System and method for generating vehicle travel data
Disclosed embodiments provide techniques for generation of vehicle travel data. Past-travel data including previously taken trips, along with metadata including, but not limited to, vehicle type, vehicle model, navigation device model, are obtained and classified. A travel route for simulation data is selected. Data from various previous trips are combined to create a simulation data set for the travel route. This data is based on actual vehicle data. This can enable a new level of accuracy for data analysis and simulations based on this data as compared with purely simulated data. Actual vehicle data accounts for driver behavior, road obstacles, signage, vegetation, vehicle characteristics, and other factors that may not be able to be captured with purely simulated traffic data. Using the data generated by disclosed embodiments enables these factors to be considered in traffic analysis.
1. A computer-implemented method for generating travel data for simulation of a travel route, comprising the steps of:
obtaining past-travel data of vehicles;
classifying the past-travel data into a plurality of travel fragments, the travel fragments being data readings from sections of paths historically traveled by one or more of the vehicles;
performing segmentation on the travel route to be simulated to obtain a plurality of route segments corresponding to the travel route, the route segments being sections of the travel route to be simulated;
identifying travel fragments that match route segments from the plurality of route segments;
identifying unmatched route segments from the plurality of route segments that do not match any travel fragment;
identifying proxy travel fragments that correspond to one or more of the identified unmatched route segments, identifying each proxy travel fragment comprising:
selecting from the plurality of travel fragments a travel fragment that does not overlay a particular one of the unmatched route segments, but has characteristics that allow the selected travel fragment to serve as a substitute for a missing travel fragment that would match that particular unmatched route segment;
combining the matched travel fragments and the proxy travel fragments to create a simulation data set for the travel route;
performing a reverse playback of the simulation data set for the travel route to generate a wrong-way simulation data set;
performing a topographical compensation on the wrong-way simulation data set to create a topographically compensated wrong-way simulation data set; and
determining a safety implication of a change in a condition on the travel route based on the simulation data set and the wrong-way simulation data set.
2. The method of claim 1 , further comprising filtering past-travel data based on road type prior to classifying the past-travel data into a plurality of travel fragments.
3. The method of claim 1 , wherein obtaining the past-travel data includes obtaining geolocation data.
4. The method of claim 1 , wherein obtaining the past-travel data includes obtaining a navigation device type.
5. The method of claim 1 , wherein obtaining the past-travel data includes obtaining a vehicle model.
6. The method of claim 1 , further comprising filtering past-travel data based on vehicle class prior to classifying the past-travel data into a plurality of travel fragments.
7. The method of claim 1 , wherein the characteristics comprise at least one feature selected from the group consisting of: a geographic proximity to the unmatched route segment, approximately a same length as the unmatched route segment, and endpoints in proximity to endpoints of the unmatched route segment.
8. The method of claim 1 , further comprising filtering past-travel data based on traffic conditions and weather conditions prior to classifying the past-travel data into a plurality of travel fragments.
9. The method of claim 1 , wherein obtaining the past-travel data includes obtaining a driver behavior analysis record, and wherein the driver behavior analysis record includes an indication selected from the group consisting of, a harsh braking indication, a rapid acceleration indication, a harsh steering indication, a curve over-braking indication, and a speeding indication.
10. The method of claim 1 , further comprising:
performing an intrusion path analysis, and:
performing a route interpolation on the wrong-way simulation data set, based on the intrusion path analysis, to create an interpolated wrong-way simulation data set.
11. An electronic computing device comprising:
a processor;
a memory coupled to the processor, the memory containing instructions, that when executed by the processor, perform the steps of:
obtaining past-travel data of vehicles;
classifying the past-travel data into a plurality of travel fragments, the travel fragments being data readings from sections of paths historically traveled by one or more of the vehicles;
performing segmentation on the travel route to be simulated to obtain a plurality of route segments corresponding to a travel route, the route segments being sections of the travel route to be simulated;
identifying travel fragments that match route segments from the plurality of route segments;
identifying unmatched route segments from the plurality of route segments that do not match any travel fragment;
identifying proxy travel fragments that correspond to one or more of the identified unmatched route segments, identifying each proxy travel fragment comprising:
selecting from the plurality of travel fragments a travel fragment that does not overlay a particular one of the unmatched route segments, but has characteristics that allow the selected travel fragment to serve as a substitute for a missing travel fragment that would match that particular unmatched route segment;
combining the matched travel fragments and the proxy travel fragments to create a simulation data set for the travel route;
performing a reverse playback of the simulation data set for the travel route to generate a wrong-way simulation data set;
performing a topographical compensation on the wrong-way simulation data set to create a topographically compensated wrong-way simulation data set; and
determining a safety implication of a change in a condition on the travel route based on the simulation data set and the wrong-way simulation data set.
12. The electronic computing device of claim 11 , wherein the memory further comprises instructions, that when executed by the processor, perform the step of filtering past-travel data based on vehicle class prior to classifying the past-travel data into a plurality of travel fragments.
13. The electronic computing device of claim 11 , wherein the memory further comprises instructions, that when executed by the processor, perform the step of performing an intrusion path analysis, and:
performing a route interpolation on the wrong-way simulation data set, based on the intrusion path analysis, to create an interpolated wrong-way simulation data set.
14. A computer program product for an electronic computing device comprising a non-transitory computer readable storage medium having program instructions embodied therewith, the program instructions executable by a processor to cause the electronic computing device to:
obtain past-travel data of vehicles;
classify the past-travel data into a plurality of travel fragments, the travel fragments being data readings from sections of paths historically traveled by one or more of the vehicles;
perform segmentation on the travel route to be simulated to obtain a plurality of route segments corresponding to a travel route, the route segments being sections of the travel route to be simulated;
identify travel fragments that match route segments from the plurality of route segments;
identify unmatched route segments from the plurality of route segments that do not match any travel fragment;
identify proxy travel fragments that correspond to one or more of the identified unmatched route segments, the identifying each proxy travel fragment further comprising:
selecting from the plurality of travel fragments a travel fragment that does not overlay a particular one of the unmatched route segments, but has characteristics that allow the selected travel fragment to serve as a substitute for a missing travel fragment that would match that particular unmatched route segment;
combine the matched travel fragments and the proxy travel fragments to create a simulation data set for the travel route;
perform a reverse playback of the simulation data set for the travel route to generate a wrong-way simulation data set;
perform a topographical compensation on the wrong-way simulation data set to create a topographically compensated wrong-way simulation data set; and
determine a safety implication of a change in a condition on the travel route based on the simulation data set and the wrong-way simulation data set.
15. The computer program product of claim 14 , wherein the non-transitory computer readable storage medium includes program instructions executable by the processor to cause the electronic computing device to:
perform an intrusion path analysis, and:
perform a route interpolation on the wrong-way simulation data set, based on the intrusion path analysis, to create an interpolated wrong-way simulation data set.