Key Takeaways & Executive Findings
- •• Proposes FS-DRL, a dual reinforced learning algorithm combining CNN and DQN for fine-grained scheduling of autonomous vehicles at non-signalized intersections. • Achieves 96.5% accuracy and improves traffic efficiency by 61.54%–85.37% compared to Dijkstra, RNN, and ant colony-based methods. • Introduces an adaptive learning rate that ensures convergence with minimal training loops, enhancing practical applicability. • Addresses the challenge of dynamic, non-signalized intersection environments, offering a scalable distributed scheduling solution.
Abstract
Complex road conditions without signalized intersections when the traffic flow is nearly saturated result in high traffic congestion and accidents, reducing the traffic efficiency of intelligent vehicles. The complex road traffic environment of smart vehicles and other vehicles frequently experiences conflicting start and stop motion. The fine-grained scheduling of autonomous vehicles (AVs) at non-signalized intersections, which is a promising technique for exploring optimal driving paths for both assisted driving nowadays and driverless cars in the near future, has attracted significant attention owing to its high potential for improving road safety and traffic efficiency. Fine-grained scheduling primarily focuses on signalized intersection scenarios, as applying it directly to non-signalized intersections is challenging because each AV can move freely without traffic signal control. This may cause frequent driving collisions and low road traffic efficiency. Therefore, this study proposes a novel algorithm to address this issue. Our work focuses on the fine-grained scheduling of automated vehicles at non-signal intersections via dual reinforced training (FS-DRL). For FS-DRL, we first use a grid to describe the non-signalized intersection and propose a convolutional neural network (CNN)-based fast decision model that can rapidly yield a coarse-grained scheduling decision for each AV in a distributed manner. We then load these coarse-grained scheduling decisions onto a deep Q-learning network (DQN) for further evaluation. We use an adaptive learning rate to maximize the reward function and employ parameter ε to tradeoff the fast speed of coarse-grained scheduling in the CNN and optimal fine-grained scheduling in the DQN. In addition, we prove that using this adaptive learning rate leads to a converged loss rate with an extremely small number of training loops. The simulation results show that compared with Dijkstra, RNN, and ant colony-based scheduling, FS-DRL yields a high accuracy of 96.5% on the sample, with improved performance of approximately 61.54%–85.37% in terms of the average conflict and traffic efficiency.
1. Introduction
The fine-grained scheduling of autonomous vehicles (AVs) at non-signal intersections has recently attracted significant attention in the industrial and academic fields of unmanned driving [1, 2]. However, most existing algorithms can only be applied to static environments, such as parking lots and signalized intersections. They cannot guarantee the stable and effective scheduling of AVs in dynamic environments, which currently hinders assisted driving and could be a barrier to driverless cars in the near future.
Existing algorithms for scheduling AVs at non-signalized intersections can be divided into the centralized and distributed methods [3]. For the centralized method, a roadside unit (RSU) is presumed to exist along the road [4], which calculates the scheduling route for each AV centrally and then pushes the calculated routes to AVs for scheduling. Notably, all tasks in the centralized method, such as data computation and uploading/downloading communications, are concentrated on the RSU, which may result in an unbalanced load distribution between AVs and RSUs [5]. By contrast, the distributed scheduling method adopts a decentralized system architecture in which each AV uses only its local information for scheduling. This method enables each AV to determine its own path, decreasing the processing burden of the RSU, and is an appropriate signal or non-signal intersection [6].
Loading authentic research manuscript (Pages 1–5)...
Ning Sun, Weihao Wu, Guangbing Xiao, Guodong Yin (2025). FS-DRL: Fine-Grained Scheduling of Autonomous Vehicles at Non-Signalized Intersections via Dual Reinforced Learning. Chinese Journal of Mechanical Engineering. https://doi.org/10.1186/s10033-025-01203-z
Research & Educational Purpose Only:The translations, structured abstracts, analytical annotations, and data reports provided by SinoTechIntel are intended exclusively for academic research, internal corporate R&D, and educational benchmarking. They do not constitute formal engineering, chemical safety, legal, or professional advice.
Copyright & Intellectual Property Notice: Original copyright of the underlying source articles and experimental data remains with the respective authors, institutions, and original publishing journals. SinoTechIntel claims intellectual property only over its proprietary translations, analytical syntheses, and AEO structured enhancements in accordance with international fair use and academic citation principles.
Frequently Asked Questions
What is FS-DRL?
FS-DRL (Fine-Grained Scheduling via Dual Reinforced Learning) is a novel algorithm for scheduling autonomous vehicles at non-signalized intersections. It combines a CNN-based fast decision model for coarse-grained scheduling and a DQN for fine-grained optimization, using an adaptive learning rate to balance speed and optimality.
How does FS-DRL improve traffic efficiency?
FS-DRL improves traffic efficiency by reducing conflicts and optimizing vehicle trajectories at non-signalized intersections. Simulation results show an improvement of 61.54%–85.37% in average conflict and traffic efficiency compared to existing methods like Dijkstra, RNN, and ant colony-based scheduling.
What are the key components of FS-DRL?
The key components include a grid-based representation of the intersection, a CNN for rapid coarse-grained decisions, a DQN for fine-grained evaluation, and an adaptive learning rate to ensure convergence with minimal training loops.
Is FS-DRL suitable for real-time applications?
Yes, FS-DRL is designed for real-time scheduling due to its distributed architecture and fast decision-making. The CNN provides quick coarse-grained decisions, while the DQN refines them, and the adaptive learning rate ensures efficient training, making it practical for dynamic environments.
What are the advantages of FS-DRL over centralized methods?
FS-DRL uses a distributed approach, reducing the processing burden on roadside units and avoiding unbalanced load distribution. Each AV makes decisions based on local information, enhancing scalability and robustness in complex traffic scenarios.
Related Technical Papers & Translations
Direct Repair of the Crystal Structure and Coating Surface of Spent LiFePO4 Materials Enables Superfast Li-Ion Migration
The rapid accumulation of spent LiFePO4 (LFP) cathodes from retired lithium-ion batteries necessitates the development of effective and environmental-friendly recycling strategies. In this context, direct regeneration has emerged as a promising approach for reclaiming LFP cathode materials, offering a streamlined pathway to restore their electrochemical functionality. We report an integrated regeneration protocol that simultaneously repairs the degraded crystal structure and reconstructs the damaged carbon coating in spent LFP. The regenerated cathode material had superfast lithium-ion diffusion kinetics and a stable cathode–electrolyte interface, giving a remarkable rate capability with specific capacities of 122 mAh g−1 at 5C and 106 mAh g−1 at 10C (1C = 170 mA g−1). It also maintained capacities of 110.7 mAh g−1 (5C) and 84.1 mAh g−1 (10C) after 400 cycles. It could be used in harsh environments and could be stably cycled at subzero temperatures (−10 and −20 °C) and in solid-state electrolyte batteries. Life cycle assessment combined with economic evaluation using the EverBatt model reveals that this direct regeneration approach has high economic and environmental benefits.
Oxide Semiconductor for Advanced Memory Architectures: Atomic Layer Deposition, Key Requirement and Challenges
Oxide semiconductors (OSs), introduced by the Hosono group in the early 2000s, have evolved from display backplane materials to promising candidates for advanced memory and logic devices. The exceptionally low leakage current of OSs and compatibility with three-dimensional (3D) architectures have recently sparked renewed interest in their use in semiconductor applications. This review begins by exploring the unique material properties of OSs, which fundamentally originate from their distinct electronic band structure. Subsequently, we focus on atomic layer deposition (ALD), a core technique for growing excellent OS films, covering both basic and advanced processes compatible with 3D scaling. The basic surface reaction mechanisms—adsorption and reaction—and their roles in film growth are introduced. Furthermore, material design strategies, such as cation selection, crystallinity control, anion doping, and heterostructure engineering, are discussed. We also highlight challenges in memory applications, including contact resistance, hydrogen instability, and lack of p-type materials, and discuss the feasibility of ALD-grown OSs as potential solutions. Lastly, we provide an outlook on the role of ALD-grown OSs in memory technologies. This review bridges material fundamentals and device-level requirements, offering a comprehensive perspective on the potential of ALD-driven OSs for next-generation semiconductor memory devices.
Laser powder bed fusion of biodegradable Zn-4Cu alloy: Processing, microstructure and properties
Zn's natural degradability and biocompatibility make it a promising candidate for implants, however, its mechanical properties remain insufficient for bone applications. In this study, the performance of Zn was enhanced by developing Zn-Cu alloys via laser powder bed fusion (LPBF). Optimal LPBF parameters for forming stable tracks were achieved by adjusting laser power and scanning speed. Under optimized conditions of 100 W and 100 mm/s, high-density (99.58%) Zn-Cu alloys with improved hardness (68.2HV) and yield strength (160 MPa) were achieved. These improvements are attributed to solid solution strengthening, segregation strengthening, and grain refinement. The Zn-Cu alloys also demonstrated favorable degradation behavior, with a rate of 0.16 mm/year. This degradation is primarily driven by micro-galvanic corrosion between the CuZn5 phase and Zn matrix, along with refined grains and increased grain boundary density. This work demonstrates a viable strategy for fabricating Zn-based implants with enhanced structural integrity and mechanical performance via LPBF.