No abstract
Increasingly available city data and advanced learning techniques have empowered people to improve the efficiency of our city functions. Among them, improving the urban transportation efficiency is one of the most prominent topics. Recent studies have proposed to use reinforcement learning (RL) for traffic signal control. Different from traditional transportation approaches which rely heavily on prior knowledge, RL can learn directly from the feedback. On the other side, without a careful model design, existing RL methods typically take a long time to converge and the learned models may not be able to adapt to new scenarios. For example, a model that is trained well for morning traffic may not work for the afternoon traffic because the traffic flow could be reversed, resulting in a very different state representation.In this paper, we propose a novel design called FRAP, which is based on the intuitive principle of phase competition in traffic signal control: when two traffic signals conflict, priority should be given to one with larger traffic movement (i.e., higher demand). Through the phase competition modeling, our model achieves invariance to symmetrical cases such as flipping and rotation in traffic flow. By conducting comprehensive experiments, we demonstrate that our model finds better solutions than existing RL methods in the complicated all-phase selection problem, converges much faster during training, and achieves superior generalizability for different road structures and traffic conditions.
Traffic signal control is an emerging application scenario for reinforcement learning. Besides being as an important problem that affects people's daily life in commuting, traffic signal control poses its unique challenges for reinforcement learning in terms of adapting to dynamic traffic environment and coordinating thousands of agents including vehicles and pedestrians. A key factor in the success of modern reinforcement learning relies on a good simulator to generate a large number of data samples for learning. The most commonly used open-source traffic simulator SUMO is, however, not scalable to large road network and large traffic flow, which hinders the study of reinforcement learning on traffic scenarios. This motivates us to create a new traffic simulator CityFlow with fundamentally optimized data structures and efficient algorithms. CityFlow can support flexible definitions for road network and traffic flow based on synthetic and real-world data. It also provides user-friendly interface for reinforcement learning. Most importantly, CityFlow is more than twenty times faster than SUMO and is capable of supporting city-wide traffic simulation with an interactive render for monitoring. Besides traffic signal control, CityFlow could serve as the base for other transportation studies and can create new possibilities to test machine learning methods in the intelligent transportation domain.
Urban anomalies, such as abnormal movements of crowds and accidents, may result in loss of life or property if not handled properly. It would be of great value for governments if anomalies can be automatically alerted in their early stage. However, detecting anomalies in urban area has two main challenges. First, the criteria to determine an anomaly on different occasions (e.g. rainy days vs. sunny days, or holidays vs. workdays) and in different places (e.g. tourist attractions vs. office areas) are distinctly different, as these occasions and places have their own definitions on normal patterns. Second, urban anomalies often exhibit complex forms (e.g. road closure may cause decrease in taxi flow and increase in bike flow). We need an algorithm that not only models the anomaly degree of individual data source but also the combination of changes in multiple data sources. In this paper, we propose a two-step method to tackle those challenges. In the first step, we use a similarity-based algorithm to estimate an anomaly score for each individual data source in each region and time slot based on the values of historically similar regions. Those scores are fed into the second step, where we propose an algorithm based on one-class Support Vector Machine to capture rare patterns occurred in multiple data sources, nearby regions or time slots, and give a final, integrated anomaly score for each region. Evaluations based on both synthetic and real world datasets show the advantages of our method beyond baseline techniques such as distance-based, probability-based methods.
The collective anomaly denotes a collection of nearby locations that are anomalous during a few consecutive time intervals in terms of phenomena collectively witnessed by multiple datasets. The collective anomalies suggest there are underlying problems that may not be identified based on a single data source or in a single location. It also associates individual locations and time intervals, formulating a panoramic view of an event. To detect a collective anomaly is very challenging, however, as different datasets have different densities, distributions, and scales. Additionally, to find the spatio-temporal scope of a collective anomaly is time consuming as there are many ways to combine regions and time slots. Our method consists of three components: MultipleSource Latent-Topic (MSLT) model, Spatio-Temporal Likelihood Ratio Test (ST_LRT) model, and a candidate generation algorithm. MSLT combines multiple datasets to infer the latent functions of a geographic region in the framework of a topic model. In turn, a estimate the underlying distribution of a sparse dataset generated in the region. ST_LRT learns a proper underlying distribution for different datasets, and calculates an anomalous degree for each dataset based on a likelihood ratio test (LRT). It then aggregates the anomalous degrees of different datasets, using a skyline detection algorithm. We evaluate our method using five datasets related to New York City (NYC): 311 complaints, taxicab data, bike rental data, points of interest, and road network data, finding the anomalies that cannot be identified (or earlier than those detected) by a single dataset. Results show the advantages beyond six baseline methods.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.