Searcharxiv⌕ Search

arXiv subjects

Zeren Xing

Publications and source records attributed to Zeren Xing.

3 recordsLinked to original sources

CoSyDelay: Cognitive Symbolic Regression for Traffic Delay Estimation

Trustworthy estimation of traffic delays at signalized intersections is critical for modern transportation systems, as it supports proactive traffic control for congestion mitigation. Existing analytical methods often rely on idealized assumptions that limit their accuracy under complex traffic conditions, whereas data-driven methods may achieve strong estimation performance but usually lack transparent structures, which reduces confidence in their practical application. To address these limitations, we propose CoSyDelay, a cognitive symbolic regression (SR) framework for automatically deriving explicit and physically consistent empirical delay estimation expressions (DEEs). Specifically, CoSyDelay decomposes intersection-level delay estimation into turning-movement-level subproblems, thereby reducing the complexity of the symbolic search. During DEE learning, CoSyDelay constructs domain-informed symbolic inputs from traffic variables. Large language models (LLMs) are employed as symbolic search operators to iteratively generate and refine candidate expression structures, whose movement-specific coefficients are subsequently calibrated using approach-level delay labels. A composite fitness function evaluates the learned DEEs jointly in terms of estimation accuracy and compliance with specified traffic-delay principles. Experimental results on multiple signalized intersections demonstrate that the resulting expressions achieve competitive estimation performance while maintaining physical consistency, thereby supporting trustworthy delay estimation. Source code and datasets are available at https://github.com/ForrestXie9/CoSyDelay.

cs.ET↗

Discovering Programmatic Policies from Reinforcement Learning-Based Traffic Signal Controllers

Traffic signal control (TSC) is critical for mitigating urban congestion. Deep reinforcement learning (DRL) has achieved strong performance by learning adaptive policies from traffic observations, but learned neural controllers are often opaque, structurally complex, and difficult to generalize across scenarios. We propose PPL-TSC, a programmatic policy learning framework that distills compact and human-readable TSC policies from DRL teachers. PPL-TSC formulates policy learning as an evolutionary search over phase utility functions (PUFs), which score candidate signal phases and select the highest-utility phase for execution. Each generation consists of four steps: policy generation, policy review, policy calibration, and policy evaluation. In the generation step, a large language model (LLM) acts as a semantics-aware evolutionary operator to propose and refine candidate PUFs. Generated PUFs are screened through explicit checks for syntactic validity, mathematical soundness, and consistency with TSC principles, with invalid ones repaired through iterative feedback. Valid PUFs are then calibrated to improve behavioral fidelity to the DRL teacher, and evaluated using a joint score combining teacher fidelity and traffic-control performance to select candidates for the next generation. Extensive experiments across diverse traffic scenarios and representative DRL-based controllers show that PPL-TSC produces compact and human-readable policies, achieves competitive performance for most teacher families, improves transfer generalization, and substantially reduces computational cost. Code is available at https://github.com/ForrestXie9/PPL-TSC.

cs.ET↗

An Enhanced Modelling Approach for Warehouse Sharing Platform System Designing Problem

With the increasing importance of sustainability, warehouse sharing arises as a possible way to improve the efficiency of the existing logistics system. This paper studied the warehouse sharing platform systems (WSPS) and investigated its supply chain network, including factories, warehouses, and customers. We proposed an enhanced modelling approach for the warehouse sharing platform system design problem (WSPSDP) using the multi-allocation hub location routing problem framework. New elements such as inter-warehouse transportation and multiple-allocation scheme were added compared to the existing WSPS model. Then an adaptive large neighbourhood decomposition search heuristic was applied to solve our problem. Computational experiments were conducted on different-sized instances for comparison with the WSPS model without inter-warehouse transportation and the WSPS model with single-allocation scheme. The results suggested that our proposed WSPSDP model is more cost-efficient than the existing WSPS models, and it has the potential to promote the utilisation of existing cheap idle warehouses.

math.OC↗