arXiv subjects

Jianping Wu

Publications and source records attributed to Jianping Wu.

35 records · Page 2Linked to original sources

arXiv2022

Cyclic Graph Attentive Match Encoder (CGAME): A Novel Neural Network For OD Estimation

Origin-Destination Estimation plays an important role in the era of Intelligent Transportation. Nevertheless, as a under-determined problem, OD estimation confronts many challenges from cross-space inference to non-convex, non-linear optimization. As a powerful nonlinear approximator, deep learning is an ideal data-driven method to provide a novel perspective for OD estimation. However, viewing multi-interval traffic counts as spatial-temporal inputs and OD matrix as heterogeneous graph-structured output, the existing neural network architecture is not suitable for the cross-space inference problem thus a new deep learning architecture is needed. We propose CGAME, short for cyclic graph attentive matching encoder, including bi-directional encoder-decoder networks and a novel graph matcher in the hidden layer with double-layer attention mechanism. It realizes effective information exchange between the forward networks and backward networks and establishes coupling relations across underlying feature space. The proposed model achieves state-of-the-art compared with baselines in the designed experiments and offers a paradigm for inference tasks across representation space.

cs.LG↗

arXiv2022

HARL: A Novel Hierachical Adversary Reinforcement Learning for Automoumous Intersection Management

As an emerging technology, Connected Autonomous Vehicles (CAVs) are believed to have the ability to move through intersections in a faster and safer manner, through effective Vehicle-to-Everything (V2X) communication and global observation. Autonomous intersection management is a key path to efficient crossing at intersections, which reduces unnecessary slowdowns and stops through adaptive decision process of each CAV, enabling fuller utilization of the intersection space. Distributed reinforcement learning (DRL) offers a flexible, end-to-end model for AIM, adapting for many intersection scenarios. While DRL is prone to collisions as the actions of multiple sides in the complicated interactions are sampled from a generic policy, restricting the application of DRL in realistic scenario. To address this, we propose a hierarchical RL framework where models at different levels vary in receptive scope, action step length, and feedback period of reward. The upper layer model accelerate CAVs to prevent them from being clashed, while the lower layer model adjust the trends from upper layer model to avoid the change of mobile state causing new conflicts. And the real action of CAV at each step is co-determined by the trends from both levels, forming a real-time balance in the adversarial process. The proposed model is proven effective in the experiment undertaken in a complicated intersection with 4 branches and 4 lanes each branch, and show better performance compared with baselines.

cs.MA↗

arXiv2022

COOR-PLT: A hierarchical control model for coordinating adaptive platoons of connected and autonomous vehicles at signal-free intersections based on deep reinforcement learning

Platooning and coordination are two implementation strategies that are frequently proposed for traffic control of connected and autonomous vehicles (CAVs) at signal-free intersections instead of using conventional traffic signals. However, few studies have attempted to integrate both strategies to better facilitate the CAV control at signal-free intersections. To this end, this study proposes a hierarchical control model, named COOR-PLT, to coordinate adaptive CAV platoons at a signal-free intersection based on deep reinforcement learning (DRL). COOR-PLT has a two-layer framework. The first layer uses a centralized control strategy to form adaptive platoons. The optimal size of each platoon is determined by considering multiple objectives (i.e., efficiency, fairness and energy saving). The second layer employs a decentralized control strategy to coordinate multiple platoons passing through the intersection. Each platoon is labeled with coordinated status or independent status, upon which its passing priority is determined. As an efficient DRL algorithm, Deep Q-network (DQN) is adopted to determine platoon sizes and passing priorities respectively in the two layers. The model is validated and examined on the simulator Simulation of Urban Mobility (SUMO). The simulation results demonstrate that the model is able to: (1) achieve satisfactory convergence performances; (2) adaptively determine platoon size in response to varying traffic conditions; and (3) completely avoid deadlocks at the intersection. By comparison with other control methods, the model manifests its superiority of adopting adaptive platooning and DRL-based coordination strategies. Also, the model outperforms several state-of-the-art methods on reducing travel time and fuel consumption in different traffic conditions.

cs.LG↗

arXiv2022

Modeling Adaptive Platoon and Reservation Based Autonomous Intersection Control: A Deep Reinforcement Learning Approach

As a strategy to reduce travel delay and enhance energy efficiency, platooning of connected and autonomous vehicles (CAVs) at non-signalized intersections has become increasingly popular in academia. However, few studies have attempted to model the relation between the optimal platoon size and the traffic conditions around the intersection. To this end, this study proposes an adaptive platoon based autonomous intersection control model powered by deep reinforcement learning (DRL) technique. The model framework has following two levels: the first level adopts a First Come First Serve (FCFS) reservation based policy integrated with a nonconflicting lane selection mechanism to determine vehicles' passing priority; and the second level applies a deep Q-network algorithm to identify the optimal platoon size based on the real-time traffic condition of an intersection. When being tested on a traffic micro-simulator, our proposed model exhibits superior performances on travel efficiency and fuel conservation as compared to the state-of-the-art methods.

cs.LG↗

arXiv2022

MILES: Visual BERT Pre-training with Injected Language Semantics for Video-text Retrieval

Dominant pre-training work for video-text retrieval mainly adopt the "dual-encoder" architectures to enable efficient retrieval, where two separate encoders are used to contrast global video and text representations, but ignore detailed local semantics. The recent success of image BERT pre-training with masked visual modeling that promotes the learning of local visual context, motivates a possible solution to address the above limitation. In this work, we for the first time investigate masked visual modeling in video-text pre-training with the "dual-encoder" architecture. We perform Masked visual modeling with Injected LanguagE Semantics (MILES) by employing an extra snapshot video encoder as an evolving "tokenizer" to produce reconstruction targets for masked video patch prediction. Given the corrupted video, the video encoder is trained to recover text-aligned features of the masked patches via reasoning with the visible regions along the spatial and temporal dimensions, which enhances the discriminativeness of local visual features and the fine-grained cross-modality alignment. Our method outperforms state-of-the-art methods for text-to-video retrieval on four datasets with both zero-shot and fine-tune evaluation protocols. Our approach also surpasses the baseline models significantly on zero-shot action recognition, which can be cast as video-to-text retrieval.

cs.CV↗

arXiv2022

All in One: Exploring Unified Video-Language Pre-training

Mainstream Video-Language Pre-training models \cite{actbert,clipbert,violet} consist of three parts, a video encoder, a text encoder, and a video-text fusion Transformer. They pursue better performance via utilizing heavier unimodal encoders or multimodal fusion Transformers, resulting in increased parameters with lower efficiency in downstream tasks. In this work, we for the first time introduce an end-to-end video-language model, namely \textit{all-in-one Transformer}, that embeds raw video and textual signals into joint representations using a unified backbone architecture. We argue that the unique temporal information of video data turns out to be a key barrier hindering the design of a modality-agnostic Transformer. To overcome the challenge, we introduce a novel and effective token rolling operation to encode temporal representations from video clips in a non-parametric manner. The careful design enables the representation learning of both video-text multimodal inputs and unimodal inputs using a unified backbone model. Our pre-trained all-in-one Transformer is transferred to various downstream video-text tasks after fine-tuning, including text-video retrieval, video-question answering, multiple choice and visual commonsense reasoning. State-of-the-art performances with the minimal model FLOPs on nine datasets demonstrate the superiority of our method compared to the competitive counterparts. The code and pretrained model have been released in https://github.com/showlab/all-in-one.

cs.CV↗

arXiv2021

Fractal Rosette: A Stable Space-Ground Network Structure in Mega-Constellation

We present F-Rosette, a stable space-ground network structure for low-earth orbit (LEO) satellite mega-constellations at scale. Due to the dynamic many-to-many space-ground mapping in high mobility, existing LEO mega-constellations with IP protocol stack suffer from frequent user IP address changes (every 133~510s per user) and network routing re-convergence (<20% network usability). To provably stabilize the space-ground network under high mobility and many-to-many dynamics, F-Rosette adopts a recursive structure over the Rosette constellation, derives a hierarchical and time-invariant network address space from a new geographical coordinate system, and ensures efficient and stable routing via geographical-to-topological routing embedding without re-convergence. Our hardware-in-the-loop, trace-driven emulations validate F-Rosette's stability, near-optimal routing (<1.4% additional delays), and marginal overhead (<1% CPU, <2MB memory) for resource-constrained satellites.

cs.NI↗

arXiv2019

Anomaly Detection in Road Networks Using Sliding-Window Tensor Factorization

Anomaly detection in road networks is vital for traffic management and emergency response. However, existing approaches do not directly address multiple anomaly types. We propose a tensor-based spatio-temporal model for detecting multiple types of anomalies in road networks. First, we represent network traffic data as a 3rd-order tensor. Next, we acquire spatial and multi-scale temporal patterns of traffic variations via a novel, computationally efficient tensor factorization algorithm: sliding window tensor factorization. Then, from the factorization results, we can identify different anomaly types by measuring deviations from different spatial and temporal patterns. Finally, we discover path-level anomalies by formulating anomalous path inference as a linear program that solves for the best matched paths of anomalous links. We evaluate the proposed methods via both synthetic experiments and case studies based on a real-world vehicle trajectory dataset, demonstrating advantages of our approach over baselines.

physics.soc-ph↗

arXiv2019

Two Dimensional Router: Design and Implementation

Higher dimensional classification has attracted more attentions with increasing demands for more flexible services in the Internet. In this paper, we present the design and implementation of a two dimensional router (TwoD router), that makes forwarding decisions based on both destination and source addresses. This TwoD router is also a key element in our current effort towards two dimensional IP routing. With one more dimension, the forwarding table will grow explosively given a straightforward implementation. As a result, it is impossible to fit the forwarding table to the current TCAM, which is the de facto standard despite its limited capacity. To solve the explosion problem, we propose a forwarding table structure with a novel separation of TCAM and SRAM. As such, we move the redundancies in expensive TCAM to cheaper SRAM, while the lookup speed is comparable with conventional routers. We also design the incremental update algorithms that minimize the number of accesses to memory. We evaluate our design with a real implementation on a commercial router, Bit-Engine 12004, with real data sets. Our design does not need new devices, which is favorable for adoption. The results also show that the performance of our TwoD router is promising.

cs.NI↗

arXiv2018

Modeling and Routing for Predictable Dynamic Networks: This paper is only for copyright protection, and unpublished to the top-level version

The topologies of predictable dynamic networks are continuously dynamic in terms of node position, network connectivity and link metric. However, their dynamics are almost predictable compared with the ad-hoc network. The existing routing protocols specific to static or ad-hoc network do not consider this predictability and thus are not very efficient for some cases. We present a topology model based on Divide-and-Merge methodology to formulate the dynamic topology into the series of static topologies, which can reflect the topology dynamics correctly with the least number of static topologies. Then we design a dynamic programing algorithm to solve that model and determine the timing of routing update and the topology to be used. Besides, for the classic predictable dynamic network---space Internet, the links at some region have shorter delay, which leads to most traffic converge at these links. Meanwhile, the connectivity and metric of these links continuously vary, which results in a great end-to-end path variations and routing updates. In this paper, we propose a stable routing scheme which adds link life-time into its metric to eliminate these dynamics. And then we take use of the Dijkstra's greedy feature to release some paths from the dynamic link, achieving the goal of routing stability. Experimental results show that our method can significantly decrease the number of changed paths and affected network nodes, and then greatly improve the network stability. Interestingly, our method can also achieve better network performance, including the less number of loss packets, smoother variation of end-to-end delay and higher throughput.

cs.NI↗

arXiv2016

Major Maintenance Schedule Optimization for Electric Multiple Unit Considering Passenger Transport Demand

It is an important objective pursued in a railway agency or company to reduce the major maintenance costs of electric multiple unit (EMU). The EMU major maintenance schedule decides when to undergo major maintenance or undertake transportation task for train-set, based on practical requirements, such as passenger transport demand, workshop inspection capacity, and maintenance requirements. Experienced railway practitioners can generally produce a feasible major maintenance schedule; however, this manual process is time-consuming, and an optimal solution is not guaranteed. This research constructs a time-space network that can display the train-set status transformation process between available and major maintenance status. On this basis, a 0-1 integer programming model is developed to reduce the major maintenance costs with consideration of all necessary regulations and practical constraints. Compared with the manual process, the genetic algorithm with simulated annealing survival mechanism is also developed to improve solution quality and efficiency. It can reduce the complexity of the algorithm substantially by excluding infeasible solutions when constructing the model.

math.OC↗

arXiv2015

Impacts of rainfall weather on urban traffic in beijing: analysis and modeling

Recently an increasing number of researches have been focused on the influence of rainfall intensity on traffic flow. Conclusions have been reached that inclement weather does have negative impacts on key traffic parameters. However, due to lack of data, limited work has been implemented in China. In this paper, the impacts of rainfall intensity on urban road traffic flow characteristics are quantified, based on the historical traffic data and weather data in Beijing, capital of China. The reductions of road capacity and operating speed are obtained by statistical estimation for different rainfall intensity categories against clear weather. Then the modified speed-density function and speed-flow function are calibrated at different rainfall levels, from which the reductions of free-flow speed can be calculated. Finally, a generalized continuous speed-flow-rainfall model is developed and calibrated. The validation results show a good accuracy, indicating the new model can be used for urban traffic management under various rainfall intensities.

physics.soc-ph↗

arXiv2015

Discovery of Important Crossroads in Road Network using Massive Taxi Trajectories

A major problem in road network analysis is discovery of important crossroads, which can provide useful information for transport planning. However, none of existing approaches addresses the problem of identifying network-wide important crossroads in real road network. In this paper, we propose a novel data-driven based approach named CRRank to rank important crossroads. Our key innovation is that we model the trip network reflecting real travel demands with a tripartite graph, instead of solely analysis on the topology of road network. To compute the importance scores of crossroads accurately, we propose a HITS-like ranking algorithm, in which a procedure of score propagation on our tripartite graph is performed. We conduct experiments on CRRank using a real-world dataset of taxi trajectories. Experiments verify the utility of CRRank.

cs.AI↗

arXiv2014

Study on FLOWSIM and its Application for Isolated Signal-ized Intersection Assessment

Recently the traffic related problems have become strategically important, due to the continuously increasing vehicle number. As a result, microscopic simulation software has become an efficient method in traffic engineering for its cost-effectiveness and safety characteristics. In this paper, a new fuzzy logic based simulation software (FLOWSIM) is introduced, which can reflect the mixed traffic flow phenomenon in China better. The fuzzy logic based car-following model and lane-changing model are explained in detail. Furthermore, its applications for mixed traffic flow management in mid-size cities and for signalized intersection management assessment in large cities are illustrated by examples in China. Finally, further study objectives are discussed.

cs.OH↗

arXiv2014

Car-following model on two lanes and stability analysis

Considering lateral influence from adjacent lane, an improved car-following model is developed in this paper. Then linear and non-linear stability analyses are carried out. The modified Korteweg-de Vries (MKdV) equation is derived with the kink-antikink soliton solution. Numerical simulations are implemented and the result shows good consistency with theoretical study.

cs.CE↗

arXiv2014

An improved car-following model considering variable safety headway distance

Considering high speed following on expressway or highway, an improved car-following model is developed in this paper by introducing variable safety headway distance. Stability analysis of the new model is carried out using the control theory method. Finally, numerical simulations are implemented and the results show good consistency with theoretical study.

math.NA↗

arXiv2013

A Multi-stage Collaborative 3D GIS to Support Public Participation

This paper presents a collaborative 3D GIS to support public participation. Realizing that public-involved decision making is often a multi-stage process, the proposed system is designed to provide coherent support for collaborations in the different stages. We differentiate ubiquitous participation and intensive participation, and identify their suitable application stages. The proposed system, then, supports both of the two types of participation by providing synchronous and asynchronous collaboration functionalities. Applying the concept of Digital Earth, the proposed system also features a virtual globe-based user interface. Such an interface integrates a variety of data, functions and services into a unified virtual environment which is delivered to both experts and public participants through the Internet. The system has been designed as a general software framework, and can be tailored for specific projects. In this study, we demonstrate it using a scene modeling case and provide a preliminary evaluation towards its usability.

cs.CY↗