VTrackIt: A Synthetic Self-Driving Dataset with Infrastructure and Pooled Vehicle Information

TL;DR

VTrackIt is a synthetic dataset that includes infrastructure and pooled vehicle data, enabling improved trajectory prediction for autonomous vehicles and reducing high-risk edge cases.

Contribution

It introduces the first comprehensive synthetic dataset with infrastructure and pooled vehicle info, and a deep learning model (InfraGAN) utilizing this data for better trajectory prediction.

Findings

InfraGAN reduces high-risk edge cases in trajectory prediction

VTrackIt dataset enhances AV training with infrastructure data

Synthetic data complements real datasets for AV safety improvements

Abstract

Artificial intelligence solutions for Autonomous Vehicles (AVs) have been developed using publicly available datasets such as Argoverse, ApolloScape, Level5, and NuScenes. One major limitation of these datasets is the absence of infrastructure and/or pooled vehicle information like lane line type, vehicle speed, traffic signs, and intersections. Such information is necessary and not complementary to eliminating high-risk edge cases. The rapid advancements in Vehicle-to-Infrastructure and Vehicle-to-Vehicle technologies show promise that infrastructure and pooled vehicle information will soon be accessible in near real-time. Taking a leap in the future, we introduce the first comprehensive synthetic dataset with intelligent infrastructure and pooled vehicle information for advancing the next generation of AVs, named VTrackIt. We also introduce the first deep learning model (InfraGAN) for trajectory predictions that considers such information. Our experiments with InfraGAN show that the comprehensive information offered by VTrackIt reduces the number of high-risk edge cases. The VTrackIt dataset is available upon request under the Creative Commons CC BY-NC-SA 4.0 license at http://vtrackit.irda.club.