Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Human-Like Autonomous Driving on Dense Traffic

Mustafa Yildirim, Saber Fallah

TL;DR

A mixture density network behaviour cloning model is proposed to manage complex and non-linear relationships between inputs and outputs and make more informed decisions about the vehicle's actions to address vulnerability to compounding errors in unseen states and inability to predict outlier driver profiles.

Abstract

This paper proposes a imitation learning model for autonomous driving on highway traffic by mimicking human drivers' driving behaviours. The study utilizes the HighD traffic dataset, which is complex, high-dimensional, and diverse in vehicle variations. Imitation learning is an alternative solution to autonomous highway driving that reduces the sample complexity of learning a challenging task compared to reinforcement learning. However, imitation learning has limitations such as vulnerability to compounding errors in unseen states, poor generalization, and inability to predict outlier driver profiles. To address these issues, the paper proposes mixture density network behaviour cloning model to manage complex and non-linear relationships between inputs and outputs and make more informed decisions about the vehicle's actions. Additional improvement is using collision penalty based on the GAIL model. The paper includes a simulated driving test to demonstrate the effectiveness of the proposed method based on real traffic scenarios and provides conclusions on its potential impact on autonomous driving.

Human-Like Autonomous Driving on Dense Traffic

TL;DR

A mixture density network behaviour cloning model is proposed to manage complex and non-linear relationships between inputs and outputs and make more informed decisions about the vehicle's actions to address vulnerability to compounding errors in unseen states and inability to predict outlier driver profiles.

Abstract

This paper proposes a imitation learning model for autonomous driving on highway traffic by mimicking human drivers' driving behaviours. The study utilizes the HighD traffic dataset, which is complex, high-dimensional, and diverse in vehicle variations. Imitation learning is an alternative solution to autonomous highway driving that reduces the sample complexity of learning a challenging task compared to reinforcement learning. However, imitation learning has limitations such as vulnerability to compounding errors in unseen states, poor generalization, and inability to predict outlier driver profiles. To address these issues, the paper proposes mixture density network behaviour cloning model to manage complex and non-linear relationships between inputs and outputs and make more informed decisions about the vehicle's actions. Additional improvement is using collision penalty based on the GAIL model. The paper includes a simulated driving test to demonstrate the effectiveness of the proposed method based on real traffic scenarios and provides conclusions on its potential impact on autonomous driving.
Paper Structure (12 sections, 5 equations, 5 figures, 1 table)

This paper contains 12 sections, 5 equations, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Model
  3. Simulation Platform
  4. Dataset
  5. Method
  6. Imitation Learning
  7. Mixture Density Network
  8. GAN
  9. GAIL
  10. Augmented Intrinsic Reward GAIL
  11. Analysis & Result
  12. Discussion

Figures (5)

  • Figure 1: HighD traffic data obtained from krajewski2018highd
  • Figure 2: Behavioral cloning model simulation on HighD traffic
  • Figure 3: Mixture Density Network Model
  • Figure 4: Average velocity profile of HighD dataset
  • Figure 5: Average acceleration profile of HighD dataset