scholarly journals Reinforcement Learning-Based End-to-End Parking for Automatic Parking System

Sensors ◽  
2019 ◽  
Vol 19 (18) ◽  
pp. 3996 ◽  
Author(s):  
Peizhi Zhang ◽  
Lu Xiong ◽  
Zhuoping Yu ◽  
Peiyuan Fang ◽  
Senwei Yan ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Tracking Error ◽  
Path Tracking ◽  
Steering Wheel ◽  
Local Optimum ◽  
Training Methods ◽  
Parking System ◽  
Network Output ◽  
Automatic Parking ◽  
End To End

According to the existing mainstream automatic parking system (APS), a parking path is first planned based on the parking slot detected by the sensors. Subsequently, the path tracking module guides the vehicle to track the planned parking path. However, since the vehicle is non-linear dynamic, path tracking error inevitably occurs, leading to inclination and deviation of the parking. Accordingly, in this paper, a reinforcement learning-based end-to-end parking algorithm is proposed to achieve automatic parking. The vehicle can continuously learn and accumulate experience from numerous parking attempts and then learn the command of the optimal steering wheel angle at different parking slots. Based on this end-to-end parking, errors caused by path tracking can be avoided. Moreover, to ensure that the parking slot can be obtained continuously in the process of learning, a parking slot tracking algorithm is proposed based on the combination of vision and vehicle chassis information. Furthermore, given that the learning network output is hard to converge, and it is easy to fall into local optimum during the parking process, several reinforcement learning training methods in terms of parking conditions are developed. Lastly, by the real vehicle test, it is proved that using the proposed method can achieve a better parking attitude than using the path planning and path tracking-based method.

scholarly journals Automatic Parking Path Planning and Tracking Control Research for Intelligent Vehicles

2020 ◽  
Vol 10 (24) ◽  
pp. 9100
Author(s):  
Chenxu Li ◽  
Haobin Jiang ◽  
Shidian Ma ◽  
Shaokang Jiang ◽  
Yue Li
Keyword(s):  
Path Planning ◽  
Tracking Control ◽  
Control Method ◽  
Sliding Mode ◽  
Vehicle Control ◽  
Path Tracking ◽  
Intelligent Vehicles ◽  
Parking System ◽  
Automatic Parking ◽  
Real Vehicle

As a key technology for intelligent vehicles, automatic parking is becoming increasingly popular in the area of research. Automatic parking technology is available for safe and quick parking operations without a driver, and improving the driving comfort while greatly reducing the probability of parking accidents. An automatic parking path planning and tracking control method is proposed in this paper to resolve the following issues presented in the existing automatic parking systems, that is, low degree of automation in vehicle control; lack of conformity between segmented path planning and real vehicle motion models; and low success rates of parking due to poor path tracking. To this end, this paper innovatively proposes preview correction which can be applied to parking path planning, and detects the curvature outliers in the parking path through the preview algorithm. In addition, it is also available for correction in advance to optimize the reasonable parking path. Meanwhile, the dual sliding mode variable structure control algorithm is used to formulate path tracking control strategies to improve the path tracking control effect and the vehicle control automation. Based on the above algorithm, an automatic parking system was developed and the real vehicle test was completed, thus exploring a highly intelligent automatic parking technology roadmap. This paper provides two key aspects of system solutions for an automatic parking system, i.e., parking path planning and path tracking control.

Control of Automobile's Automatic Parking

2011 ◽  
Vol 339 ◽  
pp. 28-31
Author(s):  
Hong Mei
Keyword(s):  
Fuzzy Logic ◽  
Fuzzy Control ◽  
Fuzzy Controller ◽  
Steering Wheel ◽  
Experienced Driver ◽  
Parking System ◽  
Automatic Parking ◽  
Conventional Methods ◽  
The Ideal

An automatic parking controller is proposed. Fuzzy control is taken to simulate the action of experienced driver as an alternative to conventional methods. The angle between the midline of the car and ideal path and the distance between the midpoint of the car and the ideal path are taken as the inputs of the fuzzy controller. The angle of the steering wheel is taken as the output of the fuzzy controller. A set of fuzzy logic rules are build for reasoning. With sensors installed in the car to replace people’s eyes and computer to replace people’s brain, the automatic parking system is more precise and quicker than human’s parking. At last, simulation is made and proved the validity of the proposed method.

scholarly journals Self-Optimizing Path Tracking Controller for Intelligent Vehicles Based on Reinforcement Learning

Symmetry ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 31
Author(s):  
Jichang Ma ◽  
Hui Xie ◽  
Kang Song ◽  
Hao Liu
Keyword(s):  
Reinforcement Learning ◽  
Pid Control ◽  
Tracking Control ◽  
Tracking Error ◽  
Path Tracking ◽  
Pid Controllers ◽  
Model Parameters ◽  
Control Parameters ◽  
Tracking Controller ◽  
Complex Trajectories

The path tracking control system is a crucial component for autonomous vehicles; it is challenging to realize accurate tracking control when approaching a wide range of uncertain situations and dynamic environments, particularly when such control must perform as well as, or better than, human drivers. While many methods provide state-of-the-art tracking performance, they tend to emphasize constant PID control parameters, calibrated by human experience, to improve tracking accuracy. A detailed analysis shows that PID controllers inefficiently reduce the lateral error under various conditions, such as complex trajectories and variable speed. In addition, intelligent driving vehicles are highly non-linear objects, and high-fidelity models are unavailable in most autonomous systems. As for the model-based controller (MPC or LQR), the complex modeling process may increase the computational burden. With that in mind, a self-optimizing, path tracking controller structure, based on reinforcement learning, is proposed. For the lateral control of the vehicle, a steering method based on the fusion of the reinforcement learning and traditional PID controllers is designed to adapt to various tracking scenarios. According to the pre-defined path geometry and the real-time status of the vehicle, the interactive learning mechanism, based on an RL framework (actor–critic—a symmetric network structure), can realize the online optimization of PID control parameters in order to better deal with the tracking error under complex trajectories and dynamic changes of vehicle model parameters. The adaptive performance of velocity changes was also considered in the tracking process. The proposed controlling approach was tested in different path tracking scenarios, both the driving simulator platforms and on-site vehicle experiments have verified the effects of our proposed self-optimizing controller. The results show that the approach can adaptively change the weights of PID to maintain a tracking error (simulation: within ±0.071 m; realistic vehicle: within ±0.272 m) and steering wheel vibration standard deviations (simulation: within ±0.04°; realistic vehicle: within ±80.69°); additionally, it can adapt to high-speed simulation scenarios (the maximum speed is above 100 km/h and the average speed through curves is 63–76 km/h).

scholarly journals Research on Path Planning and Tracking Control of Automatic Parking System

2022 ◽  
Vol 13 (1) ◽  
pp. 14
Author(s):  
Bingzhan Zhang ◽  
Zhiyuan Li ◽  
Yaoyao Ni ◽  
Yujie Li
Keyword(s):  
Path Planning ◽  
Predictive Control ◽  
Tracking Control ◽  
Path Tracking ◽  
Preview Control ◽  
Laboratory Environment ◽  
Incremental Model ◽  
Quintic Polynomial ◽  
Parking System ◽  
Automatic Parking

In this paper, we focus on the parking path planning and path tracking control under parallel parking conditions with automatic parking system as the research object. In order to solve the problem of discontinuity of curvature in the path planning of traditional arc-straight combined curve, a quintic polynomial is used to smooth the path. we design a path tracking controller based on the incremental model predictive control (MPC). The preview control based on pure tracking algorithm is used as the comparison algorithm for path tracking. The feasibility of the controller is verified by building a Simulink/CarSim co-simulation platform. In addition, the practicality of the parking controller is further verified by using the ROS intelligent car in the laboratory environment.

scholarly journals Path Tracking Control of Automatic Parking Cloud Model considering the Influence of Time Delay

2017 ◽  
Vol 2017 ◽  
pp. 1-14 ◽  
Author(s):  
Yiding Hua ◽  
Haobin Jiang ◽  
Yingfeng Cai ◽  
Xupei Zhang ◽  
Shidian Ma ◽  
...  
Keyword(s):  
Time Delay ◽  
Tracking Control ◽  
Control Method ◽  
Simulation Analysis ◽  
Cloud Model ◽  
Kinematic Model ◽  
Path Tracking ◽  
Steering Control ◽  
Parking System ◽  
Automatic Parking

This paper establishes the kinematic model of the automatic parking system and analyzes the kinematic constraints of the vehicle. Furthermore, it solves the problem where the traditional automatic parking system model fails to take into account the time delay. Firstly, based on simulating calculation, the influence of time delay on the dynamic trajectory of a vehicle in the automatic parking system is analyzed under the transverse distance Dlateral between different target spaces. Secondly, on the basis of cloud model, this paper utilizes the tracking control of an intelligent path closer to human intelligent behavior to further study the Cloud Generator-based parking path tracking control method and construct a vehicle path tracking control model. Moreover, tracking and steering control effects of the model are verified through simulation analysis. Finally, the effectiveness and timeliness of automatic parking controller in the aspect of path tracking are tested through a real vehicle experiment.

scholarly journals Reinforcement Learning-Based Motion Planning for Automatic Parking System

IEEE Access ◽  
2020 ◽  
Vol 8 ◽  
pp. 154485-154501 ◽  
Author(s):  
Jiren Zhang ◽  
Hui Chen ◽  
Shaoyu Song ◽  
Fengwei Hu
Keyword(s):  
Reinforcement Learning ◽  
Motion Planning ◽  
Parking System ◽  
Automatic Parking

scholarly journals Verifiably safe exploration for end-to-end reinforcement learning

2021 ◽  
Author(s):  
Nathan Hunt ◽  
Nathan Fulton ◽  
Sara Magliacane ◽  
Trong Nghia Hoang ◽  
Subhro Das ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
End To End

scholarly journals Crowd Evacuation Guidance Based on Combined Action Reinforcement Learning

Algorithms ◽  
2021 ◽  
Vol 14 (1) ◽  
pp. 26
Author(s):  
Yiran Xue ◽  
Rui Wu ◽  
Jiafeng Liu ◽  
Xianglong Tang
Keyword(s):  
Reinforcement Learning ◽  
Guidance System ◽  
Force Model ◽  
Interactive Simulation ◽  
Social Force ◽  
Novel Approach ◽  
Learning Agent ◽  
Network Output ◽  
Combined Action ◽  
Crowd Evacuation

Existing crowd evacuation guidance systems require the manual design of models and input parameters, incurring a significant workload and a potential for errors. This paper proposed an end-to-end intelligent evacuation guidance method based on deep reinforcement learning, and designed an interactive simulation environment based on the social force model. The agent could automatically learn a scene model and path planning strategy with only scene images as input, and directly output dynamic signage information. Aiming to solve the “dimension disaster” phenomenon of the deep Q network (DQN) algorithm in crowd evacuation, this paper proposed a combined action-space DQN (CA-DQN) algorithm that grouped Q network output layer nodes according to action dimensions, which significantly reduced the network complexity and improved system practicality in complex scenes. In this paper, the evacuation guidance system is defined as a reinforcement learning agent and implemented by the CA-DQN method, which provides a novel approach for the evacuation guidance problem. The experiments demonstrate that the proposed method is superior to the static guidance method, and on par with the manually designed model method.

Sign in / Sign up

Export Citation Format

Share Document