1,721,050 research outputs found
Conclusion : reflections and lessons from the pandemic
No full textThis concluding chapter presents a summary of the research findings in the previous chapters, along with some reflections for each of the five themes of the book and a discussion of necessary future responses (post-pandemic or in the event of a new pandemic) and topics that require further exploration. The pandemic brought into sharp relief pre-existing social disparities and affected vulnerable populations the most. The economic impacts of the pandemic were diverse and varied by geography, but again certain geographies and economic sectors were more buffered from negative outcomes than others. A lesson and a challenge for policymakers is to find ways to understand and reduce these disparities, instead of pushing them under the rug. The impacts on mobility and travel were dramatic as total trips decreased, transit usage fell dramatically, and telecommuting and active modes of transportation increased. Some positive impacts included an improved air quality, a reduced number of traffic crashes, and a proliferation of walking and biking in some neighbourhoods. As cities are slowly recovering from the pandemic, the challenge is to keep the positive impacts but also find ways to help the transit industry rebound from its plunge. Long-term impacts of the pandemic in terms of changing patterns of work and work arrangements, shopping, recreation, and other human activities that will affect travel need additional time and more research to discern
Recommended from our members
Large-Scale, Low-Latency State Estimation Of Cyberphysical Systems With An Application To Traffic Estimation
Full text linkLarge physical systems are increasingly prevalent, and designing estimation strategies for them has become both a practical necessity and a complicated problem. Their sensing infrastructure is usually ad-hoc, and the estimate of interest is often a complex function of the data. At the same time, computing power is rapidly becoming a commodity. We show with the study of two estimation tasks in urban transportation how the proper design of algorithms can lead to significant gains in scalability compared to existing solutions. A common problem in trip planning is to make a given deadline such as arriving at the airport within an hour. Existing routing services optimize for the expected time of arrival, but do not provide the most reliable route, which accounts for the variability in travel times. Providing statistical information is even harder for trips in cities which undergo a lot of variability. This thesis aims at building scalable algorithms for inferring statistical distributions of travel time over very large road networks, using GPS points from vehicles in real-time. We consider two complementary algorithms that differ in the characteristics of the GPS data input, and in the complexity of the model: a simpler streaming Expectation-Maximization algorithm that leverages very large volumes of extremely noisy data, and a novel Markov Model-Gaussian Markov Random Field that extracts global statistical correlations from high-frequency, privacy-preserving trajectories. These two algorithms have been implemented and deployed in a pipeline that takes streams of GPS data as input, and produces distributions of travel times accessible as output. This pipeline is shown to scale on a large cluster of machines and can process tens of millions of GPS observations from an area that comprises hundreds of thousands of road segments. This is to our knowledge the first research framework that considers in an integrated fashion the problem of statistical estimation of traffic at a very large scale from streams of GPS data
Recommended from our members
Real-time estimation of distributed parameters systems: Applicaton to traffic monitoring
Full text linkThis dissertation is motivated by the practical problem of highway traffic estimation using velocity measurements from GPS enabled mobile devices such as cell phones. In order to simplify the estimation procedure, a velocity model for highway traffic is constructed, which results in a dynamical system in which the observation operator is linear. It presents a new scalar hyperbolic partial differential equation (PDE) model for traffic velocity evolution on highways, based on the seminal Lighthill-Whitham-Richards (LWR) PDE for density. Equivalence of the solution of the new velocity PDE and the solution of the LWR PDE is shown for quadratic flux functions. Because this equivalence does not hold for general flux functions, a discretized model of velocity evolution based on the Godunov scheme applied to the LWR PDE is proposed. Using an explicit instantiation of the weak boundary conditions of the PDE, the discrete velocity evolution model is generalized to a network, thus making the model applicable to arbitrary highway networks. The resulting velocity model is a nonlinear and nondifferentiable discrete time dynamical system with a linear observation operator, for which a Monte Carlo based ensemble Kalman filtering data assimilation algorithm is applied. The model and estimation technique is evaluated with experimental data obtained from a large-scale field experiment known as Mobile Century. The velocity estimates using GPS data from cellphones is compared to velocity estimates using inductive loop detector data from the PeMS system. More than 900 estimation simulations are performed using various volumes of GPS data and inductive loop detector data collected during the experiment, which show travel times can be reconstructed to less than 10% error with sufficient GPS data, loop data, or a combination of both. All data collected during the field experiment and used in the simulations are available for download at http://traffic.berkeley.edu
Recommended from our members
Data-Driven Methods for Improved Estimation and Control of an Urban Arterial Traffic Network
Full text linkTransportation is a field which is universal in our society: people from every country, culture or background are familiar with the challenges of getting around in our built environment. Yet what is not always so obvious to the average traveler is how the techniques and tools of designing, observing, and controlling our modern transportation networks are derived. In fact, the theory of traffic engineering has many gaps and unknowns that are the topic of ongoing research efforts in the academic community. This work presents a collection of theoretical and practical methodologies to advance the study of traffic flow modeling, state estimation, and control of signalized roadways in particular. It uses theory from traditional transportation engineering, but also demonstrates the application of new tools from control theory and computer science to the specific application of signalized traffic networks. First, two numerical modeling dynamics representing traffic flows on signalized arterials are presented: the well-known Cell Transmission Model, a discretization of the physical hydrodynamic laws believed to govern vehicle flows, and a new Vertical Cell Model which resembles classical "store-and-forward" models with the addition of transit delays and finite buffer capacities. Each of these models is implemented in a common software framework, which provides an ideal experimental platform for direct comparison of the competing dynamics. A chapter in this dissertation contributes a validation and comparison of the two models against real vehicle trajectory data on an existing signalized road network. Accuracy and confidence in such traffic models requires complimentary methods of observing true traffic conditions to provide initial conditions and real-time state estimates. Yet there are many technological deficiencies in existing urban roadway detection systems that prevent the acquisition of a real-time estimate of arterial link state (or queue length) at signalized intersections. Hence this thesis also contains methodology to improve the estimates obtained from existing hardware by combining data from typical infrastructure sensors with new sources of Lagrangian probe measurements. These are then assimilated into a detailed model of flow dynamics. This technique was previously proposed for continuous-flow (freeway) networks, but required novel adaptions to be applied to an interrupted-flow setting. This dissertation next explores advancements in theoretically optimal control algorithms for statistically-modeled signalized queueing networks. In the context of a large body of previous work on flow-impeding control for vertical queueing networks, the practical challenges of traffic signal control are highlighted. Some of these challenges are tackled in the specific case of the max pressure controller, an algorithm derived from the field of communications networks that has been shown to optimize through-flow in an idealized network model.The lack of adequate measurements or demand-volume data has historically been a major limitation in advancing research on signalized arterial road networks. Yet the current revolution of inexpensive storage and processing of "big data" shows promise for improving daily operations of existing roadways without the need for expensive new hardware systems. One example of this potential appears is the case of traffic signal control. Existing traffic signals are capable of operating more efficiently by changing signal plans based on real-time demand measurements through a traffic responsive plan selection (TRPS) mode of operation (rather than depending on a rigid schedule for plan changes). However, this mode is rarely used in practice because its calibration process is not accessible or intuitive to traffic technicians. This dissertation presents an application of statistical learning techniques to improve the process of calibrating and implementing an existing TRPS mechanism. A proof-of-concept implementation using historical sensor data from a busy urban intersection demonstrates that real operational improvements may be immediately achievable using existing sensing infrastructure
Recommended from our members
Real Time Flow Estimation in Channel Networks using Lagrangian Data
Full text linkThe Sacramento-San Joaquin River Delta in California becomes inadequate in fresh water resources, while the water demand in California keeps increasing. Large-scale numerical flow models, for example Delta Simulation Model II (DSM2) and River, Estuary, And Land Model (REALM), used as crucial water resources management tools, are capable of providing critical information about tidal forcing and salinity transport in the bays and channels of the Delta. Reliable flow estimation and prediction of these models, however, largely depend on an accurate representation of open boundary conditions and initial conditions, which are usually calibrated against historical data sets acquired from Eulerian measurements near the boundaries. In large watershed, unfortunately, these measurements have demonstrated many intrinsic limitations, for example small spatial coverage and sparse temporal sampling. Also, existing Eulerian sensors have many recorded failures, such as broken gauges, sensor drifts, process leaks, improper measuring devices, and many other random sources. More importantly, if the hydraulic system is radically altered, as in the case of extensive levee failures, the historical data sets can be of limited usage.In this dissertation, a sensing-modeling system featuring rapidly deployed Lagrangian drifters is developed. The system is capable of predicting regional flows and transport in the Delta in a real-time mode, without dependence on historical data. Lagrangian data is obtained when floating drifters move along with the flow and report their locations. The data provides instant information about the flow, including flow advections and eddy dispersions, and is further assimilated into underlying shallow water equation (SWE) models to characterize the flow state. Different approaches to facilitate the flow estimation have been investigated in this dissertation. First, a variational assimilation method (Quadratic Programming) is applied to a 1D SWE model (Linearized Saint-Venant equations). The assimilation method poses the problem of estimating the flow state in a channel network as a quadratic programming by minimizing a quadratic cost function -- the norm of the difference between the drifter observations and the model velocity predictions -- and expressing the constraints in terms of linearized equalities and inequalities. The problem is then efficiently solved using a fast and robust algorithm. The approach is easy to implement and low in computation costs.Later, a sequential assimilation method (Ensemble Kalman Filtering) is implemented to a 2D SWE model (depth-integrated Navier-Stokes equations). The assimilation method involves a series of state analysis and updates, where the observed Lagrangian data is incorporated into the state one step at a time to incrementally correct the model prediction. The implementation of this method demands powerful computation ability, and is achieved on high-performance computing clusters at NERSC. To assess the performance of the proposed data assimilation methods, we investigated a distributed network of channels, subject to quasi-periodic tidal forcing, in the Sacramento-San Joaquin River Delta. Field operational experiments were carried out with a fleet of over 70 floating drifters, deployed within approximately 0.55 km2 of the river network. During the experiments, more than 325,000 GPS readings were taken from the floating drifters and collected, in real time, onto a central server. It is the first experiment of this kind conducted at such scale, where high-density Lagrangian data have been collected in a real river environment and successfully assimilated over a full tidal cycle. It is demonstrated that both of the proposed assimilation methods (i.e., QP in 1D SWE model and EnKF in 2D SWE model) can handle the Lagrangian data with sufficiently accurate estimations. In many practical cases, the 1D flow estimation is adequate for water resource management to retrieve critical flow characteristics in a prompt and efficient manner. In the case of complex channel geometry, however, the 2D flow estimation is vital to describe the hydraulic system
Recommended from our members
A hybrid approach of physical laws and data-driven modeling for estimation: the example of queuing networks
Full text linkMathematical models are a mathematical abstraction of the physical reality which is of great importance to understand the behavior of a system, make estimations and predictions and so on. They range from models based on physical laws to models learned empirically, as measurements are collected, and referred to as data-driven models. A model is based on a series of choices which influence its complexity and realism. These choices represent trade-offs between different competing objectives including interpretability, scalability, accuracy, adequation to the available data, robustness or computational complexity. The thesis investigates the advantages and disadvantages of models based on physical laws versus data-driven models through the example of signalized queuing networks such as urban transportation networks.The dynamics of conservation flow networks are accurately represented by a first order partial differential equation. Using Hamilton-Jacobi theory, the thesis underlines the importance to leverage physical laws to reconstruct missing information (\emph{e.g.} signal or bottleneck characteristics) and estimate the state of the network at any time and location. Noise and uncertainty in the measurements can be integrated in the model. When measurements are sparse, the state of the network cannot be estimated at every time and location on the network. Instead, the thesis shows how to leverage other characteristics, such as periodicity. From deterministic dynamics, the thesis derives the probability distribution functions of physical entities (\emph{e.g.} waiting time, density) by marginalizing the periodic variable. Using a Dynamic Bayesian Network formulation and exploiting the convexity structure of the system, the thesis shows how this modeling leads to realistic estimations and predictions, even when little measurements are available. Finally, the thesis investigates how sparse modeling and dimensionality reduction can provide insights on the large scale behavior of the network. Large scale dynamics and patterns are hard to model accurately based on physical laws. They can be discovered through data mining algorithms and integrated into physical models
Recommended from our members
Alternate Representations for Scalable Analysis and Control of Heterogeneous Time Series
Full text linkThe recent increase in the availability of very large data sets has enabled major breakthroughs in Artificial Intelligence.Automated devices are now able to achieve a higher level of performance in computer vision, playing perfect and imperfect information games, and language processing which now compares to that of humans.Such progress is largely due to improved Single Instruction Multiple Data computing capabilities and higher bandwidth in distributed computing systemsand innovative methods to leverage them.A plethora of algorithms and theories developed in the field of Machine Learning enable better identification of system dynamics and extensive control of the corresponding systems. However, the vast majority of research focuses on problems dealing with homogenous observation data sets or control environment.Additionally, a large amount of work has focused on data sets comprising only of images, videos featuring similar sampling frequencies, and of time series with regular and identical timestamps of observation.Such a setting is not representative of the actual way data sets are collected and problems present themselves to practitioners.The present work delves into a more realistic setting where a unified representation of the data or control problem of interest is not available. We deal with a collection of heterogeneous sub-parts that relate one to another but do not naturally present themselves to practitioners in a homogenous fashion.Our main objective is to design methods that are readily applicable to heterogenous data sets and control problems in the distributed setting. The development of techniques that can be employed without additional pre-processing of the data makes them more practical to use by a broader range of individuals, companies and institutions.We first focus on large multi-variate time series comprising of observations that are not synchronous in time. We then tackle Partial Differential Equations featuring a spatial continuum of distinct states.After this initial focus on the identification of dynamics in time series -- otherwise referred to as time series analysis -- we delve into the topic of control. Control leverages the knowledge we gather about a system in order to have it reach a particular desirable state.Part of the new work presented in the current work therefore focuses on the control of distributed cohorts of agents subject to individually unique constraints.Finally, we extend the work conducted separately to heterogenous time series analysis and control and devise strategies beneficial for neural policies that identify system dynamics and optimal actions as part of the same module.As we move from system identification to distributed control our aim is to find representations of the initial heterogenous problem that are homogenous and enable communication avoidance.In each of the chapters of the present work, we methodically design an alternate unifying and summarizing representation of the initial data set or control problem of interest.Our motivation to find small, concise yet expressive representations is that they enable scalable computations in the distributed setting. When utilizing cohorts of computers inter-connected by a medium such as an ethernet or wireless network, communication time presents the main factor in the overall computing time.Decreasing the size of the messages that need to be transmitted therefore minimizes the overhead created by the need to communication information from a machine to another. With less time wasted in communication, we maximize the benefit of having more computational power and memory in the form of a distributed system.We find by designing communication avoiding homogenous representations that statistical efficiency appears as a natural by-product.To that end, we leverage elements of stochastic process and point process theory, distributed spectral representations of linearized Partial Differential equations, convex duality and stochastic optimization, and finally specific regularization schemes in Reinforcement Learning of deep neural policies.The present work features novel results on the estimation of cross-correlation of irregularly observed time series with event-driven sampling. A new analysis of the linearized Aw-Rascle-Zhang system of Partial Differential Equations is developed that unravels conditions for travelling waves to expand in the system. A comparative study of a dual splitting algorithm we developed for distributed control reveals new results that highlight how the messages being transmitted are more useful to the cohort of agents for control than for an adversary to eavesdrop on individuals. The regularization scheme we developed for neural control policies enabled extensive and robust control ability that compares with cutting edge parametric control strategies despite that no preliminary calibration is needed with our method.The applications entailed in our numerical experiments span the fields of quantitative finance, macroscopic traffic modeling, Mobility-as-a-Service, electrical load balancing, and optimal ramp metering for freeways.The alternate representations we develop are statistically efficient, scale naturally and are readily usable with collections of data-sets or controllers which may not rely on similar representational conventions
Recommended from our members
Automation of vehicular systems using deep reinforcement learning and mean-field models: Application to heavy duty trucks
Full text linkThe transportation sector consumes about a third of all energy consumed in the world, about a third of which is consumed by trucks. Future transportation systems must address this energy challenge, in addition to the other inefficiencies related to time, money, and lives lost while the system is operating. Vehicle automation is one of the promising opportunities underway. For instance, cooperative adaptive cruise control, an extension of the more popular cruise control and adaptive cruise control systems, promises to reduce fuel consumption by up to 15% for participating trucks, reduce emissions, increase road capacity at high technology penetration rates, and contribute to road safety. Heavy duty trucks are complex vehicles that are designed and built for specific mission requirements. Any of these trucks could be equipped from a wide selection of vehicle components with a significantly wide spectrum of operating dynamics and performances. Driving a heavy duty truck is an equally complex task. Human drivers must be well educated and trained about the specific truck they are about to drive and operate. They must optimize in real-time for factors such as truck dynamics and driving performance; road, truck, and payload safety; truck operation economics; truck driving law constraints; mission constraints; in addition to background traffic on the road. Automation of heavy duty truck operation tasks require equally advanced engineering tools. For instance, high precision modeling and control have historically required a detailed study of each subject truck. This thesis presents a process using deep learning and deep reinforcement learning for microscopic longitudinal modeling and control of such trucks that is agnostic to their internal mechanics. The process is demonstrated and evaluated for several truck mechanical configurations using high fidelity simulation and in the field. Cruise control of single truck operations has been considered, in addition to cooperative adaptive cruise control for multi-truck coordination. Long haul heavy duty trucks often drive within shared road infrastructure with background traffic. To account for this traffic on the road, we consider multi-scale partial differential equation mean-field models. With this approach, each truck is modeled microscopically while background traffic is modeled mesoscopically. A nondissipative numerical solver is developed and evaluated for computational study of these models. The solver maintains structure and resolution at a wide range of discretization resolutions suitable for development of optimal control laws. This thesis investigates computational methods for the automation of heavy duty trucks. While vehicle driving automation is already underway, more investigation is still required to bring about full autonomy. The future of the transportation system and trucking could benefit from further study and development of the sciences and engineering of autonomy with consideration to the complex interplay between the vehicle as an agent, the transportation system as an operations context, the logistics system as a mission context, and the human beneficiary
Recommended from our members
Learning and Optimization for Mixed Autonomy Systems - A Mobility Context
Full text linkMixed autonomy characterizes problems surrounding the gradual and complex integration of automation and AI into existing systems. In the context of mobility, we consider: how will the gradual introduction of self-driving cars change urban mobility? In this dissertation, we develop machine learning and optimization techniques to address three key challenges: 1) quantifying the behavior of such complex systems, 2) addressing inherent sensing limitations, and 3) mitigating negative effects of introducing the automation.We demonstrate that deep reinforcement learning (RL) can serve as a unifying framework for studying the behavior of disparate and complex scenarios common in mixed autonomy systems. In particular, using deep RL, we find that automating a small fraction of vehicles in various traffic scenarios can result in a significant system-level velocity increase and numerous emergent driving behaviors. We demonstrate through the development of variance reduction techniques for policy gradient methods, that deep RL has the potential to scale to high-dimensional control systems, such as traffic networks and other mixed autonomy systems. We additionally present Flow, an open source RL platform with the goal of easing the design and study of disparate traffic scenarios. To address sensing limitations inherent when only parts of a system are automated, sensor fusion is explored. In particular, we introduce a convex optimization method for cellular network measurements from AT&T at the scale of the Greater Los Angeles Area, to address a flow estimation problem previously believed to be intractable. Finally, when automation reduces the cost of the activity (of transport), anticipated negative effects include induced demand and increased energy consumption. We study how the design of the mobility system itself can mitigate these effects. In particular, joint work with Microsoft Research provides insight into how high-occupancy vehicle lanes can simultaneously satisfy comfort and time preferences of users, and provide system benefits. We introduce combinatorial optimization methods based on clustering and local search for the resulting ridesharing problem. Together, these learning and optimization methods demonstrate that a small number of vehicles and sensors can be harnessed for significant impact on urban mobility, and shed light into the future study of mixed autonomy systems
Recommended from our members
Data Assimilation in Large-scale Networks of Open Channels
Full text linkThis dissertation is mainly focused on assimilation of data into hydrodynamic models of water flow in open channel networks which is motivated by the need for accurate flow models in various applications such as emergency response and flood monitoring systems, automated gate systems and hydrological studies. We investigate application of different data assimilation techniques in different scenarios to incorporate the available flow measurements obtained from sensors into flow models to improve their accuracy.Water flow in open channels is an instance of the so-called distributed parameters systems in which the dynamics of the system is described by a set of partial differential equations. As the flow model, the Saint-Venant equations, also known as shallow water equations, which are a set of first-order hyperbolic nonlinear partial differential equations are used. Different practical scenarios are considered. In a case in which streaming measurements of the flow are available and real-time estimation of the flow state is desired, we present how standard state estimation techniques such the Kalman filter, the Extended Kalman filter and the Unscented Kalman filter can be applied to integrate the available measurements into the shallow water equations. It is also shown how these techniques can be adapted to a case in which some of the model parameters are unknown to estimate unkown parameters along with the state of the system.For data assimilation in large-scale networks which lead to high dimensional models, application of two sequential Monte Carlo methods, the optimal sampling importance resampling and the implicit particle filters, is considered. The computational cost of propagating each particle is higher in implicit particle filters, however, they provide more accurate results with smaller number of particles by choosing the particles in a way that they belong to the high probability regions of the posterior density function. We also propose a maximum-a-posteriori-based method to perform the state estimation which is shown to perform better in terms of both accuracy and computational cost for the application of interest. For flow estimation in tidally influenced channels, an efficient estimation method which takes advantage of spectral decomposition of the state is proposed. The estimation problem is formulated as a least squares regression with an -norm regularization, known as the LASSO, and a homotopy-based algorithm is implemented to solve the resulting optimization problem recursively as new measurements become available. Finally, we consider the problem of optimal topology design in multi-agent systems for efficient average consensus. The network design problem is posed in two different ways. (1) Assuming that the maximum communication cost, i.e. the maximum number of communication links, is known, the goal is to find the network topology which results in the fastest convergence to the consensus (in presence of communication time delays on the links). (2) If a minimum performance of the protocol is required, the design problem is posed as finding the network with lowest possible communication cost which fulfills the required performance. The design problem is formulated as an optimization problem which is finally transformed to a mixed integer semidefinite program
- …
