arXiv subjects

Weizi Li

Publications and source records attributed to Weizi Li.

53 records · Page 3Linked to original sources

arXiv2023

A Generic Graph Sparsification Framework using Deep Reinforcement Learning

The interconnectedness and interdependence of modern graphs are growing ever more complex, causing enormous resources for processing, storage, communication, and decision-making of these graphs. In this work, we focus on the task graph sparsification: an edge-reduced graph of a similar structure to the original graph is produced while various user-defined graph metrics are largely preserved. Existing graph sparsification methods are mostly sampling-based, which introduce high computation complexity in general and lack of flexibility for a different reduction objective. We present SparRL, the first generic and effective graph sparsification framework enabled by deep reinforcement learning. SparRL can easily adapt to different reduction goals and promise graph-size-independent complexity. Extensive experiments show that SparRL outperforms all prevailing sparsification methods in producing high-quality sparsified graphs concerning a variety of objectives.

cs.LG↗

arXiv2022

Urban Socio-Technical Systems: An Autonomy and Mobility Perspective

The future of the human race is urban. The world's population is projected to grow an additional 2.5 billion by 2050, with all expected to live in urban areas. This will increase the percentage of urban population from 55% today to 70% within three decades and further strengthen the role of cities as the hub for information, transportation, and overall socio-economic development. Unlike any other time in human history, the increasing levels of autonomy and machine intelligence are transforming cities to be no longer just human agglomerations but a fusion of humans, machines, and algorithms making collective decisions, thus complex socio-technical systems. This manuscript summarizes and discusses my efforts from the urban autonomy and mobility perspective to develop the urban socio-technical system.

cs.CY↗

arXiv2022

Understanding and Developing Equitable and Fair Transportation Systems

The transportation system is an interplay between infrastructure, vehicles, and policy. During the past century, the rapid expansion of the road network, blended with increasing vehicle production and mobility demands, has been stressing the system's capacity and resulting in a shocking amount of annual costs. To alleviate these costs while providing passengers with safe and efficient travel experiences, we need to better design and plan our transportation system. To start with, not only the design of our road network is topologically flawed but also our infrastructure likely facilitates inequality: roads and bridges are found to better connect affluent sectors while excluding the poor. While technological advancements such as connected and autonomous vehicles (CAVs) and novel operation modes such as shared economy have offered new opportunities, questions remain. First, what is the relationship between the road network, community development, demographics, and mobility behaviors? Second, by leveraging the insights from studying the first question, can we better plan, coordinate, and optimize vehicles in different modalities such as human-driven and autonomous to construct safe, efficient, and resilient traffic flows? Third, how can we build an intelligent transportation system to promote equity and fairness in our community development? This proposal is the first step toward answering these questions.

cs.CY↗

arXiv2022

Learning to Control DC Motor for Micromobility in Real Time with Reinforcement Learning

Autonomous micromobility has been attracting the attention of researchers and practitioners in recent years. A key component of many micro-transport vehicles is the DC motor, a complex dynamical system that is continuous and non-linear. Learning to quickly control the DC motor in the presence of disturbances and uncertainties is desired for various applications that require robustness and stability. Techniques to accomplish this task usually rely on a mathematical system model, which is often insufficient to anticipate the effects of time-varying and interrelated sources of non-linearities. While some model-free approaches have been successful at the task, they rely on massive interactions with the system and are trained in specialized hardware in order to fit a highly parameterized controller. In this work, we learn to steer a DC motor via sample-efficient reinforcement learning. Using data collected from hardware interactions in the real world, we additionally build a simulator to experiment with a wide range of parameters and learning strategies. With the best parameters found, we learn an effective control policy in one minute and 53 seconds on a simulation and in 10 minutes and 35 seconds on a physical system.

cs.LG↗

arXiv2021

Network-wide Multi-step Traffic Volume Prediction using Graph Convolutional Gated Recurrent Neural Network

Accurate prediction of network-wide traffic conditions is essential for intelligent transportation systems. In the last decade, machine learning techniques have been widely used for this task, resulting in state-of-the-art performance. We propose a novel deep learning model, Graph Convolutional Gated Recurrent Neural Network (GCGRNN), to predict network-wide, multi-step traffic volume. GCGRNN can automatically capture spatial correlations between traffic sensors and temporal dependencies in historical traffic data. We have evaluated our model using two traffic datasets extracted from 150 sensors in Los Angeles, California, at the time resolutions one hour and 15 minutes, respectively. The results show that our model outperforms the other five benchmark models in terms of prediction accuracy. For instance, our model reduces MAE by 25.3%, RMSE by 29.2%, and MAPE by 20.2%, compared to the state-of-the-art Diffusion Convolutional Recurrent Neural Network (DCRNN) model using the hourly dataset. Our model also achieves faster training than DCRNN by up to 52%. The data and implementation of GCGRNN can be found at https://github.com/leilin-research/GCGRNN.

cs.LG↗

arXiv2021

Black-box Adversarial Attacks on Network-wide Multi-step Traffic State Prediction Models

Traffic state prediction is necessary for many Intelligent Transportation Systems applications. Recent developments of the topic have focused on network-wide, multi-step prediction, where state of the art performance is achieved via deep learning models, in particular, graph neural network-based models. While the prediction accuracy of deep learning models is high, these models' robustness has raised many safety concerns, given that imperceptible perturbations added to input can substantially degrade the model performance. In this work, we propose an adversarial attack framework by treating the prediction model as a black-box, i.e., assuming no knowledge of the model architecture, training data, and (hyper)parameters. However, we assume that the adversary can oracle the prediction model with any input and obtain corresponding output. Next, the adversary can train a substitute model using input-output pairs and generate adversarial signals based on the substitute model. To test the attack effectiveness, two state of the art, graph neural network-based models (GCGRNN and DCRNN) are examined. As a result, the adversary can degrade the target model's prediction accuracy up to $54\%$. In comparison, two conventional statistical models (linear regression and historical average) are also examined. While these two models do not produce high prediction accuracy, they are either influenced negligibly (less than $3\%$) or are immune to the adversary's attack.

cs.LG↗

arXiv2021

Analyzing Effects of The COVID-19 Pandemic on Road Traffic Safety: The Cases of New York City, Los Angeles, and Boston

The COVID-19 pandemic has resulted in significant social and economic impacts throughout the world. In addition to the health consequences, the impacts on traffic behaviors have also been sudden and dramatic. We have analyzed how the road traffic safety of New York City, Los Angeles, and Boston in the U.S. have been impacted by the pandemic and corresponding local government orders and restrictions. To be specific, we have studied the accident hotspots' distributions before and after the outbreak of the pandemic and found that traffic accidents have shifted in both location and time compared to previous years. In addition, we have studied the road network characteristics in those hotspot regions with the hope to understand the underlying cause of the hotspot shifts.

cs.LG↗

arXiv2021

Improving Robustness of Learning-based Autonomous Steering Using Adversarial Images

For safety of autonomous driving, vehicles need to be able to drive under various lighting, weather, and visibility conditions in different environments. These external and environmental factors, along with internal factors associated with sensors, can pose significant challenges to perceptual data processing, hence affecting the decision-making and control of the vehicle. In this work, we address this critical issue by introducing a framework for analyzing robustness of the learning algorithm w.r.t varying quality in the image input for autonomous driving. Using the results of sensitivity analysis, we further propose an algorithm to improve the overall performance of the task of "learning to steer". The results show that our approach is able to enhance the learning outcomes up to 48%. A comparative study drawn between our approach and other related techniques, such as data augmentation and adversarial training, confirms the effectiveness of our algorithm as a way to improve the robustness and generalization of neural network training for autonomous driving.

cs.CV↗

arXiv2020

Spatial-temporal Analysis of COVID-19's Impact on Human Mobility: the Case of the United States

COVID-19 has been affecting every aspect of societal life including human mobility since December, 2019. In this paper, we study the impact of COVID-19 on human mobility patterns at the state level within the United States. From the temporal perspective, we find that the change of mobility patterns does not necessarily correlate with government policies and guidelines, but is more related to people's awareness of the pandemic, which is reflected by the search data from Google Trends. Our results show that it takes on average 14 days for the mobility patterns to adjust to the new situation. From the spatial perspective, we conduct a state-level network analysis and clustering using the mobility data from Multiscale Dynamic Human Mobility Flow Dataset. As a result, we find that 1) states in the same cluster have shorter geographical distances; 2) a 14-day delay again is found between the time when the largest number of clusters appears and the peak of Coronavirus-related search queries on Google Trends; and 3) a major reduction in other network flow properties, namely degree, closeness, and betweenness, of all states from the week of March 2 to the week of April 6 (the week of the largest number of clusters).

cs.SI↗

arXiv2020

Assessing Road Traffic Safety During COVID-19: Inequality, Irregularity, and Severity

COVID-19 is affecting every social sector significantly, including human mobility and subsequently road traffic safety. In this study, we analyze the impact of the pandemic on traffic accidents using two cities, namely Los Angeles and New York City in the U.S., as examples. Specifically, we have analyzed traffic accidents associated with various demographic groups, how traffic accidents are distributed in time and space, and the severity level of traffic accidents that both involve and do not involve other transportation modes (e.g., pedestrians and motorists). We have made the following observations: 1) the pandemic has disproportionately affected certain age groups, races, and genders; 2) the "hotspots" of traffic accidents have been shifted in both time and space compared to time periods that are prior to the pandemic, demonstrating irregularity; and 3) the number of non-fatal accident cases has decreased but the number of severe and fatal cases of traffic accidents remains the same under the pandemic.

physics.soc-ph↗

arXiv2020

Imperatives for Virtual Humans

Seemingly since the inception of virtual humans, there has been an effort to make their behaviors more natural and human-like. In additions to improving movement's visual quality, there has been considerable research focused on creating more intelligent virtual characters. This paper presents a framework inspired by natural language constructs that aims to author more reasonable virtual human behaviors using structured English input. We focus mainly on object types and properties, quantifiers, determiners, and spatial relations. The framework provides a natural, flexible authoring system for simulating human behaviors.

cs.AI↗

arXiv2020

Predicting Station-Level Bike-Sharing Demands Using Graph Convolutional Neural Network

This study proposes a novel Graph Convolutional Neural Network with Data-driven Graph Filter (GCNN-DDGF) model that can learn hidden heterogeneous pairwise correlations among stations to predict station-level hourly demand in a large-scale bike-sharing network. Two architectures of the GCNN-DDGF model are explored: GCNNreg-DDGF is a regular GCNN-DDGF model which contains the convolution and feedforward blocks; GCNNrec-DDGF additionally contains a recurrent block from the Long Short-term Memory neural network to capture temporal dependencies in bike-sharing demand series. Furthermore, four GCNN models are proposed whose adjacency matrices are based on various bike-sharing system data, including Spatial Distance matrix (SD), Demand matrix (DE), Average Trip Duration matrix (ATD), and Demand Correlation matrix (DC). These six GCNN models along with seven other benchmark models are built and compared using the Citi Bike dataset from New York City, which includes 272 stations and over 28 million transactions from 2013 to 2016. Results show that the GCNNrec-DDGF performs the best in terms of the Root Mean Square Error, the Mean Absolute Error, and the coefficient of determination (R2), followed by the GCNNreg-DDGF. They outperform the other models.

eess.SP↗

arXiv2019

Simulation and Learning for Urban Mobility: City-scale Traffic Reconstruction and Autonomous Driving

Traffic congestion has become one of the most critical issues worldwide. The costs due to traffic gridlock and jams are approximately $160 billion in the United States, more than £13 billion in the United Kingdom, and over one trillion dollars across the globe annually. As more metropolitan areas will experience increasingly severe traffic conditions, the ability to analyze, understand, and improve traffic dynamics becomes critical. This dissertation is an effort towards achieving such an ability. I propose various techniques combining simulation and machine learning to tackle the problem of traffic from two perspectives: city-scale traffic reconstruction and autonomous driving.

cs.OH↗

arXiv2019

ADAPS: Autonomous Driving Via Principled Simulations

Autonomous driving has gained significant advancements in recent years. However, obtaining a robust control policy for driving remains challenging as it requires training data from a variety of scenarios, including rare situations (e.g., accidents), an effective policy architecture, and an efficient learning mechanism. We propose ADAPS for producing robust control policies for autonomous vehicles. ADAPS consists of two simulation platforms in generating and analyzing accidents to automatically produce labeled training data, and a memory-enabled hierarchical control policy. Additionally, ADAPS offers a more efficient online learning mechanism that reduces the number of iterations required in learning compared to existing methods such as DAGGER. We present both theoretical and experimental results. The latter are produced in simulated environments, where qualitative and quantitative results are generated to demonstrate the benefits of ADAPS.

cs.RO↗

arXiv2018

Capture and Recovery of Connected Vehicle Data: A Compressive Sensing Approach

Connected vehicles (CVs) can capture and transmit detailed data through vehicle-to-vehicle and vehicle-to-infrastructure communications, which bring new opportunities to improve the safety, mobility, and sustainability of transportation systems. However, the potential data explosion is likely to over-burden storage and communication systems. We design a compressive sensing (CS) approach which allows CVs to capture and compress data in real-time and later recover the original data accurately and efficiently. We have evaluated our approach using two case studies. In the first case study, the CS approach is applied to re-capture 10 million CV Basic Safety Message (BSM) speed samples from the Safety Pilot Model Deployment program. The recovery performances of our approach regarding several BSM variables are explored in detail. In the second case study, a freeway traffic simulation model is built to evaluate the impact of our approach on travel time estimation. Multiple scenarios with various CV market penetration rates, On-board Unit (OBU) capacities, compression ratios, arrival rate patterns, and data capture rates are simulated. The results show the potential of saving large amounts of OBU hardware cost. Furthermore, our approach can greatly improve the accuracy of travel time estimation when CVs are in traffic congestion.

eess.SP↗

arXiv2018

Estimating Traffic Conditions At Metropolitan Scale Using Traffic Flow Theory

The rapid urbanization and increasing traffic have serious social, economic, and environmental impact on metropolitan areas worldwide. It is of a great importance to understand the complex interplay of road networks and traffic conditions. The authors propose a novel framework to estimate traffic conditions at the metropolitan scale using GPS traces. Their approach begins with an initial estimation of network travel times by solving a convex optimization program based on traffic flow theory. Then, they iteratively refine the estimated network travel times and vehicle traversed paths. Last, the authors perform a bilevel optimization process to estimate traffic conditions on road segments that are not covered by GPS data. The evaluation and comparison of the authors' approach over two state-of-the-art methods show up to 96.57% relative improvements. The authors have further conducted field tests by coupling road networks of San Francisco and Beijing with real-world GIS data, which involve 128,701 nodes, 148,899 road segments, and over 26 million GPS traces.

cs.OH↗

arXiv2018

A Compressive Sensing Approach for Connected Vehicle Data Capture and Recovery and its Impact on Travel Time Estimation

Connected vehicles (CVs) can capture and transmit detailed data such as vehicle position and speed through vehicle-to-vehicle and vehicle-to-infrastructure communications. The wealth of CV data provides new opportunities to improve safety and mobility of transportation systems. However, it is likely to overburden storage and communication systems. To mitigate this issue, we propose a compressive sensing (CS) approach that allows CVs to capture and compress data in real-time and later recover the original data accurately and efficiently. The approach is evaluated using two case studies. In the first study, we use this approach to recapture 10 million CV Basic Safety Message (BSM) speed samples. It can recover the original speed data with root-mean-squared error as low as 0.05. We also explore recovery performance for other BSM variables. In the second study, a freeway traffic simulation model is built to evaluate the impact of this approach on travel time estimation. Multiple scenarios with various CV market penetration rates, On-board Unit (OBU) capacities, compression ratios, arrival rate patterns, and data capture rates are simulated. The results show that the approach provides more accurate estimation than conventional data collection methods, through up to 65% relative reduction in travel time estimation error. Even when the compression ratio is low, the approach can provide accurate estimation, thereby reducing OBU hardware costs. Further, it can improve accuracy of travel time estimation when CVs are in traffic congestion as it provides a broader spatial-temporal coverage of traffic conditions and can accurately and efficiently recover the original CV data.

stat.AP↗