An Electric Differential System for an Autonomous Mobile Robot Based on Neural Network Model

This paper describes a neural network model for an electrical differential system for electric vehicle. When a vehicle drives along curved road lane, the speed of the inner wheel has to be different from that of the outer wheel in order to prevent the vehicle vibrating and traveling an unsteady path. Because each wheel of this electrical vehicle has an independent driving force, an electrical differential system is required to replace a gear differential system. However, it is difficult to analysis the nonlinear behavior of the differential system in relation to the vehicle speed and steering angle, as well as vehicle structure. Therefore, a neural network is used to learn the relationships. To realize the neural network model, the speed data was acquired for the inner wheel and outer wheel, using an experimental electric vehicle at various speeds and steering angles. With this information, the differential system can be controlled using a neural network model of the nonlinear relationships.

The goal of this research was to develop a fuzzy obstacle avoidance system for an autonomous mobile robot using IR detection sensors. This paper presents implemented control architecture for behavior-based mobile robot. The mobile robot is able to interact with an unknown environment using a reactive strategy determined by sensory information. Current research in robotics aims to build autonomous and intelligent robots, which can plan its motion in a dynamic environment. Autonomous mobile robots are increasingly used in well structured environment such as warehouses, offices and industries. Fuzzy behavior able to make inferences is well suited for mobile robot navigation because of the uncertainty of the environment. A rule-based fuzzy controller with reactive behavior was implemented and tested on a two wheels mobile robot equipped with infrared sensors to perform collision-free navigation. The experimental results have shown that the proposed architecture provides an efficient and flexible solution for small wheeled mobile robots.

Robotics is a scientific discipline which includes the operation and development of robots and other fields of computer science, as well as electrical and mechanical engineering and high-performance modular control systems. This paper reports the first results of a research project that uses a previously developed MES - Modular Electronic System for autonomous mobile robots and for developing robots to use the MES in other scientific applications. This approach offers the ability to build a scalable and flexible control system with only a few modules. A novel feature of our approach is its modular integration of electronics with the ability to multitask, which can be adapted for particular applications. We demonstrate the robustness of this approach in controlling an indoor mobile robot for the EUROBOT 2009 and 2010.

This study aims to solve the issues of nonlinearity, non-integrity constraints, under-actuated systems in mobile robots. The wheeled robot is selected as the research object, and a kinematic and dynamic control model based on Internet of Things (IoT) and neural network is proposed. With the help of IoT sensors, the proposed model can realize effective control of the mobile robot under the premise of ensuring safety using the model tracking scheme and the radial basis function adaptive control algorithm. The results show that the robot can be controlled effectively to break the speed and acceleration constraints using the strategy based on the model predictive control, thus realizing smooth movement under the premise of safety. The self-adapting algorithm based on the IoT and neural network shows notable advantages in parameter uncertainty and roller skidding well. The proposed model algorithm shows a fast convergence rate of about 2 s, which has effectively improved performances in trajectory tracking and robustness of the wheeled mobile robot, and can solve the difficulties of wheeled mobile robots in practical applications, showing reliable reference value for algorithm research in this field.

This research work involves the speed control of a mobile robot where stabilization is provided by Non-linear controller. A Mobile Robot capable of following human target, assisted by various sensors that detects the clearance distance between the target and the robot to avoid collision or to maintain constant distance needs a robust control system. A robot in order to follow a human or target which has variable speed must have decision capabilities to decide when to speed up or slow down according to the situation. This decision can be obtained by the use of Artificial Neural Network (ANN) which reduces the burden on the controller reducing the complexity of calculation involved to control the speed of the motors. All these above sensors and actuators provide values as input to the Neural Network database for learning stage providing classification into several actions. The classes and weights obtained by the Neural Network learning phase is then used to vary the speed of the Robot. The speed however being unstable and providing several unnecessary movements will then be stabilized by using Linear Quadratic Regulator control algorithm. Thus, providing a complete solution to setting a fluent and stable Mobile Robot that can track and follow and target under any conditions.

This article presents experimental studies of fuzzy logic application to control a two-wheel mobile robot(TWMR) system. The TWMR system is composed of two systems, an inverted pendulum system and a mobile robot system. Although linear controllers can stabilize the TWMR, fuzzy controllers are expected to have robustness to uncertainties so that the resulting performances are expected to be better. Nominal fuzzy rules are used to control balance and position of TWMR. Fuzzy logic is embedded on a DSP chip to control the TWMR. Balancing performances of the PID controller and the fuzzy controller under disturbances are compared through extensive experimental studies.

The purpose of this paper is to detail the development of a mobile robot and control support system. The robot has five infrared (IR) ray sensors and three ultrasonic sensors to enable it to follow a guide person with an IR ray transmitter. The robot follows the IR rays emitted by the transmitter and moves towards its destination. The control system has been developed by using network technology (client/server model) based on the TCP/IP protocol; the CPU of the robot system has a low-enough speed for this. The advanced control strategy for the mobile robot is carried out with a high-speed host server computer connected through the TCP/IP network. In this paper, the autonomous mobile robot system and the control support system aided by the TCP/IP network are described.

Mobile robots have been the subject of research and experimentation for several decades. They combine mobility, sensor feedback, and smart control to achieve specific tasks-many times autonomously. One such task is autonomous charging. In this paper, the autonomous positioning of a differential-drive mobile robot above an inductive wireless charger is tested. Wireless charging is an increasingly popular technology for contactless power transfer, but it usually requires precise positioning of the receiver above the charger for effective charging to take place. The experimental mobile robot in this paper uses a camera sensor and computer-vison algorithm to approach a color target that marks the charger location. Then, the mobile robot uses misalignment-sensing coils to detect and correct small lateral misalignments with the charger. Measurements from the encoders on the robot wheels are used in a dual-loop controller featuring a linear quadratic regulator (LQR) to achieve the robot control objectives. The robot is successful in approaching and positioning itself within ±5 mm of the wireless charger center in several experimental trials. The hardware and control methods used in this experiment can be applied to similar systems to achieve autonomous wireless charging.

Mobile robot motion control is simplified to a DC motor motion control that may include gear system. The simplest and widespread approach to control the mobile robot motion is the differential drive style, it consists of two in-lines with each a DC motor. Both DC motors are independently powered so the desired movements will rely on how these two DC motors are commanded. Thedevelop design, model and control of Mechatronics mobile robotic system is presented in this paper. The developed robotic system is intended for research purposes as well as for educational process. The model of proposed mobile robot was created and verified using MATLAB-Simulink software.

Algorithms for mobile robotic systems are generally implemented on purely digital computing platforms. Developing alternative computational platforms may lead to more energy-efficient and responsive mobile robotics. Here, we report a hybrid analog-digital computing platform enabled by memristors on a mobile inverted pendulum robot. Our mobile robotic system can tune the conductance states of memristors adaptively using a model-free optimization method to achieve optimal control performance. We implement sensor fusion and the motion control algorithms on our hybrid analog-digital computing platform and demonstrate more than one order of magnitude enhancement of speed and energy efficiency over traditional digital platforms.

The construction of a smart autonomous mobile robot system that can operate in an anonymous environment can be difficult. Building an autonomous mobile robot requires collecting data from sensors and cameras in order to recognize the surrounding environment, get knowledge of existing landmarks, and figure out its position and orientation. Many research studies have been carried out in recent years providing algorithms for achieving autonomous motion of mobile robot systems and object detection. The most common platform utilized for robot motion design is ROS (Robot Operating System) and for object detection YOLO (You Only Look Once) is a common choice. Additionally, the autonomous system needs motion planning in a systematic way to avoid obstacles by using LIDAR or other sensing methods generating the feedback signals required for control of motion around occupied spaces. One of the most effective and versatile feedback systems for mobile robot control can be constructed using visual feedback, which relies on a high-resolution camera that processes the image in real-time and the result is fed back to the control system for decision making. Visual feedback can be employed alone without sensors for feedback control of autonomous mobile robots, and it can be used for multiple tasks like path planning, obstacle avoidance, object detection, object recognition in addition to motion control. In this research, results of design and construction of an autonomous mobile rescue robot for finding victims through video data are presented. It is aimed to find victims via applying video as a data collection and feedback generation tool in the autonomous mobile robot control system. The visual feedback and YOLO v3 are used not only for finding victims but also for motion control. Our autonomous mobile robot is designed to move smoothly to the victim's direction and avoids obstacles by using ROS Global Planner. The robot is tested in multiple scenarios in different locations, various obstacle and victim numbers, and satisfactory results with good performances are obtained.

Stability analysis and motion planning strategies with fuzzy coordinator and learning for mobile base robotic part macro/micro-assembly tasks

This paper describes a novel application of mobile robot technology to the construction of mobility for the frail blind. Trajectory control of an experimental mobile robot using proposed neural network based controller structure for frail blind persons are presented. The robot is a non-holonomic experimental mobile robot with all electronic equipments. A prescribed double triangle reference trajectory is employed to test the robot with proposed controller structure for following exact trajectory of blind disable persons. The gain parameters of the P controller are tuned with neural network. The results of the proposed adaptive neural network based P controller are improved that this controller has superior performance at adapting large disturbances on the mobile robot.

A dead reckoning system for a wheeled mobile robot was designed, and the method for robot’s pose estimation in the 3D environments was presented on the basis of its rigid-body kinematic equations. After analyzing the locomotion architecture of mobile robot and the principle of proprioceptive sensors, the kinematics model of mobile robot was built to realize the relative localization. Considering that the research on dead reckoning of mobile robot was confined to the 2 dimensional planes, the locomotion of mobile robot in the 3 coordinate axis direction was thought over in order to estimate its pose on uneven terrain. Because the computing method in a plane is rather mature, the calculation in height direction is emphatically represented as a key issue. With experimental results obtained by simulation program and robot platform, the position of mobile robot can be reliably estimated and the localization precision can be effectively improved, so the effectiveness of this dead reckoning system is demonstrated.

1. In this study, neural network (NN) and response surface (RS) models were developed to investigate the response [average daily gain (ADG) and feed efficiency (FE)] of young broiler chickens to dietary protein and lysine. For this purpose, data on their responses to dietary protein and lysine were extracted from the literature and separate NN and RS models were constructed. 2. Comparison between the NN and RS models revealed higher accuracy of prediction with the NN models compared to the RS models. In terms of R 2 values, the NN models developed for both ADG (R 2 = 0.923) and FE (R 2 = 0.904) were far superior to the RS models (R 2 for ADG = 0.511; R 2 for FE = 0.67). This suggests that the NN models can serve as an alternative option to conventional regression approaches including use of RS models. 3. Optimisation of the NN models developed for response to protein and lysine showed that diets containing 220.7 (g/kg of diet) protein and 12.85 (g/kg of diet) lysine maximise ADG, whereas maximum FE is achieved with diets containing 241.3 and 13.12 (g/kg) protein and lysine, respectively. Based on the optimisation results, optimal dietary protein and lysine concentrations for maximum FE in broiler chickens during the starting period are higher than for ADG.