Extracting Traffic Primitives Directly from Naturalistically Logged Data for Self-Driving Applications

Abstract

Developing an automated vehicle, that can handle complicated driving scenarios and appropriately interact with other road users, requires the ability to semantically learn and understand driving environment, oftentimes, based on analyzing massive amounts of naturalistic driving data. An important paradigm that allows automated vehicles to both learn from human drivers and gain insights is understanding the principal compositions of the entire traffic, termed as traffic primitives. However, the exploding data growth presents a great challenge in extracting primitives from high-dimensional time-series traffic data with various types of road users engaged. Therefore, automatically extracting primitives is becoming one of the cost-efficient ways to help autonomous vehicles understand and predict the complex traffic scenarios. In addition, the extracted primitives from raw data should 1) be appropriate for automated driving applications and also 2) be easily used to generate new traffic scenarios. However, existing literature does not provide a method to automatically learn these primitives from large-scale traffic data. The contribution of this paper has two manifolds. The first one is that we proposed a new framework to generate new traffic scenarios from a handful of limited traffic data. The second one is that we introduce a nonparametric Bayesian learning method -- a sticky hierarchical Dirichlet process hidden Markov model -- to automatically extract primitives from multidimensional traffic data without prior knowledge of the primitive settings. The developed method is then validated using one day of naturalistic driving data. Experiment results show that the nonparametric Bayesian learning method is able to extract primitives from traffic scenarios where both the binary and continuous events coexist.

7 pages, 8 figures, 2 tables, ICRA 2018

References in corpus (3)

• Modeling the Complex Dynamics and Changing Correlations of Epileptic Events
• Driving Style Analysis Using Primitive Driving Patterns With Bayesian Nonparametric Approaches
• TrafficNet: An Open Naturalistic Driving Scenario Library

Cited by in corpus (18)

• Social Interactions for Autonomous Driving: A Review and Perspectives
• A Deep Learning Framework for Generation and Analysis of Driving Scenario Trajectories
• Spatiotemporal Learning of Multivehicle Interaction Patterns in Lane-Change Scenarios
• How to Evaluate Proving Grounds for Self-Driving? A Quantitative Approach
• A New Multi-vehicle Trajectory Generator to Simulate Vehicle-to-Vehicle Encounters
• Understanding V2V Driving Scenarios through Traffic Primitives
• On the Adversarial Scenario-based Safety Testing of Robots: the Comparability and Optimal Aggressiveness
• A Generic Framework for Clustering Vehicle Motion Trajectories
• Modeling Multi-Vehicle Interaction Scenarios Using Gaussian Random Field
• A Scenario-Based Development Framework for Autonomous Driving
• A Comprehensive Survey of Logging in Software: From Logging Statements Automation to Log Mining and Analysis
• An "Xcity" Optimization Approach to Designing Proving Grounds for Connected and Autonomous Vehicles
• Estimating Risk Levels of Driving Scenarios through Analysis of Driving Styles for Autonomous Vehicles
• A Tempt to Unify Heterogeneous Driving Databases using Traffic Primitives
• Hierarchical Reinforcement Learning Framework towards Multi-agent Navigation
• Energy Efficiency and Emission Testing for Connected and Automated Vehicles Using Real-World Driving Data
• An Accelerated Approach to Safely and Efficiently Test Pre-Production Autonomous Vehicles on Public Streets
• Robust Unsupervised Learning of Temporal Dynamic Interactions