arXiv subjects

Li Jin

Publications and source records attributed to Li Jin.

At least 55 records · Page 3Linked to original sources

arXiv2023

Robust Queue Length Estimation for Ramp Metering in a Connected Vehicle Environment

Connected vehicles (CVs) can provide numerous new data via vehicle-to-vehicle or vehicle-to-infrastructure communication. These data can in turn be used to facilitate real-time traffic state estimation. In this paper, we focus on ramp queue length estimation in a connected vehicle environment, which improves control design and implementation of ramp metering algorithms. One major challenge of the estimation problem is that the CV data only represent partial traffic observations and could introduce new uncertainties if real-time CV penetration rates are unknown. To address this, we build our estimation approach on both traditional freeway sensors and new CV data. We first formulate a ramp queue model that considers i) variations in the penetration rate and ii) noise in measurements. Then we develop a robust filter that minimizes the impacts of these two kinds of uncertainties on queue estimation. More importantly, we show that the designed filter has guaranteed long-term estimation accuracy. It allows us to quantify in a theoretical way the relationship between estimation error and fluctuation of CV penetration rates. We also provide a series of simulation results to verify our approach.

eess.SY↗

arXiv2023

TOT: Topology-Aware Optimal Transport For Multimodal Hate Detection

Multimodal hate detection, which aims to identify harmful content online such as memes, is crucial for building a wholesome internet environment. Previous work has made enlightening exploration in detecting explicit hate remarks. However, most of their approaches neglect the analysis of implicit harm, which is particularly challenging as explicit text markers and demographic visual cues are often twisted or missing. The leveraged cross-modal attention mechanisms also suffer from the distributional modality gap and lack logical interpretability. To address these semantic gaps issues, we propose TOT: a topology-aware optimal transport framework to decipher the implicit harm in memes scenario, which formulates the cross-modal aligning problem as solutions for optimal transportation plans. Specifically, we leverage an optimal transport kernel method to capture complementary information from multiple modalities. The kernel embedding provides a non-linear transformation ability to reproduce a kernel Hilbert space (RKHS), which reflects significance for eliminating the distributional modality gap. Moreover, we perceive the topology information based on aligned representations to conduct bipartite graph path reasoning. The newly achieved state-of-the-art performance on two publicly available benchmark datasets, together with further visual analysis, demonstrate the superiority of TOT in capturing implicit cross-modal alignment.

cs.CL↗

arXiv2023

Vehicle Sequencing at Signal-Free Intersections: Analytical Performance Guarantees Based on PDMP Formulation

Signal-free intersections are a representative application of smart and connected vehicle technologies. Although extensive results have been developed for trajectory planning and autonomous driving, the formulation and evaluation of vehicle sequencing have not been well understood.In this paper, we consider theoretical guarantees of macroscopic performance (i.e., capacity and delay) of typical sequencing policies at signal-free intersections. We model intersection traffic as a piecewise-deterministic Markov process (PDMP). We analytically characterize the intersection capacity regions and provide upper bounds on travel delay under three typical policies, viz. first-in-first-out, min-switchover, and longer-queue-first. We obtain these results by constructing policy-specific Lyapunov functions and computing mean drift of the PDMP. We also validate the results via a series of micro-simulation-based experiments.

eess.SY↗

arXiv2022

Securing Signal-free Intersections against Strategic Jamming Attacks: A Macroscopic Approach

We consider the security-by-design of a signal-free intersection for connected and autonomous vehicles in the face of strategic jamming attacks. We use a fluid model to characterize macroscopic traffic flow through the intersection, where the saturation rate is derived from a vehicle coordination algorithm. We model jamming attacks as sudden increase in communication latency induced on vehicle-to-infrastructure connectivity; such latency triggers the safety mode for vehicle coordination and thus reduces the intersection saturation rate. A strategic attacker selects the attacking rate, while a system operator selects key design parameters, either the saturation rate or the recovery rate. Both players' actions induce technological costs and jointly determine the mean travel delay. By analyzing the equilibrium of the security game, we study the preferable level of investment in the intersection's nominal discharging capability or recovery capability.

math.OC↗

arXiv2022

EMVLight: a Multi-agent Reinforcement Learning Framework for an Emergency Vehicle Decentralized Routing and Traffic Signal Control System

Emergency vehicles (EMVs) play a crucial role in responding to time-critical calls such as medical emergencies and fire outbreaks in urban areas. Existing methods for EMV dispatch typically optimize routes based on historical traffic-flow data and design traffic signal pre-emption accordingly; however, we still lack a systematic methodology to address the coupling between EMV routing and traffic signal control. In this paper, we propose EMVLight, a decentralized reinforcement learning (RL) framework for joint dynamic EMV routing and traffic signal pre-emption. We adopt the multi-agent advantage actor-critic method with policy sharing and spatial discounted factor. This framework addresses the coupling between EMV navigation and traffic signal control via an innovative design of multi-class RL agents and a novel pressure-based reward function. The proposed methodology enables EMVLight to learn network-level cooperative traffic signal phasing strategies that not only reduce EMV travel time but also shortens the travel time of non-EMVs. Simulation-based experiments indicate that EMVLight enables up to a $42.6\%$ reduction in EMV travel time as well as an $23.5\%$ shorter average travel time compared with existing approaches.

cs.AI↗

arXiv2022

Resilient Ramp Control for Highways Facing Stochastic Perturbations

Highway capacity is often subject to stochastic perturbations due to the combined effects of weather, traffic mixture, driver behavior, etc. This paper is motivated by the need of a systematic approach to traffic control with performance guarantees in the face of such perturbations. We develop a novel control-theoretic method for designing perturbation-resilient ramp metering. We consider a cell-transmission model with 1) Markovian cell capacities and 2) buffers representing on-ramps and upstream mainline. Using this model, we analyze the stability of on-ramp queues by constructing piecewise Lyapunov functions that consider the nature of nonlinear traffic dynamics. Then, we design ramp controllers that guarantee bounds for throughput and queue sizes. We also formulate the problem of coordinated ramp metering as a bi-level optimization with non-convex inner sub-problems. To address the computational issue in solving this problem, we also consider localized and partially coordinated reformulations. A case study of a 18.1-km highway in Los Angeles, USA indicates a 8.3\% (resp. 9.9\%) reduction of vehicle-hours-traveled obtained by the localized (resp. partially coordinated) control, both outperforming the classical ALINEA and METALINE controllers.

math.OC↗

arXiv2021

V2I Connectivity-Based Dynamic Queue-Jump Lane for Emergency Vehicles: A Deep Reinforcement Learning Approach

Emergency vehicle (EMV) service is a key function of cities and is exceedingly challenging due to urban traffic congestion. A main reason behind EMV service delay is the lack of communication and cooperation between vehicles blocking EMVs. In this paper, we study the improvement of EMV service under V2I connectivity. We consider the establishment of dynamic queue jump lanes (DQJLs) based on real-time coordination of connected vehicles. We develop a novel Markov decision process formulation for the DQJL problem, which explicitly accounts for the uncertainty of drivers' reaction to approaching EMVs. We propose a deep neural network-based reinforcement learning algorithm that efficiently computes the optimal coordination instructions. We also validate our approach on a micro-simulation testbed using Simulation of Urban Mobility (SUMO). Validation results show that with our proposed methodology, the centralized control system saves approximately 15\% EMV passing time than the benchmark system.

cs.AI↗

arXiv2021

HYPER^2: Hyperbolic Poincare Embedding for Hyper-Relational Link Prediction

Link Prediction, addressing the issue of completing KGs with missing facts, has been broadly studied. However, less light is shed on the ubiquitous hyper-relational KGs. Most existing hyper-relational KG embedding models still tear an n-ary fact into smaller tuples, neglecting the indecomposability of some n-ary facts. While other frameworks work for certain arity facts only or ignore the significance of primary triple. In this paper, we represent an n-ary fact as a whole, simultaneously keeping the integrity of n-ary fact and maintaining the vital role that the primary triple plays. In addition, we generalize hyperbolic Poincaré embedding from binary to arbitrary arity data, which has not been studied yet. To tackle the weak expressiveness and high complexity issue, we propose HYPER^2 which is qualified for capturing the interaction between entities within and beyond triple through information aggregation on the tangent space. Extensive experiments demonstrate HYPER^2 achieves superior performance to its translational and deep analogues, improving SOTA by up to 34.5\% with relatively few dimensions. Moreover, we study the side effect of literals and we theoretically and experimentally compare the computational complexity of HYPER^2 against several best performing baselines, HYPER^2 is 49-61 times quicker than its counterparts.

cs.CL↗

arXiv2021

A Hybrid Queuing Model for Coordinated Vehicle Platooning on Mixed-Autonomy Highways: Training and Validation

Platooning of connected and autonomous vehicles (CAVs) is an emerging technology with a strong potential for throughput improvement and fuel reduction. Adequate macroscopic models are critical for system-level efficiency and reliability of platooning. In this paper, we consider a hybrid queuing model for a mixed-autonomy highway section and develop an easy-to-use training algorithm. The model predicts CAV and non-CAV counts according to the traffic demand as well as key parameters of the highway section. The training algorithm learns the highway parameters from observed data in real time. We test the model and the algorithm in Simulation of Urban Mobility (SUMO) and show that the prediction error is around 15% in a stationary setting and around 25% in a non-stationary setting. We also show that the trained model leads to a platoon headway regulation policy very close to the simulated optimum. The proposed model and algorithm can directly support model-predictive decision-making for platooning in mixed autonomy.

eess.SY↗

arXiv2021

Dielectric and electro-mechanic nonlinearities in perovskite oxide ferroelectrics, relaxors and relaxor ferroelectrics

The polarization and strain response of ferroelectric materials at fields below the macroscopic coercive field is of a paramount importance for the operation of many electronic devices. The response of real ferroelectric and related materials is in general complex and difficult to interpret. The reason for this is that many processes in a ferroelectric material contribute to its properties, often concurrently. Examples include motion of ferroelectric and ferroelastic domains, presence of domains within domains, dynamics of different types of polar nano-entities, interaction of polar nano-entities (e.g., polar nanoregions in relaxors) with the strain and polarization within domains, motion of defects and rearrangement of defect clusters and their interaction with polarization and strain. One signature of these processes is nonlinearity of the strain and polarization. Most ferroelectrics exhibit nonlinear response at all practical field levels meaning that the apparent material coefficients depend on the amplitude of the driving excitation. In this paper we show that an investigation of nonlinear behavior is a sensitive way to study various mechanisms operating in dielectric and piezoelectric materials. We review the basic formalism of the nonlinear description of polarization and strain, give a physical interpretation of different terms and illustrate this approach on numerous examples of relaxors, relaxor ferroelectrics, hard and soft ferroelectrics, and morphotropic phase boundary compositions. An experimental approach based on a lock-in technique that is well-suited for such studies is also discussed.

cond-mat.mtrl-sci↗

arXiv2021

Dynamic Queue-Jump Lane for Emergency Vehicles under Partially Connected Settings: A Multi-Agent Deep Reinforcement Learning Approach

Emergency vehicle (EMV) service is a key function of cities and is exceedingly challenging due to urban traffic congestion. The main reason behind EMV service delay is the lack of communication and cooperation between vehicles blocking EMVs. In this paper, we study the improvement of EMV service under V2X connectivity. We consider the establishment of dynamic queue jump lanes (DQJLs) based on real-time coordination of connected vehicles in the presence of non-connected human-driven vehicles. We develop a novel Markov decision process formulation for the DQJL coordination strategies, which explicitly accounts for the uncertainty of drivers' yielding pattern to approaching EMVs. Based on pairs of neural networks representing actors and critics for agent vehicles, we develop a multi-agent actor-critic deep reinforcement learning algorithm that handles a varying number of vehicles and a random proportion of connected vehicles in the traffic. Approaching the optimal coordination strategies via indirect and direct reinforcement learning, we present two schemata to address multi-agent reinforcement learning on this connected vehicle application. Both approaches are validated, on a micro-simulation testbed SUMO, to establish a DQJL fast and safely. Validation results reveal that, with DQJL coordination strategies, it saves up to 30% time for EMVs to pass a link-level intelligent urban roadway than the baseline scenario.

cs.AI↗

arXiv2020

Analysis and Design of Vehicle Platooning Operations on Mixed-Traffic Highways

Platooning of connected and autonomous vehicles (CAVs) has a significant potential for throughput improvement. However, the interaction between CAVs and non-CAVs may limit the practically attainable improvement due to platooning. To better understand and address this limitation, we introduce a new fluid model of mixed-autonomy traffic flow and use this model to analyze and design platoon coordination strategies. We propose tandem-link fluid model that considers randomly arriving platoons sharing highway capacity with non-CAVs. We derive verifiable conditions for stability of the fluid model by analyzing an underlying M/D/1 queuing process and establishing a Foster-Lyapunov drift condition for the fluid model. These stability conditions enable a quantitative analysis of highway throughput under various scenarios. The model is useful for designing platoon coordination strategies that maximize throughput and minimize delay. Such coordination strategies are provably optimal in the fluid model and are practically relevant. We also validate our results using standard macroscopic (cell transmission model, CTM) and microscopic (Simulation for Urban Mobility, SUMO) simulation models.

math.OC↗

arXiv2020

Latency-Robust Control of High-Speed Signal-Free Intersections

High-speed signal-free intersections are a novel urban traffic operations enabled by connected and autonomous vehicles. However, the impact of communication latency on intersection performance has not been well understood. In this paper, we consider vehicle coordination at signal-free intersections with latency. We focus on two questions: (i) how to ensure latency-resiliency of the coordination algorithm, and (ii) how latency affects the intersection's capacity. We consider a trajectory-based model with bounded speed uncertainties. Latency leads to uncertain state observation. We propose a piecewise-linear control law that ensures safety (avoidance of interference) as long as the initial condition is safe. We also analytically quantify the throughput that the proposed control can attain in the face of latency.

eess.SY↗

arXiv2020

Analysis of a Markovian Queuing Model for Autonomous Signal-Free Intersection

We consider a novel, analytical queuing model for vehicle coordination at signal-free intersections. Vehicles arrive at an intersection according to Poisson processes, and the crossing times are constants dependent of vehicle types. We use this model to quantitatively relate key operational parameters (vehicle speed/acceleration, inter-vehicle headway) to key performance metrics (throughput and delay) under the first-come-first-serve rule. We use the Foster-Lyapunov drift condition to obtain stability criteria and an upper bound for average time delay. Based on these results, we compare the efficiency of signal free intersections with conventional vehicles and with connected and autonomous vehicles. We also validate our results in Simulation of Urban Mobility (SUMO).

eess.SY↗

arXiv2020

SRQA: Synthetic Reader for Factoid Question Answering

The question answering system can answer questions from various fields and forms with deep neural networks, but it still lacks effective ways when facing multiple evidences. We introduce a new model called SRQA, which means Synthetic Reader for Factoid Question Answering. This model enhances the question answering system in the multi-document scenario from three aspects: model structure, optimization goal, and training method, corresponding to Multilayer Attention (MA), Cross Evidence (CE), and Adversarial Training (AT) respectively. First, we propose a multilayer attention network to obtain a better representation of the evidences. The multilayer attention mechanism conducts interaction between the question and the passage within each layer, making the token representation of evidences in each layer takes the requirement of the question into account. Second, we design a cross evidence strategy to choose the answer span within more evidences. We improve the optimization goal, considering all the answers' locations in multiple evidences as training targets, which leads the model to reason among multiple evidences. Third, adversarial training is employed to high-level variables besides the word embedding in our model. A new normalization method is also proposed for adversarial perturbations so that we can jointly add perturbations to several target variables. As an effective regularization method, adversarial training enhances the model's ability to process noisy data. Combining these three strategies, we enhance the contextual representation and locating ability of our model, which could synthetically extract the answer span from several evidences. We perform SRQA on the WebQA dataset, and experiments show that our model outperforms the state-of-the-art models (the best fuzzy score of our model is up to 78.56%, with an improvement of about 2%).

cs.CL↗

arXiv2020

Optimizing Coordinated Vehicle Platooning: An Analytical Approach Based on Stochastic Dynamic Programming

Platooning connected and autonomous vehicles (CAVs) can improve traffic and fuel efficiency. However, scalable platooning operations require junction-level coordination, which has not been well studied. In this paper, we study the coordination of vehicle platooning at highway junctions. We consider a setting where CAVs randomly arrive at a highway junction according to a general renewal process. When a CAV approaches the junction, a system operator determines whether the CAV will merge into the platoon ahead according to the positions and speeds of the CAV and the platoon. We formulate a Markov decision process to minimize the discounted cumulative travel cost, i.e. fuel consumption plus travel delay, over an infinite time horizon. We show that the optimal policy is threshold-based: the CAV will merge with the platoon if and only if the difference between the CAV's and the platoon's predicted times of arrival at the junction is less than a constant threshold. We also propose two ready-to-implement algorithms to derive the optimal policy. Comparison with the classical value iteration algorithm implies that our approach explicitly incorporating the characteristics of the optimal policy is significantly more efficient in terms of computation. Importantly, we show that the optimal policy under Poisson arrivals can be obtained by solving a system of integral equations. We also validate our results in simulation with Real-time Strategy (RTS) using real traffic data. The simulation results indicate that the proposed method yields better performance compared with the conventional method.

eess.SY↗

arXiv2020

Dynamic Origin-Destination Matrix Prediction with Line Graph Neural Networks and Kalman Filter

Modern intelligent transportation systems provide data that allow real-time dynamic demand prediction, which is essential for planning and operations. The main challenge of prediction of dynamic Origin-Destination (O-D) demand matrices is that demands cannot be directly measured by traffic sensors; instead, they have to be inferred from aggregate traffic flow data on traffic links. Specifically, spatial correlation, congestion and time dependent factors need to be considered in general transportation networks. In this paper we propose a novel O-D prediction framework combining heterogeneous prediction in graph neural networks and Kalman filter to recognize spatial and temporal patterns simultaneously. The underlying road network topology is converted into a corresponding line graph in the newly designed Fusion Line Graph Convolutional Networks (FL-GCNs), which provide a general framework of predicting spatial-temporal O-D flows from link information. Data from New Jersey Turnpike network are used to evaluate the proposed model. The results show that our proposed approach yields the best performance under various prediction scenarios. In addition, the advantage of combining deep neural networks and Kalman filter is demonstrated.

cs.LG↗

arXiv2020

Coordinating Vehicle Platoons for Highway Bottleneck Decongestion and Throughput Improvement

Truck platooning is a technology that is expected to become widespread in the coming years. Apart from the numerous benefits that it brings, its potential effects on the overall traffic situation need to be studied further, especially at bottlenecks and ramps. Assuming we can control the platoons from the infrastructure, they can be used as controlled moving bottlenecks, actuating control actions on the rest of the traffic, and potentially improving the throughput of the whole system. In this paper, we use a multi-class cell transmission model to capture the interaction between truck platoons and background traffic, and propose a corresponding queuing model, which we use for control design. We use platoon speeds, and the number of lanes platoons occupy as control inputs, and design a control strategy for throughput improvement of a highway section with a bottleneck. By postponing and shaping the inflow to the bottleneck, we are able to avoid traffic breakdown and capacity drop, which significantly reduces the total time spent of all vehicles. We derived the estimated improvement in throughput that is achieved by applying the proposed control law, and then tested it in a simulation study and found that the median delay of all vehicles by 75.6% compared to the uncontrolled case. Notably, although they are slowed down while actuating control actions, platooned vehicles experience less delay compared to the case without control, since they avoid going through congestion at the bottleneck.

math.OC↗