Principal Investigator

Anthony Tomasic

Status

Completed

Start Date

Jan. 1, 2015

End Date

Dec. 31, 2015

Project Type

Research Advanced

Grant Program

MAP-21 TSET National (2013 - 2018)

Grant Cycle

2015 TSET UTC - National

Visibility

Public

Abstract

This project used to be named "Tiramisu: Live Bus Occupancy and Data Feeds” but we feel it is more appropriate to use the name listed above. The primary source of information for rider safety with respect to dynamic events such as cancelled buses, detours, traffic conditions and other factors is the transit system website. Although technological enhancements, such as real-time tracking, rider alert RSS feeds, and Twitter feeds, are available for transit users, such information sources do not always report updates reliably. For example, some real-time tracking systems stop transmitting updates about a bus if the bus takes a detour from its scheduled route. Rider alerts might temporarily suspend updates due to holidays or employee PTO. Notifications through social media frequently offer information of relevance, but are often difficult to understand, or for one to comprehend the impact of the message on their trip. Paradoxically, users are still faced with a lot of effort at navigating the appropriate information sources, finding and understanding messages and updates of relevance to their trip. Our project goal is to access transit service live update data feeds, identify the routes and stops on which their updates will have an impact, and provide an integrated display of that information in the user’s Tiramisu smart phone app. The extracted information can be used in multiple ways to improve the interactive experience of the user and keep them better informed. For example, if bus stops will be discontinued between certain hours of a day for, say, water main repair, and other stops will be established during that period, a search of nearby stops will reflect such temporary changes. This, combined with vehicle fullness data from the Tiramisu system, will allow riders to identify alternate transit trip options that are not too full to board.    

Description

-

Timeline

-

Strategic Description / RD&T

Deployment Plan

-

Expected Outcomes/Impacts

-

Expected Outputs

TRID

Individuals Involved

Email	Name	Affiliation	Role	Position
steinfeld@cmu.edu	Steinfeld, Aaron	Robotics Institute	Co-PI	Faculty - Tenured
tomasic@cs.cmu.edu	Tomasic, Anthony	Port Authority of Allegheny County	PI	Faculty - Tenured

Budget

Amount of UTC Funds Awarded

$77813.38

Total Project Budget (from all funding sources)

$77813.00

Documents

Type	Name	Uploaded
Final Report	modeling_transit_patterns_via_mobile_app_logs.pdf	March 21, 2018, 8:19 a.m.
Publication	Leveraging Vehicle Connectivity and Autonomy to Stabilize Flow in Mixed Traffic Conditions: Accounting for Human-driven Vehicle Driver Behavioral Heterogeneity and Perception-reaction Time Delay	Oct. 24, 2020, 5:55 p.m.
Publication	Understanding human perception of bus fullness: An empirical study of crowdsourced fullness ratings and automatic passenger count data	Oct. 24, 2020, 6 p.m.
Publication	Facilitating connected autonomous vehicle operations using space-weighted information fusion and deep reinforcement learning based control.	Oct. 24, 2020, 7:02 p.m.

Match Sources

No match sources!

Partners

No partners!