Position and orientation of vehicle must keep the precise navigation and known its positioning at each place during travelling. To known and maintain its position, the currently the localization is the key of research on mobile vehicle. AGV is one of the significance of the present research trend. In industrial application, manufacturing factory is brought the mobile vehicle to incorporate working with other machine in order to being the automated manufacturing system. Many applications were adopted the AGV in different tasks such as material handling system, AS/RS system, transportation system, etc. Thus the research on the localization of mobile vehicle has increasingly researched in different aspects for improving the ability of vehicle. For reviewing the past research, several methods have been reported the localization of mobile vehicle such as [21-22] was developed a system in which the basic localization algorithm is formalized as a vehicle-tracking problem, employing an extended Kalman filter (EKF) to match beacon observations to a navigation map to maintain an estimate of mobile robot location. Tong and Tang proposed the robot self-localization. They applied the sensor fusion algorithm, which is used ultrasonic and CCD sensors, to filter out unreliable the sensor data reading. Moreover Extend Discrete Kalman Filters (EDKF) used to design for raw sensor data fusion to obtain more reliable representation in environment perception procedures . Modeling of ultrasonic range sensors was developed by , and they presented a probabilistic model of ultrasonic range sensors using back propagation neural networks trained on experimental data. Extend Kalman filter is used for update location from the prediction and observation matching as shown in [24-25]. Self-localization techniques by using probabilistic for mobile robot that based on the maximum-likelihood estimation were also done by . For outdoor navigation problem of mobile robot,  reported the localization with 2-D mobile robot localization based on observability analysis in order to determine the undergo difficulties. They developed the localization algorithm called multisensor localization system (MLS). Due to nonlinear system model obtained in state- space description, Extend Kalman Filter is applied for estimate the state X which is done in
In this paper, An AutomateGuidedVehicle (AGV) is presented. The developed algorithm is based on memorised path and kinematics determination of the movement. The vehicle position and deviation are calculated from rear wheels rotation measurement. The steering and driving command are determined from this deviation. Localization of AGV by Kaman filtering algorithm is presented. Overall structure of designing AGV is described. Control of AGV motion is implemented by using PID control scheme. Displacement axis and steering axis are separated to implement the motion control. We proposed the localization system for estimation of AGV. Position and orientation are estimated by Kalman filtering in state-space model. Position and orientation of AGV are measured and used for simulation for localization system. We conclude that the vehicle can reach from the initial position moved along with generated path with accurate location. A Schneider PLC is used to implement this control. The tests reveal a smooth movement and convenient deviation. The first prototype working, the next research steps will be development of a correction system to correct none detected errors. It will also be necessary to develop the fleet management strategy and software. Future work is planed to increase the accuracy of the system by equip more sensors for observation technique. Treatment of dynamic model and machine vision application of automated vehicle are also planed to the next step.
AGV, the AGV will triangulate its current position by comparing the map of reflectors layout store in memory with environment information . In contrast, inertial guided AGV uses various sensors e.g. accelerometer, gyroscope, and magnetometer to determine its position during navigation . Even though the free range AGV is more flexible and does not require a huge initial installation cost in terms of installing the required fixed path, the navigation system of a free range AGV navigation system is much complex and expensive compared to the fixed path AGV. This is because the navigation system involves various expensive sensors and complex system to aggregate and analyse the signals from various sensors in order to navigate the AGV as required. Thus, an alternative of a free range AGV is worthy to be designed and investigated so that a compromise can be reached between complexity and flexibility.
There are two major field that AGV is commonly implemented, the main part in industry as the material handling equipment, transferring load in warehouse, production line and loading unloading that need repeat process. Automated GuidedVehicle (AGV) now days not just been implemented in industry, there are also had been used in facilities like distributing medicine in hospital, in military as ground covering vehicle and so on. The main focus on these studies is the implementation of AGV in industry. There is several type of field in industry that needed the implementation of AGV. For example the transportation of containers, the volume of goods transported by containers through sea ports has been rapidly increasing during the last decade. Therefore automated container terminals (ACTs) have become an interesting research topic in order to increase the productivity and efficiency as well as to decrease the cost of container terminals. ACTs are equipped with automated container transshipment systems consisting of automated cranes and automated guided vehicles (AGV) (Adriaansen 2011). There are also research that been done by developing an AGV in warehouse, an intelligent forklift Automatic GuidedVehicle (AGV) been developed to perform various transporting tasks in factories and warehouses for improving the quality and efficiency as well as saving the manpower in manufacturing and service industries (Li et al. 2015). AutomateGuided Vehicles (AGV) has been applied for the flexible manufacturing system. Many factories were adopted it into assembly line or production line such as automobile, food processing, wood working, and other factories. Many researchers developed and designed in order to suite with their applications which are related to the main problem of factory (Butdee et al. 2008).
The developed algorithm is based on memorised path and kinematics determination of the movement. The vehicle position and deviation are calculated from rear wheels rotation measurement. The steering and driving command are determined from this deviation. Localization of AGV by Kaman filtering algorithm is presented. Overall structure of designing AGV is described. Control of AGV motion is implemented by using PID control scheme. Displacement axis and steering axis are separated to implement the motion control. 
Automated guided vehicles (AGVs) are self-driven vehicles. Early types of AGVS were introduced around 1954. They are used to transport material from one location on the facility floor to another without any accompanying operator, and are widely used in material handling systems, flexible manufacturing systems, and container handling applications. With the advance of technology, more sophisticated machines are available, which considerably reduce machining and internal setup time . The aim of production planning includes along with fast production, efficient transportation of material between the workstations and in and out of storage. Flexible material handling systems are required to perform an efficient routing of material with random handling capability. The use of AGVs increases flexibility, since the flow path can easily be selected from number of alternative paths, or, can be reconfigured to accommodate new locations. The design of material handling guide path has a significant implication on the overall system performance and reliability, since it has a direct impact on the travel time, the installation cost, and the complexity of the control system software.
AGV can be defined as an unmanned, autonomous vehicle that is a subset of mobile robots. The AGV may have on-board computer to store path planning and motion control system. A traditional AGV usually rely on either wired technology, guided tape, laser technology or inertial guidance systems that make use of the gyroscopes and wheel odometry for their path planning system (Kelly et al., 2007). These technologies have made the AGVs dependent on the infrastructure in order to navigate around the facilities where it was deployed. The dependency on the infrastructure demands every single AGV to be in operational state to avoid any disruption to the whole system. This system is, more or less, similar to a conveyor belt system.
Page 11 Figueiredo, et.al  describe a method to use intelligent agents for the control of a robot which has been simulated by a Khepera simulator. The intelligence of these agents is based on a Fuzzy Logic system. These systems have shown by repeated application to the area of mobile robotics that they are an effective procedure for control problems. The behaviour that is expected by each agent at each moment is defined with the help of a set of fuzzy rules. This is based on the position of the robot, its sensor values and heading angle. A path memory system was also developed so that the robot is not stuck by particular obstacles. This allows the robot to look for other alternatives on getting trapped. For a control system that must be capable of avoiding dead end situations, this method has again resulted in a successful combination of computational intelligence and the agents‘ theory.
Basically, Motion Control includes two sections: one is path planning, the other one is path tracking or following. Model Predictive Control (MPC) has been popular in industry for a long time . The key feature of MPC is explicit use of a dynamical process model for controlled variable prediction at a future time horizon and calculation of a control actions to minimize a cost function . It can be used for both application, path planning as a planner and path tracking as a controller. It optimizes a performance cost satisfying the physical constraints, which is initialized by the real measurements, to obtain a sequence of control moves or control laws . Dynamics model developed in Chapter 3 is nonlinear, presenting nonlinear state-space equation, which requires a nonlinear model predictive control controller for path tracking. Current nonlinear MPC can handle high nonlinearity well, so there is no need to further linearize the nonlinear problem, which might have negative effect on the accuracy of the problem. Nonlinear model predictive control, or NMPC, is a variant of model predictive control (MPC) that is characterized by the nonlinear system models in the prediction . NMPC executes the iterative solution of optimal control problems on a specific prediction horizon. Several optimal control methods are used to get the numerical solution of the NMPC, including single shooting and multiple shooting methods. These optimal control methods indicate the optimal control problem is transformed to nonlinear programming program.
Generally, AGVs consist of onboard microprocessors and supervisory control system that helps in various tasks, such as tracking and tracing a modules and generating and/or distributing transport orders to perform a specific task [6-8]. These are able to navigate a guide path network that is flexible and easy to program. Laser, camera, optical, inertial and wire guided systems are used as navigation methods on AGVs. AGVs are programmed for many different and useful maneuvers, like spinning and side-traveling, which allow for more effective production. Some are designed for the use of an operator, but most are capable of operating independently.
In this paper, the requirement for trolleys and conveyers to deal with transfer of materials in big industries is totally eliminated. For the above requirement an automated GuidedVehicle has been implemented & controlled by a microcontroller. Generally the power from fuel is used for the existing methods of handling material. In the future there is going to be a depletion of fuel in the world due to various reasons. This automated guidedvehicle can be employed to avoid this type of fuel depletion thereby reducing the requirements of manpower. In this vehicle, a microcontroller is used to control the path of vehicle in an automatic manner. The power is supplied to the GuidedVehicle by a rechargeable battery. The DC motors used to apply movements to guidedvehicle are driven by power previously stored in the battery. The microcontroller controls the velocity (speed of rotation) of DC motor. The available types of guided vehicles and conveyers use petrol or diesel as fuel for their operation. Large amount of fuel will be consumed by these types of vehicles for a specified period. This guidedvehicle employs a rechargeable battery which can easily detachable and replaceable and employed for charging while the vehicle is under idle operation. The microcontroller can be programmed to decide the path for the vehicle which can be changed if needed.
Autonomous robots are independent of any controller and can act on their own. The robot is programmed to respond in a particular way to an outside stimulus. The bump- and -go robot is a good example. This robot uses bumper sensors to detect obstacle. When the robot is turned on, it moves in a straight direction and when it hits an obstacle, the crash triggers its bumper sensor. The robot gives a programming instruction that asks the robot to back up, turn to the right direction and move forward. This is its response to every bump. In this way, the robot can change direction every time, it encounters an obstacle. A more elaborate version of the same idea is used by more advanced robots .Robotics create new sensor systems and algorithms to make robots more perceptive and smarter. Today, robots are able to effectively navigate a variety of environments. Obstacle avoidance can be implemented as a reactive control law whereas path planning involves the pre-computation of an obstacle- free path which a controller will then guide a robot=along. Some mobile robots also use various ultrasound sensors to see obstacles or infrared. These sensors work in a similar fashion to animal echolocation. The robot sends out a beam of infrared light or a sound signal. It then detects the reflection of the signal. The robot locates this distance to the obstacles depending on how long it takes the signal to bounce back. Some advanced robots also use stereo vision. Two cameras provide robots with depth perception. Image recognition software then gives them the ability to locate, classify various objects. Robots also use smell and sound sensors to gain knowledge about its surroundings
Gaskin and Tanchoco (1987) presented a binary integer model to determine the optimal flow path for an AGV system. They only considered the movement of loaded vehicles unlike Maxwell and Muckstadt (1982). They did not make any assumptions about the flow path except that movement was restricted to certain areas (such as the aisles), nor did they discuss any generic solution method to the model. An example is solved to illustrate the approach used, but this approach cannot be generalized.
There are few review papers on AGV systems. However, they concentrate on only limited parts of the problem (Qiu et al. (2002) focus on scheduling and routing problems) or are not up to date (Sinriech, 1995; Co and Tanchoco, 1991; King and Wilson, 1991). Moreover, they ignore some areas such as idle-vehicle positioning and battery management. This paper attempts to fill this gap, by giving an extended overview of existing literature, including the most recent contributions, and also structures the design and implementation decision process for AGV systems. For each area, we review and classify key decision models. In addition, a new classification for dispatching rules, a guideline for selecting a suitable scheduling system and a decision framework for design and implementation of AGV systems are proposed. We also consider idle-vehicle positioning and battery management problem, which many review papers neglect. Finally, we make suggestions for some fruitful future research directions. We start with an introduction to AGV systems followed by a discussion of guide-path design in section 2. Section 3 investigates the problem of determining the required number of single- or multi-load vehicles. Section 4 reviews the problem of managing an AGV system including online and offline scheduling, vehicle dispatching, idle-vehicle positioning, battery management, vehicle routing and conflict resolution. In section 5, we illustrate the design and implementation decision process of an AGV system by a decision framework. Finally, in section 6 we draw conclusions and identify subjects for further research.
response of the controller is obtained; however, the small value of the lateral acceleration generated caused the comfort level to increase. If the fast response controller is selected, the comfort level of the vehicle is therefore reduced. Furthermore, the spike detection algorithm is introduced. The simulation results show that the algorithm is able to reduce the unwanted coordinates of the vehicle and achieve a smoother response. The experiment is carried out to monitor the noise characteristics of the GPS sensor. From that, the actual GPS data is fetched to the controller to monitor the controller response if the input data is noisy. The proposed controller is proven to be stable by simulation and experiment from the actual GPS data. However, noisy data will affect the performance of the controller as well. For future research, an Extended Kalman Filter will be investigated in order to estimate the GPS coordinate and reduce the noise in the position reading.
The analysis and modeling of AUV 3D path tracking problem were accomplished in a case study of a cylindrical helix path. The training environment for 3D path tracking was designed by applying deep reinforcement learning DDPG algorithm. A method of selecting actions based on positive distribution was adopted to maintain the exploratory action selection. The rudders angles and their rates of change was added to be the new term in reward function, and a boundary reward was also designed to form a part of the reward function. The new reward function was shown to be effective to lower the frequency of steering. The LOS method with the integral term added was adopted to provide an indication of the target course angle and target flight path angle. Furthermore, to enable the controller to observe the current disturbance and adjust outputs, a currents disturbance observer was proposed. The observer was found to perform very well in terms of anti-disturbance.
In order to improve the performance of battery and increase the security of electric vehicle, in the future work, these battery optimal control parameters should be validated on the road, and the results of validation based on the optimal control parameters simulation should be compared with the calculated battery optimal objective values. Then, the battery model which added PSO should be mounted in a controller, and control performance should be evaluated.
Locally available hardware components and materials were used in design and fabrication of the vehicle. Structure of the vehicle was very simple in construction and small in size to minimize the cost and weight of the vehicle to have better mobility and performance. Hybrid of ATV and AGV, as shown in Fig. 1 was designed to move from one location to another. The detailed auto cad drawings and bill of material is as follows.
The tokens inside the ‘base’ place indicate that there are AGV’s free to be allocated to a mission. Only the same coloured tokens in the MPN and the PPN can enable transitions enabling the movement of AGV’s and their working phases to be correlated. For example, once a token is placed into the ‘P2’ place, representing dispatch to station, then the transition between the ‘base’ and ‘pickup station’ places in the PPN is enabled. After the delay associated with travelling between the base and the station has expired this transition will fire and the token will be removed from ‘P2’ and a token of the same colour will be removed from ‘base’. Tokens of the same colour will then be placed in ‘P2’ and ‘pickup station’. The progression through the mission carries on in the same way. Once an AGV fails the corresponding token for that vehicle will reside in the place ‘down’ hence enabling a transition to ‘mission failure’ for the appropriate
In the next simulations, instead of using traffic condition analyzer all the time, we retrieved the up-to-date traffic conditions from the dynamic traffic condition database if they had been freshly updated. The total response time for different numbers of users is illustrated in Fig. 9. The A* Search algorithm regards each user as a dependent path planning task, so one’s planned result cannot be used for others. Consequently, the total response time would increase with the increasing number of users. On the other hand, the cellular automata approach evaluates the road condition for the whole region at the initial stage, so it only needs to check whether the starting point and the destination have been connected or not while planning a new route. Even the number of users might increase rapidly, the cellular automata approach does not have to repeatedly calculate the road condition, and the planned results can be provided to the following uses as well. Accordingly, our proposed scheme achieve cost less time than A* Search algorithm regardless of the increasing or decreasing number of users.