The integration of information and communications technologies across existing transportation infrastructure, systems and vehicles is fundamental to reducing traffic congestion, to improving driver safety, and to improving traveler experiences. Central to such intelligent traffic management are techniques and algorithms that are capable of analyzing the wealth of available contextual sensor data in "real time". Initial existing approaches tend to apply probability models and inference techniques to optimize traffic flow but fail to take into account certain aspects of human behavior that can affect the flow of traffic, such as patterns in human travel behavior. In this paper we explore how vehicle context information can be combined with the behavioral patterns of travelers to facilitate and improve intelligent traffic management. We present services for deriving reports on vehicle journeys that assist in the analysis of route performance, for enabling passengers to have remote access to real-time route performance information, and for the observation, learning, and utilization of human travel behavior patterns. These services provide essential traffic analysis information that is ultimately expected to lead to further improvements in intelligent traffic management, which aims at easing the flow of traffic in urban and suburban environments.
[1]
Peter Stone,et al.
Multiagent traffic management: a reservation-based intersection control mechanism
,
2004,
Proceedings of the Third International Joint Conference on Autonomous Agents and Multiagent Systems, 2004. AAMAS 2004..
[2]
John Krumm,et al.
Real Time Destination Prediction Based On Efficient Routes
,
2006
.
[3]
Krzysztof Z. Gajos,et al.
Opportunity Knocks: A System to Provide Cognitive Assistance with Transportation Services
,
2004,
UbiComp.
[4]
Henry A. Kautz,et al.
Learning and inferring transportation routines
,
2004,
Artif. Intell..
[5]
John Krumm,et al.
Route Prediction from Trip Observations
,
2008
.
[6]
Henry A. Kautz,et al.
Extracting Places and Activities from GPS Traces Using Hierarchical Conditional Random Fields
,
2007,
Int. J. Robotics Res..
[7]
Gregory D. Abowd,et al.
A Conceptual Framework and a Toolkit for Supporting the Rapid Prototyping of Context-Aware Applications
,
2001,
Hum. Comput. Interact..
[8]
Steven I-Jy Chien,et al.
Dynamic freeway travel time prediction using probe vehicle data: Link-based vs
,
2001
.
[9]
Peter Stone,et al.
Sharing the Road: Autonomous Vehicles Meet Human Drivers
,
2007,
IJCAI.