Navigate Like a Cabbie: Probabilistic Reasoning from Observed Context-Aware Behavior

被引:222
作者
Ziebart, Brian D. [1 ]
Maas, Andrew L. [1 ]
Dey, Anind K. [1 ]
Bagnell, J. Andrew [1 ]
机构
[1] Carnegie Mellon Univ, Sch Comp Sci, Pittsburgh, PA 15213 USA
来源
PROCEEDINGS OF THE 10TH INTERNATIONAL CONFERENCE ON UBIQUITOUS COMPUTING (UBICOMP 2008) | 2008年
基金
美国国家科学基金会;
关键词
Decision modeling; vehicle navigation; route prediction;
D O I
10.1145/1409635.1409678
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
We present PROCAB, an efficient method for Probabilistically Reasoning from Observed Context-Aware Behavior. It models the context-dependent utilities and underlying reasons that people take different actions. The model generalizes to unseen situations and scales to incorporate rich contextual information. We train our model using the route preferences of 25 taxi drivers demonstrated in over 100,000 miles of collected data, and demonstrate the performance of our model by inferring: (1) decision at next intersection, (2) route to known destination, and (3) destination given partially traveled route.
引用
收藏
页码:322 / 331
页数:10
相关论文
共 28 条
[1]  
Abbeel P, 2004, INT C MACHINE LEARNI, P1
[2]   Using GPS to learn significant locations and predict movement across multiple users [J].
Ashbrook, Daniel ;
Starner, Thad .
PERSONAL AND UBIQUITOUS COMPUTING, 2003, 7 (05) :275-286
[3]   LeZi-update: An information-theoretic framework for personal mobility tracking in PCS networks [J].
Bhattacharya, A ;
Das, SK .
WIRELESS NETWORKS, 2002, 8 (2-3) :121-135
[4]  
Bohnenberger T, 2002, LECT NOTES COMPUT SC, V2411, P155
[5]  
Chang KH, 2007, LECT NOTES COMPUT SC, V4717, P19
[6]  
Fogarty J., 2005, ACM Transactions on Computer-Human Interaction, V12, P119, DOI 10.1145/1057237.1057243
[7]  
Hennessy DA, 1999, AGGRESSIVE BEHAV, V25, P409, DOI 10.1002/(SICI)1098-2337(1999)25:6<409::AID-AB2>3.0.CO
[8]  
2-0
[9]  
Hull B., 2006, SENSYS, DOI DOI 10.1145/1182807.1182821
[10]   INFORMATION THEORY AND STATISTICAL MECHANICS [J].
JAYNES, ET .
PHYSICAL REVIEW, 1957, 106 (04) :620-630