Deployment of OTA-Upgradable Teammate Advanced Drive
- 提供方法
- 版元よりダウンロードリンクを連絡
- 形態
- 価格
- 一般価格(税込)：￥6,600 会員価格(税込)：￥5,280
- 文献・情報種別
- SAE Paper
No.2022-01-0063
- 掲載ページ
- 1-10(Total 10 p)
- 発行年月
- 2022年 3月
- 出版社
- SAE International
- 言語
- 英語
- イベント
- WCX SAE World Congress Experience 2022
書誌事項
| 著者（英） | 1) Tomoya Kawasaki, 2) Kaiji Itabashi, 3) Derek Caveney, 4) Masaki Kitago, 5) Yuichiro Nara, 6) Takashi Oda |
|---|---|
| 勤務先（英） | 1) Toyota Motor Corporation, 2) Woven Core, Inc., 3) Toyota Motor North America, Inc., 4) Woven Core, Inc., 5) Woven Core, Inc., 6) Toyota Motor Corporation |
| 抄録（英） | Teammate Advanced Drive is a driving support system with state-of-the-art automated driving technology that has been developed for customers’ safe and secure driving on highways based on the Toyota’s Mobility Teammate Concept. This SAE Level 2 (L2) system assists overtaking, lane changes, and branching to the destination, in addition to providing hands-free lane centering and car following. The automated driving technology includes self-localization onto a High Definition Map, multi-modal sensing to cover 360 degrees of the surrounding environment using fusion of LiDARs, cameras, and radars, and a redundant architecture to realize fail-safe operation when a malfunction or system limitation occurs. High-performance computing is provided to implement deep learning for predicting and responding to various situations that may be encountered while driving. The system also includes digital data uploading and downloading capabilities wirelessly over-the-air (OTA) in order to provide customers new software features and upgraded performance as well as the latest map updates. Utilizing the OTA updates, the automated driving technology has progressed and delivered several new intelligent features to customers. Examples of new features delivered by OTA include lane maker detection by Deep Neural Networks (DNN) that provide enhanced positive detection and reduced false detection compared to conventional edge detection methods, resulting in better localization performance. Also, DNN for turn signal detection is introduced to react to a cut-in vehicle at an early stage while it is still inside the adjacent lane. A final example is emergency braking performance has been enhanced by introducing an overlap ratio detection with dynamic pitching estimation. 翻訳 |
