• International Journal of Automotive Technology
• /
• v.3 no.2
• /
• pp.71-78
• /
• 2002

A new control method far vision-based autonomous vehicle is proposed to determine navigation direction by analyzing lane information from a camera and to navigate a vehicle. In this paper, characteristic featured data points are extracted from lane images using a lane recognition algorithm. Then the vehicle is controlled using new Levenberg-Marquardt neural network algorithm. To verify the usefulness of the algorithm, another algorithm, which utilizes the geometric relation of a camera and vehicle, is introduced. The second one involves transformation from an image coordinate to a vehicle coordinate, then steering is determined from Ackermann angle. The steering scheme using Ackermann angle is heavily depends on the correct geometric data of a vehicle and a camera. Meanwhile, the proposed neural network algorithm does not need geometric relations and it depends on the driving style of human driver. The proposed method is superior than other referenced neural network algorithms such as conjugate gradient method or gradient decent one in autonomous lateral control .

• Transactions of the Korean Society of Mechanical Engineers A
• /
• v.38 no.5
• /
• pp.551-557
• /
• 2014

This paper presents a robust lateral controller for autonomous guidance of a farm tractor in field operations. Although mechanical steering actuators have recently been used for passenger vehicles, the steering actuator of the farm tractor is based on a hydraulic system, resulting in limited bandwidth and a larger time delay. Based on a kinematic tractor model with steering actuator dynamics, a nonlinear control technique called dynamic surface control is applied to design a robust lateral controller that compensates for uncertainty owing to steering actuator and road geometry. Finally, tracking performance and robustness of the proposed controller are validated via commercial tractor simulations, with respect to the time delay of the steering actuator and road geometry (e.g., up and down hills), on a given field with a constant friction coefficient.

• The Journal of the Korea institute of electronic communication sciences
• /
• v.16 no.4
• /
• pp.699-708
• /
• 2021

In this paper, a steering control and speed control algorithm was presented for autonomous driving based on two vision sensors and road speed sign board. A car speed control algorithm was developed to recognize the speed sign by using TensorFlow, a deep learning program provided by Google to the road speed sign image provided from vision sensor B, and then let the car follows the recognized speed. At the same time, a steering angle control algorithm that detects lanes by analyzing road images transmitted from vision sensor A in real time, calculates steering angles, controls the front axle through PWM control, and allows the vehicle to track the lane. To verify the effectiveness of the proposed algorithm's steering and speed control algorithms, a car's prototype based on the Python language, Raspberry Pi and OpenCV was made. In addition, accuracy could be confirmed by verifying various scenarios related to steering and speed control on the test produced track.

• Journal of Drive and Control
• /
• v.17 no.4
• /
• pp.113-124
• /
• 2020

Most of the work of construction equipment and agricultural machinery is done in off-road conditions. Autonomous driving required in these conditions uses GPS sensors, and PID controllers to control their speed and position. The hydrostatic steering, which is composed of a PSU, hydraulic hoses, and cylinders, rather than a mechanical coupling is used in these equipments. The PSU plays a key role in hydrostatic steering. Precise control of the position under various conditions requires detailed behavioral analysis of the basic components and operation. Two Gerotor PSU is now a commonly used safer option. The components of the PSU can be divided into mechanical and hydraulic actuating elements by its behavior. Since the system is combined by mechanical and hydraulic elements, the modelings are performed using Amesim, which is one of the most effective for the multi-domain dynamic system analysis. To confirm the validity of the model, input torque and pressures are checked with varying steering speed. The opening and the steering speed of normal and newly designed control valve set is investigated with the effect of centering spring force and friction. Finally, simulation results with fully detailed model with two gerotors are analyzed and compared with simple model.

• Journal of Institute of Control, Robotics and Systems
• /
• v.7 no.10
• /
• pp.827-836
• /
• 2001

The PID controller has been widely applied to the most control systems because of its simple structure and east designing. One of the important points to design the PID control system is to tune the approximate control parameters for the given target system. To find the PID parameters using Ziegler Nichols(ZN) method needs a lot of experience and experiments to ensure the optimal performance. In this paper, CMIA(Cell Mediated Immune Algorithm) controller is proposed to drive the autonomous guided vehicle (AGV) more effectively. The proposed controller is based on specific immune responses of the biological immune system which is the cell mediated immunity. To verify the performance of the proposed CMIA controller, some experiments for the control of steering and speed of that AGV are performed. The tracking error of the AGV is mainly investigated for this purpose. As a result, the capability of realization and reliableness are proved by comparing the response characteristics of the proposed CMIA controllers with those of the conventional PID and NNPID(Neural Network PID) controller.

• Journal of the Korean Society for Precision Engineering
• /
• v.25 no.10
• /
• pp.58-66
• /
• 2008

In the development of intelligent vehicles, path tracking of unmanned vehicle is a basis of autonomous driving and automatic navigation. It is very important to find the exact position of a vehicle for the path tracking, and it is possible to get the position information from GPS. However the information of GPS is not the current position but the past position because a vehicle is moving and GPS has a time delay. In this paper, therefore, the moving distance of a vehicle is estimated using a direction sensor and a velocity sensor to compensate the position error of GPS. In the steering control, optimal fuzzy rules for the path tracking can be found through the simulation of Simulink. Real driving experiments show the fuzzy rules are good for the steering control and the position error of GPS is well compensated by the proposed estimation method.

• Journal of KIISE:Computing Practices and Letters
• /
• v.9 no.6
• /
• pp.674-682
• /
• 2003

Ship autonomous navigation is designated as what computerizes mental faculties possessed of navigation experts, which are building navigation plans, grasping the situation, forecasting the fluctuation, and coping with the situation. An autonomous navigation system, which consists of several subsystems such as navigation system, a collision avoidance system, several data fusion systems, and a motion control system, is based on an intelligent control architecture for the sake of integrating the systems. The motion control system, which is one of the most essential system in autonomous navigation system, controls its propulsion and steering gears to move the ship satisfying its hydrodynamic characteristics. This paper is the study on the ship movement control system and its implementation which are totally developed and run on virtual-world system. Receiving the high-level control values such as a waypoint presented from the collision avoidance system, the motion control system generates them to low-level control values for propulsion and steering devices. In the paper, we develop a ship motion controller using Oldenburger's theory based on mathematical fundamentals, and simulate it with various scenarios in order to verify its performance.

• Journal of Biosystems Engineering
• /
• v.26 no.1
• /
• pp.29-38
• /
• 2001

A navigation system was developed for autonomous guidance of a combine. It consisted of a DGPS, a machine vision system, a gyro sensor and an ultrasonic sensor. For an autonomous operation of the combine, target points were determined at first. Secondly, heading angle and offset were calculated by comparing current positions obtained from the DGPS with the target points. Thirdly, the fuzzy controller decided steering angle by the fuzzy inference that took 3 inputs of heading angle, offset and distance to the bank around the rice field. Finally, the hydraulic system was actuated for the combine steering. In the case of the misbehavior of the DGPS, the machine vision system found the desired travel path. In this way, the combine traveled straight paths to the traget point and then turned to the next target point. The gyro sensor was used to check the turning angle. The autonomous combine traveled within 31.11cm deviation(RMS) on the straight paths and harvested up to 96% of the whole rice field. The field experiments proved a possibility of autonomous harvesting. Improvement of the DGPS accuracy should be studied further by compensation variations of combines attitude due to unevenness of the rice field.

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.91.1-91
• /
• 2001

The subject of this paper is vision system analysis of the autonomous vehicle. But, autonomous vehicle is one of the difficult topics from the point of view of several constrains on mobility, speed of vehicle and lack of environment information. Therefore, we are application of the vision system so that autonomous vehicle. Vision system of autonomous vehicle is likely to eyes of human. This paper can be divided into 2 parts. First, acceleration system and brake control system for longitudinal motion control. Second vision system of real time lane detection is for lateral motion control. This part deals lane detection method and image processing method. Finally, this paper focus on the integration of tole-operating vehicle and autonomous ...

• Agricultural and Biosystems Engineering
• /
• v.4 no.1
• /
• pp.22-27
• /
• 2003

An autonomous tractor requires not only automatic steering (automatic guidance) but also automated control of tractor functions and implement operations. Examples of tractor functions include engine throttle, transmission speed, and 3-point hitch position. Implement operations include tillage, planting, and cultivating. This article provides an overview of a map-based methodology used for the implementation of autonomous field operations of agricultural tractors. The procedure for developing autonomous field operation maps were presented, and several important issues in the implementation of map-based autonomous operations were discussed. These issues included combining field operation maps, position offset, and real-time sensing and update of field operation maps.