Naturalistic Vehicle Speed Profile Generation
Using high level route information, SVTRIP (Stochastic Vehicle TRIp Prediction) generates naturalistic vehicle speed profiles following training on a large datasets of recorded driving data. The workflow includes the following steps:
- End users define a trip on a digital map (e.g. HERE maps) or a travel simulator (e.g. POLARIS), by providing origin, destination, and waypoints
- SVTRIP then extracts a macroscopic definition of the trip with attributes such as speed limit, travel time, road class, and intersection type for each segment of the trip
- SVTRIP sequentially generates a time-indexed speed signal that fits the attributes of each segment
- Data-driven. SVTRIP models how people drive by training on very large databases of recorded driving data. Every transition in speed that occurs in the output has been observed in the real-world dataset. A combination of Markov chains and machine learning is used to train on thousands of hours or real-world driving.
- Naturalistic and Stochastic. The algorithms include the randomness inherently associated with human driving. As a result, the output of multiple runs/generations of SVTRIP with the same route target as an input results in a different result each time. The result is naturalistic, because it is made of speed transitions that actually occurred in the training dataset.
- Route-specific. Each speed profile SVTRIP generates is particular to the route provided as input. For each segment of the route, the algorithm identifies the most relevant subset of data (e.g., high-speed highway driving) and generates a speed trace whose attributes match the target attributes of the segment (e.g., segment distance, initial speed, travel time, speed limit, stop or not at the end).
- Drive cycle generation. When developing and improving powertrains, automotive engineers rely heavily on drive cycles to (1) predict fuel consumption or electric range; (2) predict aging of the components (e.g., batteries or transmission); (3) appropriately size the components of the powertrains; and (4) predict or account for other variables.
- Data-augmentation for mesoscopic travel simulators: SVTRIP is used to generate naturalistic drive cycles from the outputs of POLARIS, enabling linkage with Autonomie as part of the SMART Mobility Workflow
- Generation of speed horizon: a stochastic estimation of future speed can be used by control optimization algorithms to improve energy consumption or other metrics.