A Steering Strategy for Self-Driving Automobile Systems Based on Lane-Line Detection

Phan, Thanh-Danh; Nguyen, Tan-Thien-Nien; Duong, Minh-Thien; Nguyen, Chi-Tam; Le, Hoang-Anh; Le, My-Ha

doi:10.1109/gtsd54989.2022.9989030

Cited by 2 publications

(1 citation statement)

References 20 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The method is evaluated on the UDACITY simulation platform, yielding impressive accuracy results. In a different approach, literature [15] presents a prototype of a monocular vision autonomous vehicle based on Raspberry Pi deep neural network. This work focuses on developing a model using a deep neural network to directly map the input image to the predicted steering angle.…”

Section: Introductionmentioning

confidence: 99%

Mecanum Wheel AGV Trajectory Tracking Control Based on Efficient MPC Algorithm

Tang,

Lin,

Luo

2024

IEEE Access

View full text Add to dashboard Cite

In response to the challenge of insufficient trajectory tracking accuracy and low solution efficiency of Mecanum wheel AGV (Automated Guided Vehicle) under complex and constrained working conditions, this paper proposes an efficient Model Predictive Control (MPC) method to achieve superior tracking performance and robustness. Initially, a linear error model of the mobile platform is established based on pose error, serving as the predictive model for the MPC controller. A target function is designed to transform the trajectory tracking control problem into an optimal control problem. To handle inequality constraints, penalty terms are introduced into the objective function, and the resulting constrained problem is subsequently solved to approximate the optimal solution for the original inequalities. To alleviate the computational burden associated with real-time optimization problem-solving, an efficient MPC algorithm. has been developed. To ensure closed-loop stability under the MPC control method, stability constraints are imposed on the new optimization problem. Simulation results demonstrate that, in comparison to traditional Model Predictive Control methods, the proposed approach reduces the average solution calculation time by 5.1% and the maximum single calculation time by 13.7%, all while maintaining trajectory tracking accuracy. These results validate the algorithm's feasibility, effectively addressing the challenges associated with solving Model Predictive Control problems.

show abstract

Section: Introductionmentioning

confidence: 99%

Mecanum Wheel AGV Trajectory Tracking Control Based on Efficient MPC Algorithm

Tang,

Lin,

Luo

2024

IEEE Access

View full text Add to dashboard Cite

show abstract

A Comparative Analysis of Deep Reinforcement Learning-Enabled Freeway Decision-Making for Automated Vehicles

Liu,

Yang,

Xiao

et al. 2024

IEEE Access

View full text Add to dashboard Cite

In application, advanced autonomous driving technologies still face numerous challenges. Deep Reinforcement Learning (DRL) has emerged as a widespread and effective approach to address artificial intelligence challenges, due to its substantial potential for autonomous learning and self-improvement. In this study, four DRL algorithms-Deep Q-Learning (DQN), along with its enhanced algorithm, Double DQL, Dueling DQL, and Priority Replay DQL(PR-DQN), are employed to address decision-making challenges for autonomous vehicles on highways, with a comprehensive comparative analysis conducted. The decisionmaking model is constructed as a Markov Decision Process, guided by specially designed reward functions, enabling the target vehicle to learn safe and efficient decision-making strategies through multiple environmental explorations. Through the analysis and discussion of a series of experimental results, the feasibility of DRL-based decision strategies is demonstrated. Finally, through comparing the experimental outcomes of different algorithms, the connection between autonomous driving results and the inherent learning features of these DRL technologies is analyzed.

show abstract

A Steering Strategy for Self-Driving Automobile Systems Based on Lane-Line Detection

Cited by 2 publications

References 20 publications

Mecanum Wheel AGV Trajectory Tracking Control Based on Efficient MPC Algorithm

Mecanum Wheel AGV Trajectory Tracking Control Based on Efficient MPC Algorithm

A Comparative Analysis of Deep Reinforcement Learning-Enabled Freeway Decision-Making for Automated Vehicles

Contact Info

Product

Resources

About