Driving time and path generation for heavy construction sites from GPS traces

The paper presents a methodology for using GPS probe data to automatically extract the driving time between workstations and build a detailed representation of the paths between workstations in a construction environment. The inferred driving time distribution is aimed as input to construction simulation models to assess fleet performance, while the path information can be utilized to examine the performance of individual vehicles. A case study, using GPS data collected from a construction site, is used to demonstrate the capability of the proposed approach. The GPS data are processed without any prior knowledge about the underlying work environment. The results show that the proposed approach is capable of accurately inferring the driving time distribution and the paths between workstations.

[1]  Dieter Pfoser,et al.  A comparison and evaluation of map construction algorithms using vehicle tracking data , 2014, GeoInformatica.

[2]  James Biagioni,et al.  Map inference in the face of noise and disparity , 2012, SIGSPATIAL/GIS.

[3]  Erik Jenelius,et al.  Identification of Workstations in Earthwork Operations from Vehicle GPS Data , 2017 .

[4]  M. Ahmed,et al.  A Comparison and Evaluation of Map Construction Algorithms , 2014, ArXiv.

[5]  Eduardo Mario Nebot,et al.  Robust Inference of Principal Road Paths for Intelligent Transportation Systems , 2011, IEEE Transactions on Intelligent Transportation Systems.

[6]  Haris N. Koutsopoulos,et al.  Optimal Fleet Selection for Earthmoving Operations , 2013 .

[7]  S. Abourizk,et al.  STATISTICAL PROPERTIES OF CONSTRUCTION DURATION DATA , 1992 .

[8]  Stefan Edelkamp,et al.  Route Planning and Map Inference with Global Positioning Traces , 2003, Computer Science in Perspective.

[9]  Cliff Schexnayder,et al.  Describing a beta probability distribution function for construction simulation , 2005 .

[10]  John Krumm,et al.  From GPS traces to a routable road map , 2009, GIS.

[11]  Andy Hopper,et al.  Scalable, Distributed, Real-Time Map Generation , 2006, IEEE Pervasive Computing.

[12]  Gianantonio Bortolin,et al.  Gear shift optimization for off-road construction vehicles , 2012 .

[13]  Derya Birant,et al.  ST-DBSCAN: An algorithm for clustering spatial-temporal data , 2007, Data Knowl. Eng..

[14]  Anil K. Jain.  Data clustering: 50 years beyond K-means , 2010, Pattern Recognit. Lett..

[15]  Dieter Pfoser,et al.  On vehicle tracking data-based road network generation , 2012, SIGSPATIAL/GIS.

[16]  Mohamed Marzouk.  Optimizing earthmoving operations using computer simulation , 2002 .

[17]  Christopher Wilson,et al.  Mining GPS Traces for Map Refinement , 2004, Data Mining and Knowledge Discovery.

[18]  Christopher Wilson,et al.  Mining GPS data to augment road models , 1999, KDD '99.

[19]  Jimmie C. Hicks.  Haul-Unit Performance , 1993 .

[20]  Jiali Fu.  A Microscopic Simulation Model for Earthmoving Operations , 2012 .

[21]  M. Braga,et al.  Exploratory Data Analysis , 2018, Encyclopedia of Social Network Analysis and Mining. 2nd Ed..

[22]  John Krumm,et al.  Detecting Road Intersections from GPS Traces , 2010, GIScience.