無人自動駕駛車之「意圖傳達」設計

Design of Autonomous Vehicle Intent Communication

邱國崇(Kuo-Chung Chiu)

指導教授 ： 陳炳宇

共同指導教授 ： 唐玄輝(Hsien-Hui Tang)

國立臺灣大學/管理學院/創業創新管理碩士在職專班/碩士(2019年)

https://doi.org/10.6342/NTU201901614

摘要

本論文研究目的，為設計一個無人自動駕車與用路人的溝通方式，讓用路人瞭解無人自動駕駛車的狀態，提升交通活動效率與安全。該研究先透由質性研究，從人類駕駛與其它人類用路人互動中，找出溝通的意圖種類、使用的信號方式、選擇信號的環境變因。接下來設計意圖與信號對映方式，使用量化研究，把意圖與信號對映的設計透由影片播放，與問卷答題的方式來實行群眾設計，找出用路人對該意圖最佳的認知信號。
最後本研究提出一個「意圖-變因-信號」可擴展資訊架構，把意圖至信號選擇的決策方式系統化，可以讓未來的研究者可以在發展新的意圖與信號使用時，可以根據這樣的指導原則去延伸使用。

關鍵字

無人自動駕駛車 ； 群眾設計 ； 用路人溝通 ； 感知與意圖 ； 汽車信號 ； 人機互動 ； 決策樹

並列摘要

This study aims to provide a design guideline for communication between autonomous vehicles and road users. The guideline can help road users better realize the intents of autonomous vehicles and hence improve the efficiency and safety of road activities. The research was conducted in two parts. In the first stage, we interviewed human drivers to analyze the relationship between the choice of car signals and in-depth intents. The resulting factors lead to a series of intent-signal design, which was evaluated with a large-scale survey study in the second phase. With this Intent-Factor-Signal approach, we propose an extensible architecture of autonomous vehicle signal design. Vehicle designers can choose the signal based on the intent systematically by following the guideline. The research framework also serves as a guide on how to organize and facilitate future research on communication between autonomous vehicles and road users.

並列關鍵字

autonomous vehicle ； crowdsourced design ； road user communication ； perceived awareness and intent ； car signals ； HCI ； decision tree

參考文獻

DARPA. (2004). The Grand Challenge. Retrieved from https://www.darpa.mil/about-us/timeline/-grand-challenge-for-autonomous-vehicles

drive.ai. (2019). drive.ai provides external display panel. Retrieved from https://www.drive.ai/

Lex Fridman, B. M., Lei Xia, Yangyang Yang, Laura Yvonne Facusse, Bryan Reimer. (2017). To Walk or Not to Walk- Crowdsourced Assessment of External Vehicle-to-Pedestrian Displays.

Mahadevan, K., Somanath, S., & Sharlin, E. (2018). Communicating Awareness and Intent in Autonomous Vehicle-Pedestrian Interaction. Paper presented at the Proceedings of the 2018 CHI Conference on Human Factors in Computing Systems - CHI '18.

NHTSA. (2019). Automated Vehicles for Safety. Retrieved from https://www.nhtsa.gov/technology-innovation/automated-vehicles-safety