arXiv subjects

Xi Xiong

Publications and source records attributed to Xi Xiong.

26 records · Page 2Linked to original sources

arXiv2023

ADLight: A Universal Approach of Traffic Signal Control with Augmented Data Using Reinforcement Learning

Traffic signal control has the potential to reduce congestion in dynamic networks. Recent studies show that traffic signal control with reinforcement learning (RL) methods can significantly reduce the average waiting time. However, a shortcoming of existing methods is that they require model retraining for new intersections with different structures. In this paper, we propose a novel reinforcement learning approach with augmented data (ADLight) to train a universal model for intersections with different structures. We propose a new agent design incorporating features on movements and actions with set current phase duration to allow the generalized model to have the same structure for different intersections. A new data augmentation method named \textit{movement shuffle} is developed to improve the generalization performance. We also test the universal model with new intersections in Simulation of Urban MObility (SUMO). The results show that the performance of our approach is close to the models trained in a single environment directly (only a 5% loss of average waiting time), and we can reduce more than 80% of training time, which saves a lot of computational resources in scalable operations of traffic lights.

eess.SY↗

arXiv2021

From Semantic Retrieval to Pairwise Ranking: Applying Deep Learning in E-commerce Search

We introduce deep learning models to the two most important stages in product search at JD.com, one of the largest e-commerce platforms in the world. Specifically, we outline the design of a deep learning system that retrieves semantically relevant items to a query within milliseconds, and a pairwise deep re-ranking system, which learns subtle user preferences. Compared to traditional search systems, the proposed approaches are better at semantic retrieval and personalized ranking, achieving significant improvements.

cs.IR↗

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↗

arXiv2019

Analysis of a Stochastic Model for Coordinated Platooning of Heavy-duty Vehicles

Platooning of heavy-duty vehicles (HDVs) is a key component of smart and connected highways and is expected to bring remarkable fuel savings and emission reduction. In this paper, we study the coordination of HDV platooning on a highway section. We model the arrival of HDVs as a Poisson process. Multiple HDVs are merged into one platoon if their headways are below a given threshold. The merging is done by accelerating the following vehicles to catch up with the leading ones. We characterize the following random variables: (i) platoon size, (ii) headway between platoons, and (iii) travel time increment due to platoon formation. We formulate and solve an optimization problem to determine the headway threshold for platooning that leads to minimal cost (time plus fuel). We also compare our results with that from Simulation of Urban MObility (SUMO).

eess.SY↗

arXiv2019

Evaluation of Headway Threshold-based Coordinated Platooning over a Cascade of Highway Junctions

Platooning of vehicles with coordinated adaptive cruise control (CACC) capabilities is a promising technology with a strong potential for fuel savings and congestion mitigation. Although some researchers have studied the vehicle-level fuel savings of platooning, few have considered the system-level benefits. This paper evaluates vehicle platooning as a fuel-reduction method and propose a hierarchical control system. We particularly focus on the impact of platooning coordination algorithm on system-wide benefits. The main task of platooning coordination is to regulate the times at which multiple vehicles arrive at a particular junction: these vehicles can platoon only if they meet (i.e. arrive within a common time interval) at the junction. We use a micro-simulation model to evaluate a class of threshold-based coordination strategies and derive insights about the trade-off between the fuel savings due to air drag reduction in platoons and the extra fuel consumption due to the coordination (i.e. acceleration of some vehicles to catch up with the leading ones). The model is calibrated using real traffic data of a section of Interstate 210 in the Los Angeles metropolitan area. We study the relation between key decision variables, including the platooning threshold and the coordination radius, and key performance metric, fuel consumption.

eess.SY↗

arXiv2016

Combining Deep Reinforcement Learning and Safety Based Control for Autonomous Driving

With the development of state-of-art deep reinforcement learning, we can efficiently tackle continuous control problems. But the deep reinforcement learning method for continuous control is based on historical data, which would make unpredicted decisions in unfamiliar scenarios. Combining deep reinforcement learning and safety based control can get good performance for self-driving and collision avoidance. In this passage, we use the Deep Deterministic Policy Gradient algorithm to implement autonomous driving without vehicles around. The vehicle can learn the driving policy in a stable and familiar environment, which is efficient and reliable. Then we use the artificial potential field to design collision avoidance algorithm with vehicles around. The path tracking method is also taken into consideration. The combination of deep reinforcement learning and safety based control performs well in most scenarios.

cs.RO↗

arXiv2013

Practical Fine-grained Privilege Separation in Multithreaded Applications

An inherent security limitation with the classic multithreaded programming model is that all the threads share the same address space and, therefore, are implicitly assumed to be mutually trusted. This assumption, however, does not take into consideration of many modern multithreaded applications that involve multiple principals which do not fully trust each other. It remains challenging to retrofit the classic multithreaded programming model so that the security and privilege separation in multi-principal applications can be resolved. This paper proposes ARBITER, a run-time system and a set of security primitives, aimed at fine-grained and data-centric privilege separation in multithreaded applications. While enforcing effective isolation among principals, ARBITER still allows flexible sharing and communication between threads so that the multithreaded programming paradigm can be preserved. To realize controlled sharing in a fine-grained manner, we created a novel abstraction named ARBITER Secure Memory Segment (ASMS) and corresponding OS support. Programmers express security policies by labeling data and principals via ARBITER's API following a unified model. We ported a widely-used, in-memory database application (memcached) to ARBITER system, changing only around 100 LOC. Experiments indicate that only an average runtime overhead of 5.6% is induced to this security enhanced version of application.

cs.OS↗