A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters

Abstract

Generating multi-vehicle trajectories from existing limited data can provide rich resources for autonomous vehicle development and testing. This paper introduces a multi-vehicle trajectory generator (MTG) that can encode multi-vehicle interaction scenarios (called driving encounters) into an interpretable representation from which new driving encounter scenarios are generated by sampling. The MTG consists of a bi-directional encoder and a multi-branch decoder. A new disentanglement metric is then developed for model analyses and comparisons in terms of model robustness and the independence of the latent codes. Comparison of our proposed MTG with $\beta$-VAE and InfoGAN demonstrates that the MTG has stronger capability to purposely generate rational vehicle-to-vehicle encounters through operating the disentangled latent codes. Thus the MTG could provide more data for engineers and researchers to develop testing and evaluation scenarios for autonomous vehicles.

arXiv comment6 pages, accepted by ICRA 2019

References in corpus (11)

• Sequence to Sequence Learning with Neural Networks
• Conditional Generative Adversarial Nets
• Progressive Growing of GANs for Improved Quality, Stability, and Variation
• Disentangling by Factorising
• A Neural Representation of Sketch Drawings
• Real-valued (Medical) Time Series Generation with Recurrent Conditional GANs
• Variational Recurrent Auto-Encoders
• Extracting Traffic Primitives Directly from Naturalistically Logged Data for Self-Driving Applications
• DESIRE: Distant Future Prediction in Dynamic Scenes with Interacting Agents
• Incremental Parsing with Minimal Features Using Bi-Directional LSTM
• Naturalistic Driver Intention and Path Prediction using Recurrent Neural Networks

Cited by in corpus (5)

• A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories
• Conditional Generative Neural System for Probabilistic Trajectory Prediction
• Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process
• Learning to Collide: An Adaptive Safety-Critical Scenarios Generating Method
• Multimodal Safety-Critical Scenarios Generation for Decision-Making Algorithms Evaluation