Dynamic Graph Configuration with Reinforcement Learning for Connected Autonomous Vehicle Trajectories

Udesh Gunarathna; Hairuo Xie; Egemen Tanin; Shanika Karunasekara; Renata Borovica-Gajic

Home/Archive/arXiv

arXiv · 1910.06788

Dynamic Graph Configuration with Reinforcement Learning for Connected Autonomous Vehicle Trajectories

Udesh Gunarathna·Hairuo Xie·Egemen Tanin·Shanika Karunasekara·Renata Borovica-Gajic

View original source ↗Read source document ↗Export metadata ↓

Abstract

Traditional traffic optimization solutions assume that the graph structure of road networks is static, missing opportunities for further traffic flow optimization. We are interested in optimizing traffic flows as a new type of graph-based problem, where the graph structure of a road network can adapt to traffic conditions in real time. In particular, we focus on the dynamic configuration of traffic-lane directions, which can help balance the usage of traffic lanes in opposite directions. The rise of connected autonomous vehicles offers an opportunity to apply this type of dynamic traffic optimization at a large scale. The existing techniques for optimizing lane-directions are however not suitable for dynamic traffic environments due to their high computational complexity and the static nature. In this paper, we propose an efficient traffic optimization solution, called Coordinated Learning-based Lane Allocation (CLLA), which is suitable for dynamic configuration of lane-directions. CLLA consists of a two-layer multi-agent architecture, where the bottom-layer agents use a machine learning technique to find a suitable configuration of lane-directions around individual road intersections. The lane-direction changes proposed by the learning agents are then coordinated at a higher level to reduce the negative impact of the changes on other parts of the road network. Our experimental results show that CLLA can reduce the average travel time significantly in congested road networks. We believe our method is general enough to be applied to other types of networks as well.

Explore related subjects

eess.SY cs.DB cs.LG cs.SY math.OC

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Udesh Gunarathna, Hairuo Xie, Egemen Tanin, Shanika Karunasekara, Renata Borovica-Gajic. 2019-10-14. Dynamic Graph Configuration with Reinforcement Learning for Connected Autonomous Vehicle Trajectories. https://arxiv.org/abs/1910.06788

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Co-Investment with Payoff-Sharing Mechanism for Cooperative Decision-Making in Network Design Games

Network-based systems are inherently interconnected, with the design and performance of subnetworks being interdependent. However, the decisions of self-interested operators may lead to suboptimal outcomes for users and the overall system. This paper explores cooperative mechanisms that can simultaneously benefit both operators and users. We address this challenge using a game-theoretical framework that integrates both non-cooperative and cooperative game theory. In the non-cooperative stage, we propose a network design game in which subnetwork decision-makers strategically design local infrastructures. In the cooperative stage, co-investment with payoff-sharing mechanism is developed to enlarge collective benefits and fairly distribute them. To demonstrate the effectiveness of our framework, we conduct case studies on the Sioux Falls network and real-world public transport networks in Zurich and Winterthur, Switzerland. Our evaluation considers impacts on environmental sustainability, social welfare, and economic efficiency. The proposed framework provides a foundation for improving interdependent networked systems by enabling strategic cooperation among self-interested operators.

eess.SY↗

arXiv2026

Generalizable Optimal Control with Transformers: One Policy Across Diverse Systems

Classical optimal control designs a separate controller for each plant. Even for the Linear Quadratic Regulator (LQR), every new model must be identified and its Riccati equation re-solved. We ask whether a single learned policy can instead serve an entire family of systems, and we show that one transformer can. We train the policy to imitate optimal LQR state feedback across a collection of heterogeneous Multiple-Input, Multiple-Output (MIMO) Linear Time-Invariant (LTI) systems that differ in their state and input dimensions and in their cost objectives. A shared representation lets the same parameters control every member of the family. It combines system-wise standardization, zero-padding and masking across dimensions, and an explicit encoding of the cost matrices. At run time, the policy maps a short window of recent states and the specified cost to a control action. It uses no plant matrices and identifies the dynamics implicitly from the state history. We evaluate on $28$ simulated systems over $9{,}675$ closed-loop rollouts, and no unstable rollout was observed in any of them. On the systems seen during training, it attains a median relative sub-optimality of $0.022\%$, even under parameter perturbations of up to $\pm10\%$. It transfers to unseen systems with lightweight fine-tuning, reaching a median sub-optimality of $0.19\%$. These results support transformers as generalizable near-optimal controllers for structured families of linear systems.

eess.SY↗

arXiv2026

Two-Timescale Asymptotic Simulations of Hybrid Inclusions with Applications to Stochastic Hybrid Optimization

Convergence properties of model-free two-timescale asymptotic simulations of singularly perturbed hybrid inclusions are developed. A hybrid inclusion combines constrained differential and difference inclusions to capture continuous (flow) and discrete (jump) dynamics, respectively. Sufficient conditions are established under which sequences of iterates and step sizes constitute a two-timescale asymptotic simulation of such a system, with limiting behavior characterized via weakly invariant and internally chain-transitive sets of an associated boundary layer and reduced system. To illustrate the applicability of these results, conditions are given under which a two-timescale stochastic approximation of a hybrid optimization algorithm asymptotically recovers the behavior of its deterministic counterpart.

eess.SY↗