Synchronous and Open, Real World, Vehicle, ADAS, and Infrastructure Data Streams for Automotive Machine Learning Algorithms Research 2020-01-0736
Prediction based optimal energy management systems are a topic of high interest in the automotive industry as an effective, low-cost option for improving vehicle fuel efficiency. With the continuing development of connected and autonomous vehicle (CAV) technology there are many data streams which may be leveraged by transportation stakeholders. The Suite of CAVs-derived data streams includes advanced driver-assistance (ADAS) derived information about surrounding vehicles, vehicle-to-vehicle (V2V) communications for real time and historical data, and vehicle-to-infrastructure (V2I) communications. The suite of CAVs-derived data streams have been demonstrated to enable improvements in system-level safety, emissions and fuel economy. Practical concerns, lack of standardization, and current low levels of technology penetration dictate that the acquisition of real-world data for use in the development of optimal energy management systems is challenging and expensive, presenting a bottleneck for research in the subject area. This paper describes the gathering, processing, and use of on-road data collected from probe vehicles in Fort Collins, Colorado. General guidelines are provided for the definition of data streams, and the gathering, and processing of said data. Specific discussion is provided for the several synchronous datasets which were gathered using a test vehicle equipped with sensors to measure ego vehicle position, velocity, and driver and engine data, ADAS-derived near-neighbor relative position and velocity, and infrastructure-level transit time and signal phase and timing information. The processed dataset is made available to the research community. The utility of these data streams are briefly demonstrated by using them in the applications of vehicle velocity prediction.
Citation: Rabinowitz, A., Gaikwad, T., White, S., Bradley, T. et al., "Synchronous and Open, Real World, Vehicle, ADAS, and Infrastructure Data Streams for Automotive Machine Learning Algorithms Research," SAE Technical Paper 2020-01-0736, 2020, https://doi.org/10.4271/2020-01-0736. Download Citation
Aaron I. Rabinowitz, Tushar Gaikwad, Samantha White, Thomas Bradley, Zachary Asher
Colorado State University, Western Michigan University
WCX SAE World Congress Experience
Subscribers can view annotate, and download all of SAE's content.
Learn More »