(Travel) time is money! Costing turns, intersections, and ways
summary
A scalable method uses OLS regressions on map‑matched traces (Tokyo and Richmond) to estimate seconds per meter for ways and fixed seconds per intersection or turn. Empirical results: turns can consume ~50% of route time, sample implied bulk speed 26 mph, removing intersections raises implied speed to 45 mph with a ~6 s intersection delay, left turns ~4 s slower, and some residential models push node cost to ~10 s. Outputs are fast to compute and ready for OSRM.
AI-written summary · about
chapters (7)
- 0:00Introduction to turn costing
- 1:56Why turns matter in routing
- 3:19Turn costs in Richmond analysis
- 6:49Global turn cost comparisons
- 7:11Turns versus way costs in trips
- 11:53Modeling road class impacts
- 14:21Key takeaways and conclusions
related talks
13mUtilizing Vehicle Trajectory Data to Characterize Performance Measures of a Highway Corridors
06mReal-time Travel Time Estimation with Sparse Reliable Surveillance Information
45mKEYNOTE: Traffic simulation modeling: combining generative modeling with transportation science ...
42mShould we stop using distance in our location-based data recommendation models?
15mComputational Mobility: Learning, Prediction, and Algorithms
19mSimulation-based origin destination matrix reduction: a case study of Helsinki city area
16mTopology-Preserving Simplification of OpenStreetMap Network Data for Large-scale Simulation in SUMO
20mSimulating platooned connected autonomous vehicle in a large scale urban scenario