Your Selections

Wuhan University of Technology, China
Show Only

Collections

File Formats

Content Types

Dates

Sectors

Topics

Authors

Publishers

Affiliations

Events

   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

An Optimal Controller for Trajectory Tracking of Automated Guided Vehicle

Wuhan University of Technology, China-Zhang Jian, Yang Bo, Pei Xiaofei
  • Technical Paper
  • 2020-01-5024
Published 2020-02-24 by SAE International in United States
A trajectory tracking strategy for an Automated Guided Vehicle (AGV) is presented in this paper, containing a hybrid algorithm of a preview feedforward control and a feedback control via linear quadratic regulator (LQR). The purpose of trajectory tracking is to decrease the position and orientation errors between the trajectory and AGV. The vehicle - road dynamics model applied to establish the relationship between vehicle and trajectory and accurately describes plant motion. The preview feedforward control is adopted to solve time delay of steering mechanism in trajectory tracking. The feedback control via LQR is applied to decrease the errors caused by environmental disturbances. For real-time embedded system, the optimal gain is calculated offline and is used by lookup table online, which could reduce the computation time. The results of tests on a practical AGV system demonstrate the effectiveness and accuracy of the strategy presented in this paper.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.
new

An Integrated Navigation System Using GPS and Low-Cost Vehicle Dynamic Sensors

Wuhan University of Technology, China-Li Hao, Yang Bo, Pei Xiaofei
  • Technical Paper
  • 2020-01-5028
Published 2020-02-24 by SAE International in United States
The aim of this paper is to present a novel integrated navigation system, based on the fusion between the Global Positioning System (GPS) and low-cost vehicle onboard dynamic sensors for autonomous vehicle positioning problems. In this system, the information of vehicle’s angular rotation is applied to dead reckoning (DR) module based on the Unscented Kalman Filter (UKF) to provide the vehicle position information during GPS outage. In the DR module based on UKF, vehicle onboard dynamic sensors, include wheels speed sensors, accelerometer, and steering angle sensor, are utilized to estimate the vehicle yaw rate, while the traditional method using IMU sensor is relatively expensive. Also, the vehicle dynamic model is employed in the estimation of yaw rate, which can provide better accuracy than the traditional kinematic model. To validate the effectiveness of the integrated navigation system, tests are carried out on a small-scale vehicle platform. The test results show that the yaw rate could be well estimated and the integrated navigation system using low-cost sensors could also keep the error distance in a small range.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

A Personalized Lane-Changing Model for Advanced Driver Assistance System Based on Deep Learning and Spatial-Temporal Modeling

SAE International Journal of Transportation Safety

Wuhan University of Technology, China-Honghui Zhu
Jianghan University, China-Jun Gao, Jiangang Yi
  • Journal Article
  • 09-07-02-0009
Published 2019-11-14 by SAE International in United States
Lane changes are stressful maneuvers for drivers, particularly during high-speed traffic flows. However, modeling driver’s lane-changing decision and implementation process is challenging due to the complexity and uncertainty of driving behaviors. To address this issue, this article presents a personalized Lane-Changing Model (LCM) for Advanced Driver Assistance System (ADAS) based on deep learning method. The LCM contains three major computational components. Firstly, with abundant inputs of Root Residual Network (Root-ResNet), LCM is able to exploit more local information from the front view video data. Secondly, the LCM has an ability of learning the global spatial-temporal information via Temporal Modeling Blocks (TMBs). Finally, a two-layer Long Short-Term Memory (LSTM) network is used to learn video contextual features combined with lane boundary based distance features in lane change events. The experimental results on a -world driving dataset show that the LCM is capable of learning the latent features of lane-changing behaviors and achieving significantly better performance than other prevalent models.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Speed Planning and Prompting System for Commercial Vehicle Based on Real-Time Calculation of Resistance

SAE International Journal of Commercial Vehicles

Wuhan University of Technology, China-Zhaocong Sun, Zhimin Li, Jinyi Xia, Gangfeng Tan
  • Journal Article
  • 02-12-03-0013
Published 2019-06-25 by SAE International in United States
When commercial vehicles drive in a mountainous area, the complex road condition and long slopes cause frequent acceleration and braking, which will use 25% more fuel. And the brake temperature rises rapidly due to continuous braking on the long-distance downslopes, which will make the brake drum fail with the brake temperature exceeding 308°C [1]. Meanwhile, the kinetic energy is wasted during the driving progress on the slopes when the vehicle rolls up and down. Our laboratory built a model that could calculate the distance from the top of the slope, where the driver could release the accelerator pedal. Thus, on the slope, the vehicle uses less fuel when it rolls up and less brakes when down. What we do in this article is use this model in a real vehicle and measure how well it works. Thus, to improve the safety and economy of commercial vehicles on mountainous areas, the Vehicle Speed Planning and Prompting System based on real-time calculation of resistance is established. The system consists of four parts: Hardware on Vehicle, Microcontroller Unit…
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Detection of Lane-Changing Behavior Using Collaborative Representation Classifier-Based Sensor Fusion

SAE International Journal of Transportation Safety

Wuhan University of Technology, China-Honghui Zhu
University of Michigan-Dearborn, USA-Jun Gao, Yi Lu Murphey
  • Journal Article
  • 09-06-02-0010
Published 2018-10-29 by SAE International in United States
Sideswipe accidents occur primarily when drivers attempt an improper lane change, drift out of lane, or the vehicle loses lateral traction. In this article, a fusion approach is introduced that utilizes data from two differing modality sensors (a front-view camera and an onboard diagnostics (OBD) sensor) for the purpose of detecting driver’s behavior of lane changing. For lane change detection, both feature-level fusion and decision-level fusion are examined by using a collaborative representation classifier (CRC). Computationally efficient detection features are extracted from distances to the detected lane boundaries and vehicle dynamics signals. In the feature-level fusion, features generated from two differing modality sensors are merged before classification, while in the decision-level fusion, the Dempster-Shafer (D-S) theory is used to combine the classification outcomes from two classifiers, each corresponding to one sensor. The results indicated that the feature-level fusion outperformed the decision-level fusion, and the introduced fusion approach using a CRC performs significantly better in terms of detection accuracy, in comparison to other state-of-the-art classifiers.
This content contains downloadable datasets
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

On the Determination of Joint Motion Coupling for the Human Shoulder Complex

Wuhan University of Technology, China-Xuemei Feng
The University of Iowa-Jingzhou Yang, Karim Abdel-Malek
Published 2008-06-17 by SAE International in United States
This paper presents a novel approach to determining the joint motion coupling relationship for the human shoulder complex. The human shoulder complex is the most sophisticated part in terms of degrees of freedom and motion. In the literature, different human shoulder biomechanical models have been developed for various purposes. Also, researchers have realized that there are constant movement relationships among the shoulder bones: the clavicle, scapula, and humerus. This is due to muscles and tendons that are involved in skeletal motions. These relationships, which are also called shoulder rhythm, entail joint motion coupling and joint limit coupling. However, the scope of this work is to determine the joint motion coupling relationship. This relationship is available in the literature, but it is an Euler-angle-based relationship. In the virtual human modeling environment, we cannot directly use this Euler-angle-based relationship. A novel approach is proposed to transfer Euler-angle-based coupling equations into a relationship based on the Denavit-Hartenberg (DH) method. A realistic shoulder complex model is built within Virtools. Euler angles are obtained for static positions with intervals of…
Annotation ability available
   This content is not included in your SAE MOBILUS subscription, or you are not logged in.

Research on Road Feeling Control Strategy of Steer-by-Wire

Wuhan University of Technology, China-Yang Shengbing, Den Chunan
Tsinghua University, China-Ji Xuewu, Chen Kuiyuan
Published 2007-08-05 by SAE International in United States
A steer-by-wire system has many benefits over conventional steering system for no mechanical link existing between the steering wheel and the road wheels. Road feeling has been being one of the most important vehicle characteristics reflecting vehicle directional control and stability. Besides the steering angle, road wheels reactive torque and vehicle dynamical behavior are considered in this paper. A control strategy with road wheels force feedback and steering wheel angle feedback was developed. The vehicle dynamic states are taken into account for road feeling simulation. Simulation shows that the control strategy achieves desired road feeling, and the second control strategy can improve the road feeling dynamically.
Annotation ability available