• The Journal of Korea Robotics Society
• /
• v.8 no.4
• /
• pp.292-297
• /
• 2013

This paper presents a new method of kinematic modeling for autonomous bicycle by using the differential motion transformation. Kinematic model is indispensable to trajectory planning and control for an autonomous mobile robot. The conventional methods of kinematic modeling for an autonomous bicycle depend on intuition by geometry. On the contrary, the proposed method in this paper is based on the systematic differential motion transformation, thus applicable to various types of autonomous bicycles. The differential motion transformation gives Jacobian between two coordinate frames and the velocity kinematics as a result.

• Proceedings of the Korean Institute of Intelligent Systems Conference
• /
• 2004.04a
• /
• pp.446-449
• /
• 2004

In the former researches〔2〕〔5〕 for the unmanned bicycle system, we do only focus on stabilizing it by using the lateral motion of mass which plays important role in driving a bicycle system. In this papers, we suggest an algorithm for deriving steering angle and speed for a given desired tracking path. As you may see in this paper, load mass balance system plays important role in stabilization and it is also discussed. We propose a control algorithm for the autonomous self stabilization of unmanned bicycle by using nonlinear compensation-like control based on the Lyapunov stability theory We then propose a tracking control strategy by moving the center of load mass left and right respectively. From the computer simulation results, we can show the effectiveness of the proposed control strategy.

• Convergence Security Journal
• /
• v.18 no.3
• /
• pp.3-9
• /
• 2018

The Deep Deterministic Policy Gradient (DDPG) algorithm is an algorithm that learns by using artificial neural network s and reinforcement learning. Among the studies related to reinforcement learning, which has been recently studied, the D DPG algorithm has an advantage of preventing the cases where the wrong actions are accumulated and affecting the learn ing because it is learned by the off-policy. In this study, we experimented to control the bicycle autonomously by applyin g the DDPG algorithm. Simulation was carried out by setting various environments and it was shown that the method us ed in the experiment works stably on the simulation.

• Proceedings of the Korean Society of Precision Engineering Conference
• /
• 2013.05a
• /
• pp.335-336
• /
• 2013

• 제어로봇시스템학회:학술대회논문집
• /
• 2001.10a
• /
• pp.173.3-173
• /
• 2001

In this paper, attitude control of autonomous system using bike based on variable structure control is discussed. Variable structure control is more than a promising technique in the field of nonlinear control. It permits the realization of very robust and simple regulators, with appealing sliding mode characteristics especially if the considered dynamics requires a very short sampling time. We derive dynamic equation of it and demonstrate that the designed controller stabilizes attitude simultaneously regardless of wheel position by computer simulation.

• The Journal of The Korea Institute of Intelligent Transport Systems
• /
• v.22 no.5
• /
• pp.200-215
• /
• 2023

With the rapid advance of autonomous driving technology, the related vehicle market is experiencing explosive growth, and it is anticipated that the era of fully autonomous vehicles will arrive in the near future. However, along with the development of autonomous driving technology, questions regarding its safety and reliability continue to be raised. Concerns among technology adopters are increasing due to media reports of accidents involving autonomous vehicles. To promote the improvement of the safety of autonomous vehicles, it is essential to analyze previous accident cases and identify their causes. Therefore, in this study, we aimed to analyze the factors influencing the severity of autonomous vehicle accidents using previous accident cases and related data. The data used for this research primarily comprised autonomous vehicle accident reports collected and distributed by the California Department of Motor Vehicles (CA DMV). Spatial information on accident locations and additional traffic data were also collected and utilized. Given that the primary data used in this study were accident reports, a Poisson regression analysis was conducted to model the expected number of accidents. The research results indicated that the severity of autonomous vehicle accidents increases in areas with low lighting, the presence of bicycle or bus-exclusive lanes, and a history of pedestrian and bicycle accidents. These findings are expected to serve as foundational data for the development of algorithms to enhance the safety of autonomous vehicles and promote the installation of related transportation infrastructure.

• The Journal of Korea Robotics Society
• /
• v.18 no.1
• /
• pp.93-98
• /
• 2023

In this paper, the development of an autonomous electric vehicle for logistics with a robotic arm is introduced. The manual driving electric vehicle was converted into an electric vehicle platform capable of autonomous driving. For autonomous driving, an encoder is installed on the driving wheels, and an electronic power steering system is applied for automatic steering. The electric vehicle is equipped with a lidar sensor, a depth camera, and an ultrasonic sensor to recognize the surrounding environment, create a map, and recognize the vehicle location. The odometry was calculated using the bicycle motion model, and the map was created using the SLAM algorithm. To estimate the location of the platform based on the generated map, AMCL algorithm using Lidar was applied. A user interface was developed to create and modify a waypoint in order to move a predetermined place according to the logistics process. An A-star-based global path was generated to move to the destination, and a DWA-based local path was generated to trace the global path. The autonomous electric vehicle developed in this paper was tested and its utility was verified in a warehouse.

• Journal of Institute of Control, Robotics and Systems
• /
• v.12 no.9
• /
• pp.850-855
• /
• 2006

This is concerned with the development and design of automatic maneuvering system using Differential Global Positioning System(DGPS). To achievement of autonomous maneuvering controller for giant ship, first, we investigated automatic maneuvering controller using DGPS in motor car. The sensors are configured with DGPS and digital compass. We calculated velocity and steering angle of motor car based on sensor signal. To design the controller, we derived the bicycle model and developed critically damped controller. The critically damped controller can be tracing previously appointed position in the fastest time. We are used a laptop computer to realize and the control algorithm is programmed by visual basic software. The obtained experimental results from developed system show unmanned motor car is good tracing planed positions. Hence, the system is looking forward to use the autonomous maneuvering control fur giant ship.

• Journal of Auto-vehicle Safety Association
• /
• v.13 no.4
• /
• pp.7-13
• /
• 2021

This paper presents an vulnerable road user (VRU) classification and tracking algorithm using vision and LiDAR sensor fusion method for urban autonomous driving. The classification and tracking for vulnerable road users such as pedestrian, bicycle, and motorcycle are essential for autonomous driving in complex urban environments. In this paper, a real-time object image detection algorithm called Yolo and object tracking algorithm from LiDAR point cloud are fused in the high level. The proposed algorithm consists of four parts. First, the object bounding boxes on the pixel coordinate, which is obtained from YOLO, are transformed into the local coordinate of subject vehicle using the homography matrix. Second, a LiDAR point cloud is clustered based on Euclidean distance and the clusters are associated using GNN. In addition, the states of clusters including position, heading angle, velocity and acceleration information are estimated using geometric model free approach (GMFA) in real-time. Finally, the each LiDAR track is matched with a vision track using angle information of transformed vision track and assigned a classification id. The proposed fusion algorithm is evaluated via real vehicle test in the urban environment.

• Journal of Positioning, Navigation, and Timing
• /
• v.11 no.3
• /
• pp.209-215
• /
• 2022

As intelligent autonomous driving vehicle development has become a big topic around the world, accurate reference dynamics estimation has been more important than before. Current systems generally use speed and heading information sensed from a distant point as a vehicle reference dynamic, however, the dynamics between different points are not same especially during rotating motions. In order to estimate properly estimate the reference dynamics from the information such as velocity and heading sensed at a point distant from the reference point such as center of gravity, this study proposes estimating reference dynamics from any location in the vehicle by combining the Bicycle and Ackermann models. A test system was constructed by implementing multiple GNSS/INS equipment on an Robot Operating System (ROS) and an actual car. Angle and speed errors of 10° and 0.2 m/s have been reduced to 0.2° and 0.06 m/s after applying the suggested method.