforcement learning offers a method to develop robotic control systems for complex locomotive behaviours that exhibit characteristics found in biological gaits. This study explores the emergence of intermediate to high-speed quadrupedal gaits using deep reinforcement learning without motion references. This study confirms that varying framework parameters can successfully produce several gaits, including a pace, bound, half-bound, and a pronk, as well as a novel ‘one-after-three’ pattern characterised by synchronised movement of three legs followed by a single supporting leg. In particular, the study achieved the first documented pace gait using this methodology, demonstrating that reference data is not required for complex gait development. Ultimately, the findings demonstrate how reinforcement learning without motion references can enable the discovery of locomotion strategies based solely on morphology and environmental interaction. The code and training framework used in this study are available here.

The study objective is to develop an unmanned vehicle for robotizing transport and warehouse operations at logistics enterprises. It is shown that robotization of transport operations in warehouses increases productivity and labor safety, helps to minimize manual labor, and increases the efficiency of warehouse operations. The concept of an unmanned transport system for robotizing warehouse logistics is presented, which is a mobile wheeled robot equipped with a lifting cargo platform and providing net load transportation with the possibility of self-unloading. Based on mathematical simulation methods, a model of a transporting module of a delivery robot has been developed, which makes it possible to study the kinematic parameters of its movement. A numerical study of the robot transport platform on a computer using a package of simulation software is carried out. A strength analysis of the most loaded structural elements of the robot frame is performed, which makes it possible to determine its load capacity and confirm the operability of the proposed structure. The novelty of the work is in developing a technique for studying the computational geometric model of the robot frame, which allows to identify critical areas in the design of the drive wheel axis of an electromechanical differential drive. The results of the conducted research provide prerequisites for developing an automatic control system of the delivery robot, ensuring the autonomy of its functioning. Conclusions: a mathematical model of an unmanned transport system for robotizing warehouse logistics is developed, its operating modes are studied, and a control method is proposed through a point with coordinates that are input into a special regulator of the control system for electric drives of traction wheels.

In this paper, we considered potential benefits of the neuromorphic control technique for solving specific challenges in robotic control. Developing a neuromorphic control system for a robot involves simulating the architecture and dynamics of biological neurons to perform control tasks. This differs from typical control techniques and frequently employs spiking neural networks (SNNs). SNNs are more closely related to our brains than conventional neural networks, as they incorporate temporal dynamics. Biological neurons transmit information using spikes. Neurons do not fire in each cycle, but rather when the membrane potential reaches a predetermined threshold, as in a binary system. When a neuron fires, it transmits a signal to the synapse. The control strategy presented in this paper is based on the Leaky Integrated-and-Fire (LIF) and Generalized Integrate-and-Fire (GIF) neuron models. We designed neuromorphic control systems and utilized three robotic systems as examples. Numerical simulations were used to demonstrate the stability, robustness, and effectiveness of the neuromorphic robot control system design.

The concept of a Brain–Computer Interface (BCI) represents a transformative advancement in human–machine communication. By establishing a direct connection between the human brain and external digital systems, BCIs enable control of computers, prosthetic devices, and robotic systems through neural signals—bypassing physical movement. This paper explores the fundamental architecture, signal acquisition techniques, data processing methods, and application domains of BCIs. A prototype model demonstrating the feasibility of translating EEG signals into machine commands is discussed, emphasizing system design, ethical implications, and real-world challenges. The study highlights the potential of BCI technology to revolutionize assistive communication, healthcare, and human–computer symbiosis

HighlightsWhat are the main findings?This study presents a novel framework for the modeling and control of robotic systems based on data gathered from real-time sensors.We developed and tested a scheme to estimate robot dynamics online from the trajectory data gathered during robot movements.What is the implication of the main finding?The proposed approach sidesteps the need for complete a priori knowledge of system parameters.Using this approach, robots with unmodeled dynamics can successfully operate in unknown environments.Traditional control of robotic systems relies on the availability of an exact model, which assumes complete knowledge of the robot’s parameters and all dynamic effects. However, this idealized scenario rarely holds in practice, as real-world interactions introduce unpredictable environmental influences, friction, and edge effects. This paper presents a novel data-driven approach to modeling and estimating robot dynamics by leveraging data collected during the robot’s movements. The proposed method operates without prior knowledge of the system parameters, thereby addressing the limitations of conventional model-based control strategies in complex and uncertain environments. Our unified data-driven framework integrates classical control theory with modern machine learning techniques, including system identification, physics-informed neural networks (PINNs), and deep learning. We demonstrate its efficacy in the case of a two-link robotic manipulator that achieves superior trajectory tracking and robustness to unmodeled dynamics. The technique is modular and can be extended to manipulators with more joints.

A central event-triggered nonlinear MPC approach to reduce the computational time of WMR.

High-precision camera calibration is essential for ensuring reliable environmental perception and precise visual servo control in robotic systems. Traditional target calibration methods have exhibited limited robustness and high sensitivity to environmental disturbances, primarily due to the dispersion of the coordinate system resulting from multiple target poses. An ArUco-pillar composite target is developed to improve the efficiency of feature point extraction and to enrich spatial information. At the same time, a fixed reference is integrated to reduce the dimensionality of the calibration parameter space. These innovations jointly contribute to enhanced calibration accuracy. Furthermore, a reward feedback-driven sampling strategy is introduced to improve the robustness of the calibration outcomes further. The proposed method is validated through both simulation and real-world experiments, in which the simulation data contain varying levels of uniformly distributed noise. Experimental results demonstrate that, compared with conventional methods, the proposed approach achieves significantly higher calibration accuracy and robustness.

Event-triggered intelligent critic control for uncertain robotic systems: Guaranteed optimal tracking with disturbance attenuation

Abstract The primary objective of this study is to develop an automatic spray coating system. The overall system architecture consists of a production line control system and a 7-axis robotic arm control system, each operating independently. A servo control board based on FPGA serves as the core for motion control. When a workpiece is suspended on a fixture and enters the spraying area, sensors detect whether any positional deviation has occurred. If no deviation is detected, the 7-axis suspended robotic arm executes the spraying process following a pre-defined trajectory. In the event of a deviation, the system immediately transmits the data to the robotic arm control computer, which recalculates a corrected path to compensate and ensure spraying precision. Experimental validation was conducted using a motorcycle shell sample provided by the manufacturer. Spray trajectory tracking tests were performed under both no deviation and 10° deviation conditions. The spraying motion of the robotic arm is derived through inverse kinematics, while the MDDS control method is applied in conjunction with forward kinematics to calculate positional errors along the X, Y, and Z axes. Results show that the maximum positional error in all three axes is less than 0.5 mm, and the final coating thickness ranged from 36 to 38 μm, meeting the manufacturer’s specification of 35-40 μm. The successfully developed automatic spray coating system significantly improves coating quality, operational efficiency, and system stability. It offers high scalability and serves as a practical and forward-looking automated solution for the advanced manufacturing industry.

Predefined-Time Reliable Control for Robotic Systems With Prescribed Performance

The development of robotics applications heavily relies on artificial intelligence and machine learning, which are prerequisites for creating ‎intelligent robotic systems. Furthermore, the development of intelligent robots requires feature selection, classification, and fuzzy rule-based ‎decision making. Because they immediately aid the elderly in receiving medical care, allowing them to go about their daily lives more ‎quickly and effectively, medical assistive robots are beneficial to society. By removing characteristics that don't contribute, such as noise, ‎null values in databases, and properties unrelated to classification problems, feature selection lowers the dimension of the data. Natural ‎language processing can be utilized in medical applications, such as providing medical assistance through robot arm control, to handle the ‎challenging task of directing the robot arm using elderly instructions or orders. To effectively convert speech to text and conduct ‎morphological, syntactic, and semantic analysis on the converted text to more precisely detect the commands issued to robots by older ‎adults, the Fuzzy Temporal Rule-based Semantic Analysis Algorithm (FTRSAA) is suggested in this study. Additionally, the efficient ‎design and execution of the system that helps the elderly are made possible by this voice-activated robot control system, which utilizes the ‎latest intelligent robot technology. By using these recently suggested algorithms to comprehend natural language texts generated from ‎discussions, it communicates with older people.

This research focuses on designing a control system for pesticide applicator robots on rice plants. Control is carried out via radio wave communication using a transmitter-receiver (Flysky FS-iA6 2.4 GHz). The remote can control the robot wheel (forward, backward and turn), boom sprayer (raise-fall and open-close), and spray pump. The research method is carried out using the waterfall model because it is under the needs that require a sequential flow in the process. The test results show that the use of a bevel gear gearbox can increase the torque value up to 3 times. The use of 4 electric motors further increases the stability of the robot's movement (RPM and torque) when given the maximum load of the robot. The boom sprayer successfully opens-closes and fluctuates smoothly at the optimum value of PWM 50 and voltage 2.35. The time required for the boom sprayer to open-close, and rise-fall is 30 s. The relay which functions as a switch is successfully controlled, so that the pump can be activated and deactivated in mode 2 at the input. Transmitter-receiver communication test was successfully carried out. Transmitter-receiver communication is capable of up to a distance of < 150 m. Input mode 1 on the transmitter successfully controls the boom sprayer. Input mode 2 successfully controls the motion of the wheels and pump.

Robotization of production processes and the use of 3D vision systems are currently becoming more and more popular. It allows for more flexibility in the robotic process as well as expands the possibilities of process control, depending on changes in the parameters of the object, its pose, and changes in the process itself. Unfortunately, the use of standard solutions is limited to a relatively small space in which the robot’s vision system operates. The use of the latest solutions in the field of Artificial Intelligence (AI) and external vision systems, in combination with the closed structures of industrial robot control systems, provides advantages by enhancing the digital awareness of the environment of robotic systems. This article presents an example of solving the problem of low digital awareness of the environment of robotic systems resulting from the limited field of view of vision systems used in industrial robots, while maintaining high precision of the systems consisting of the combination of a 3D vision system using a stereovision camera and software with AI elements with the control system of an industrial robot from FANUC and an integrated Robot Vision (iRVision) system to maintain the positioning accuracy of the robot tool.

Various robotic arm control systems have been proposed to support the daily lives of patients with severe motor impairments; however, existing robotic arm control devices typically require physical input devices, such as joysticks, which are often difficult for patients with motor impairments to use. To overcome these limitations, this paper proposes a new method for controlling a robotic arm using augmented reality and object detection. The system automatically configures the path from the robotic arm to the object, allowing all operations to be performed using only eye tracking. With precise object localization and an intuitive gaze-based interface, the proposed robotic arm control system offers a significant advantage for patients with motor impairments, providing a more accessible and user-friendly alternative to traditional control methods.