Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Results and Lessons Learned from Autonomous Driving Transportation Services in Airfield, Crowded Indoor, and Urban Environments

Doosan Baek, Sanghyun Kim, Seung-Woo Seo, Sang-Hyun Lee

TL;DR

The research results and lessons learned from autonomous driving transportation services in airfield, crowded indoor, and urban environments are presented and how to address several unique challenges in these diverse environments are discussed.

Abstract

Autonomous vehicles have been actively investigated over the past few decades. Several recent works show the potential of autonomous vehicles in urban environments with impressive experimental results. However, these works note that autonomous vehicles are still occasionally inferior to expert drivers in complex scenarios. Furthermore, they do not focus on the possibilities of autonomous driving transportation services in other areas beyond urban environments. This paper presents the research results and lessons learned from autonomous driving transportation services in airfield, crowded indoor, and urban environments. We discuss how we address several unique challenges in these diverse environments. We also offer an overview of remaining challenges that have not received much attention but must be addressed. This paper aims to share our unique experience to support researchers who are interested in exploring autonomous driving transportation services in various real-world environments.

Results and Lessons Learned from Autonomous Driving Transportation Services in Airfield, Crowded Indoor, and Urban Environments

TL;DR

The research results and lessons learned from autonomous driving transportation services in airfield, crowded indoor, and urban environments are presented and how to address several unique challenges in these diverse environments are discussed.

Abstract

Autonomous vehicles have been actively investigated over the past few decades. Several recent works show the potential of autonomous vehicles in urban environments with impressive experimental results. However, these works note that autonomous vehicles are still occasionally inferior to expert drivers in complex scenarios. Furthermore, they do not focus on the possibilities of autonomous driving transportation services in other areas beyond urban environments. This paper presents the research results and lessons learned from autonomous driving transportation services in airfield, crowded indoor, and urban environments. We discuss how we address several unique challenges in these diverse environments. We also offer an overview of remaining challenges that have not received much attention but must be addressed. This paper aims to share our unique experience to support researchers who are interested in exploring autonomous driving transportation services in various real-world environments.
Paper Structure (25 sections, 3 equations, 7 figures, 4 tables)

This paper contains 25 sections, 3 equations, 7 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Related Works
  3. Autonomous Driving Transportation Services in Various Challenging Environments
  4. Airfield Environment
  5. Sensor Fusion for Aircraft Detection
  6. Probabilistic Aircraft Intention Prediction
  7. Efficient Occlusion-aware Risk Assessment via Simplified Reachability Quantification
  8. Crowded Indoor Environment
  9. Complex and Narrow Area Collision-free Trajectory Planning
  10. Fail-safe System for Passenger Safety
  11. Urban Environment
  12. Imagination-augmented Hierarchical Reinforcement Learning for Safe and Interactive Motion Planning
  13. Real-time and Accurate Multi-sensor Object Detection
  14. Problems to be Solved
  15. Airfield Environment
  16. ...and 10 more sections

Figures (7)

  • Figure 1: Autonomous driving service area. (a) Airfields: Cincinnati/Northern Kentucky Airport (2.68 km). (b) Crowded indoors: Incheon Airport Terminal 1 (300 m) and Terminal 2 (550 m). (c) Urban: top: from the left, last-mile delivery in Seoul (4.67 km) and testbed in Seoul (8.21 km) and bottom: from the left, shuttle in Sejong (6.12 km), health care service in Gwangju (5.2 km), and road infra monitoring in Hwaseong (15.5 km).
  • Figure 2: Developed autonomous driving platforms. (a) Airfields: tow tractor. (b) Crowded indoors: shuttle (AirRide). (c) Urban: top: from the left, last-mile delivery vehicle (Eligo) and on-demand taxi, and bottom: from the left, health care service vehicle, road infra monitoring vehicle, and shuttle.
  • Figure 3: Overall architecture of the general- and mission-purpose autonomous driving system.
  • Figure 4: Over-segmented aircraft detection results (left) and ours (right).
  • Figure 5: Object detection results in complex urban environments. The cyan, pink, and purple boxes show a vehicle, a pedestrian, and a cyclist, respectively.
  • ...and 2 more figures