A real-time high-speed autonomous driving based on a low-cost RTK-GPS

Park, Seong-Hyeon; Ryu, Seokhoon; Lim, Jihea; Lee, Young-Sup

doi:10.1007/s11554-021-01084-0

Cited by 8 publications

(5 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The accuracy of GPS is about from a few meters to twenty meters [35]. In order to increase the accuracy of GPS localization, various techniques such as real-time kinematic (RTK) [69], has been proposed. However, GPS accuracy is easily affected by factors such as obstacles, atmospheric conditions and signal blockage.…”

Section: B Gps-based Self-localization Methodsmentioning

confidence: 99%

A Survey of Vehicle Localization: Performance Analysis and Challenges

Shan,

Cabani,

Chafouk

2023

IEEE Access

View full text Add to dashboard Cite

Vehicle localization plays a crucial role in ensuring the safe operation of autonomous vehicles and the development of intelligent transportation systems (ITS). However, there is insufficient effort to compare the performance and challenges of different vehicle localization algorithms. This paper aims to address this gap by analyzing the comprehensive performance of existing advanced vehicle localization techniques and discussing their challenges. Firstly, we analyze the self-localization methods based on active and passive sensors. The results show that, the light detection and ranging (LiDAR) and vision-based techniques can reach high accuracy. However, they have high computational complexity. And only using the inertial measurement unit (IMU), global positioning system (GPS), radar, and ultrasonic sensors may not realize localization result with high accuracy. Then, we discuss V2X-based cooperative methods and analyze the multi-sensor based localization techniques and compare the comprehensive performance among all methods. Although the artificial intelligence (AI) techniques can effectively enhance the efficiency of vision-based localization algorithms, the high computational complexity still should be considered. In addition, since the IMU, GPS, radar, and ultrasonic sensors have good performance in terms of the availability, scalability, computational complexity, and cost-effectiveness, they can be used as auxiliary sensors to achieve good comprehensive performance through data fusion techniques. Finally, we propose the challenges of different techniques and look forward to future work.

show abstract

Section: B Gps-based Self-localization Methodsmentioning

confidence: 99%

A Survey of Vehicle Localization: Performance Analysis and Challenges

Shan,

Cabani,

Chafouk

2023

IEEE Access

View full text Add to dashboard Cite

show abstract

“…It adopts deep coupling technology combining Global Navigation Satellite System (GNSS) positioning and Inertial Measurement Unit (IMU) [27], where the IMU can compensate for the shortcomings of the Global Positioning System (GPS) in the area where the satellite signal is obscured, and the positioning accuracy is low. Meanwhile, the GPS signal can correct the IMU's accumulated error [28,29].…”

Section: Methodsmentioning

confidence: 99%

Investigating the Path Tracking Algorithm Based on BP Neural Network

Liu

Xue

Gao

et al. 2023

Sensors

View full text Add to dashboard Cite

In this paper, we propose an adaptive path tracking algorithm based on the BP (back propagation) neural network to increase the performance of vehicle path tracking in different paths. Specifically, based on the kinematic model of the vehicle, the front wheel steering angle of the vehicle was derived with the PP (Pure Pursuit) algorithm, and related parameters affecting path tracking accuracy were analyzed. In the next step, BP neural networks were introduced and vehicle speed, radius of path curvature, and lateral error were used as inputs to train models. The output of the model was used as the control coefficient of the PP algorithm to improve the accuracy of the calculation of the front wheel steering angle, which is referred to as the BP–PP algorithm in this paper. As a final step, simulation experiments and real vehicle experiments are performed to verify the algorithm’s performance. Simulation experiments show that compared with the traditional path tracking algorithm, the average tracking error of BP–PP algorithm is reduced by 0.025 m when traveling at a speed of 3 m/s on a straight path, and the average tracking error is reduced by 0.27 m, 0.42 m, and 0.67 m, respectively, at a speed of 1.5 m/s with a curvature radius of 6.8 m, 5.5 m, and 4.5 m, respectively. In the real vehicle experiment, an electric patrol vehicle with an autonomous tracking function was used as the experimental platform. The average tracking error was reduced by 0.1 m and 0.086 m on a rectangular road and a large curvature road, respectively. Experimental results show that the proposed algorithm performs well in both simulation and actual scenarios, improves the accuracy of path tracking, and enhances the robustness of the system. Moreover, facing paths with changes in road curvature, the BP–PP algorithm achieved significant improvement and demonstrated great robustness. In conclusion, the proposed BP–PP algorithm reduced the interference of nonlinear factors on the system and did not require complex calculations. Furthermore, the proposed algorithm has been applied to the autonomous driving patrol vehicle in the park and achieved good results.

show abstract

“…Finally, under this scheme, the positioning accuracy is 1-2 m. In [7], the authors put forward the solution of auxiliary GPS (AGPs), which mainly improves the speed of information acquisition and enhances the signal strength, but its positioning accuracy is slightly lower than DGPS. In [8], the authors put forward a lowcost RTK-GPS positioning solution, which can still have good robustness and positioning accuracy under high-speed road conditions. Although these methods have improved the positioning accuracy compared with GPS solutions, their reliability is still a very serious problem.…”

Section: Related Workmentioning

confidence: 99%

LiDAR-IMU-UWB-Based Collaborative Localization

Zhang

Qin

2022

WEVJ

View full text Add to dashboard Cite

This article introduced a positioning system composed of different sensors, such as LiDAR, IMU, and ultra-wideband (UWB), for the positioning method in autonomous driving technology under closed coal mine tunnels. First, we processed the LiDAR data, extracted its feature points and merged the extracted feature point clouds to generate a skewed combined feature point cloud. Then, we used the skew combined feature point clouds for feature matching, performed pre-integration processing on the IMU sensor data, and completed the LiDAR-IMU odometer with the LiDAR. Finally, we added UWB data to IMU pose node as a one-dimensional over-edge constraint. By updating the sliding window, the positioning accuracy was further improved. Moreover, we have conducted experiments to verify the proposed positioning system in a simulated roadway. The experimental results showed that the method proposed in this paper is superior to the single LiDAR method and the single UWB method in terms of positioning accuracy.

show abstract

A real-time high-speed autonomous driving based on a low-cost RTK-GPS

Cited by 8 publications

References 14 publications

A Survey of Vehicle Localization: Performance Analysis and Challenges

A Survey of Vehicle Localization: Performance Analysis and Challenges

Investigating the Path Tracking Algorithm Based on BP Neural Network

LiDAR-IMU-UWB-Based Collaborative Localization

Contact Info

Product

Resources

About