scholarly journals Route Choice of the Shortest Travel Time Based on Floating Car Data

2016 ◽  
Vol 2016 ◽  
pp. 1-11 ◽  
Author(s):  
Jingwei Shen ◽  
Yifang Ban
Keyword(s):  
Travel Time ◽  
Optimal Path ◽  
Route Choice ◽  
Edge Weight ◽  
Map Matching ◽  
Traffic Condition ◽  
Floating Car Data ◽  
Road Map ◽  
Shortest Distance ◽  
Comparison Results

Finding a route with shortest travel time according to the traffic condition can help travelers to make better route choice decisions. In this paper, the shortest travel time based on FCD (floating car data) which is used to assess overall traffic conditions is proposed. To better fit FCD and road map, a new map matching algorithm which fully considers distance factor, direction factor, and accessibility factor is designed to map all GPS (Global Positioning System) points to roads. A mixed graph structure is constructed and a route analysis algorithm of shortest travel time which considers the dynamic edge weight is designed. By comparing with other map matching algorithms, the proposed method has a higher accuracy. The comparison results show that the shortest travel time path is longer than the shortest distance path, but it costs less traveling time. The implementation of the route choice based on the shortest travel time method can be used to guide people’s travel by selecting the space-time dependent optimal path.

scholarly journals The Effect of Route-choice Strategy on Transit Travel Time Estimates

2019 ◽  
Author(s):  
Nate Wessel ◽  
Steven Farber
Keyword(s):  
Travel Time ◽  
Shortest Path ◽  
Imperfect Information ◽  
Optimal Path ◽  
Shortest Paths ◽  
Route Choice ◽  
Travel Times ◽  
Selection Strategies ◽  
Time Estimates ◽  
Average Travel Time

Estimates of travel time by public transit often rely on the calculation of a shortest-path between two points for a given departure time. Such shortest-paths are time-dependent and not always stable from one moment to the next. Given that actual transit passengers necessarily have imperfect information about the system, their route selection strategies are heuristic and cannot be expected to achieve optimal travel times for all possible departures. Thus an algorithm that returns optimal travel times at all moments will tend to underestimate real travel times all else being equal. While several researchers have noted this issue none have yet measured the extent of the problem. This study observes and measures this effect by contrasting two alternative heuristic routing strategies to a standard shortest-path calculation. The Toronto Transit Commission is used as a case study and we model actual transit operations for the agency over the course of a normal week with archived AVL data transformed into a retrospective GTFS dataset. Travel times are estimated using two alternative route-choice assumptions: 1) habitual selection of the itinerary with the best average travel time and 2) dynamic choice of the next-departing route in a predefined choice set. It is shown that most trips present passengers with a complex choice among competing itineraries and that the choice of itinerary at any given moment of departure may entail substantial travel time risk relative to the optimal outcome. In the context of accessibility modelling, where travel times are typically considered as a distribution, the optimal path method is observed in aggregate to underestimate travel time by about 3-4 minutes at the median and 6-7 minutes at the \nth{90} percentile for a typical trip.

Taxi Driver's Route Choice Behavior Analysis Based on Floating Car Data

2013 ◽  
Vol 361-363 ◽  
pp. 2036-2039 ◽  
Author(s):  
En Jian Yao ◽  
Long Pan ◽  
Yang Yang ◽  
Yong Sheng Zhang
Keyword(s):  
Behavior Analysis ◽  
Choice Behavior ◽  
Road Traffic ◽  
Choice Model ◽  
Route Choice ◽  
Map Matching ◽  
Taxi Drivers ◽  
Floating Car Data ◽  
Route Choice Behavior ◽  
Minor Road

Taxi drivers are viewed having more driving experience, being more familiar with road traffic condition, and in turn having more rational route choice behaviors than ordinary drivers. Using floating car data (FCD) of Beijing taxi in 2010, this study discusses the influence of road network conditions and traffic status to taxi drivers route choice behaviors. First, trip information is extracted from FCD using trip-identification method; Second, map matching and K-shortest paths are used to construct the trajectories and the sets of alternate routes, and route similarity evaluation is conducted to build the sample data of route choice behavior analysis; Finally, route choice model for taxi drivers based on Multinomial Logit (MNL) Model is estimated. The result shows that taxi drivers tend to choose the route which has faster driving speed, less frequency of left turns, more proportion of express way and less proportion of minor road, and increasing a left-turn or decreasing travel speed by 2.12km/h has the same effect on route choice utility. This study is expected to be helpful to establish map-matching algorithm of FCD, route guidance scheme and traffic assignment model.

scholarly journals ANALISIS TINGKAT KESESUAIAN DARI KLASIFIKASI KEPADATAN LALU LINTAS DAN WAKTU TEMPUH GOOGLE MAPS

2019 ◽  
Vol 2 (2) ◽  
Author(s):  
Laksita Amelia Paramesti ◽  
Dedi Atunggal
Keyword(s):  
Travel Time ◽  
Statistical Tests ◽  
Statistical Test ◽  
Traffic Information ◽  
Actual Condition ◽  
Traffic Density ◽  
Traffic Classification ◽  
Google Maps ◽  
Traffic Condition ◽  
Significant Difference

 Traffic congestion is one of problem that occur in big cities, therefore people need traffic information to determine traffic condition. One of many applications that provides traffic information is Google Maps. From the information generated, there are insuitability between google maps’s traffic update and travel time with the actual condition. So the aim of this study is to analyze the suitability level of traffic density classification and google maps travel time. Based on the speed range by Google, the level of suitability can be determined, while the google maps travel time is done by statistical tests. The statistical test used is a statistical test of two parameters using table t with 95% confidence level. The results of this study indicate that the level of suitability of the traffic classification only reaches 35%. The low level of suitability is caused by network latency. While information on google maps travel time does not have a significant difference in actual time.

TAML: A Traffic-aware Multi-task Learning Model for Estimating Travel Time

2021 ◽  
Vol 12 (6) ◽  
pp. 1-14
Author(s):  
Jiajie Xu ◽  
Saijun Xu ◽  
Rui Zhou ◽  
Chengfei Liu ◽  
An Liu ◽  
...  
Keyword(s):  
Travel Time ◽  
Mutual Influence ◽  
Time Estimation ◽  
Travel Time Estimation ◽  
Mobility Patterns ◽  
Traffic Condition ◽  
Task Learning ◽  
Shared Space ◽  
Important Research Topic ◽  
Multiple Loss

Travel time estimation has been recognized as an important research topic that can find broad applications. Existing approaches aim to explore mobility patterns via trajectory embedding for travel time estimation. Though state-of-the-art methods utilize estimated traffic condition (by explicit features such as average traffic speed) for auxiliary supervision of travel time estimation, they fail to model their mutual influence and result in inaccuracy accordingly. To this end, in this article, we propose an improved traffic-aware model, called TAML, which adopts a multi-task learning network to integrate a travel time estimator and a traffic estimator in a shared space and improves the accuracy of estimation by enhanced representation of traffic condition, such that more meaningful implicit features are fully captured. In TAML, multi-task learning is further applied for travel time estimation in multi-granularities (including road segment, sub-path, and entire path). The multiple loss functions are combined by considering the homoscedastic uncertainty of each task. Extensive experiments on two real trajectory datasets demonstrate the effectiveness of our proposed methods.

Fuel-optimal path finding algorithm using traffic information at urban intersection

2019 ◽  
Author(s):  
Jooin Lee ◽  
Hyeongcheol Lee
Keyword(s):  
Fuel Consumption ◽  
Intelligent Transportation System ◽  
Optimal Path ◽  
Intelligent Transportation ◽  
Transportation System ◽  
Traffic Model ◽  
Traffic Information ◽  
Traffic Condition ◽  
Decision Algorithm ◽  
The Road

Intelligent Transportation System (ITS) is actively studied as the sensor and communication technology in the vehicle develops. The Intelligent Transportation System collects, processes, and provides information on the location, speed, and acceleration of the vehicles in the intersection. This paper proposes a fuel optimal route decision algorithm. The algorithm estimates traffic condition using information of vehicles acquired from several ITS intersections and determines the route that minimizes fuel consumption by reflecting the estimated traffic condition. Simplified fuel consumption models and road information (speed limit, average speed, etc.) are used to estimate the amount of fuel consumed when passing through the road. Dynamic Programming (DP) is used to determine the route that fuel consumption can be minimized. This algorithm has been verified in an intersection traffic model that reflects the actual traffic environment (Korea Daegu Technopolis) and the corresponding traffic model is modeled using AIMSUN.

Valuation of Different Types of Travel Time Reliability in Route Choice

2006 ◽  
Vol 1985 (1) ◽  
pp. 162-170 ◽  
Author(s):  
Enide A. I. Bogers ◽  
Francesco Viti ◽  
Serge P. Hoogendoorn ◽  
Henk J. Van Zuylen
Keyword(s):  
Travel Time ◽  
Route Choice ◽  
Travel Time Reliability ◽  
Different Types
Sign in / Sign up

Export Citation Format

Share Document