- 著者
- Siméon Capy Gentiane Venture Pongsathorn Raksincharoensak
- 出版者
- Society of Automotive Engineers of Japan, INC
- 雑誌
- International Journal of Automotive Engineering (ISSN:21850984)
- 巻号頁・発行日
- vol.14, no.1, pp.10-19, 2023 (Released:2023-01-31)
- 参考文献数
- 66
- 被引用文献数
- 1
ABSTRACT: This article provides a systematic review of research articles on pedestrians and cyclists’ intention recognition to be integrated into autonomous vehicles, especially for decision making and motion planning. We firstly describe why the intention recognition of pedestrians and cyclists is suitable and necessary for autonomous vehicles and why they cannot only rely on traffic regulation laws. Then, we summarise, amongst others, the methodology and sensors used by eighteen peerreviewed research articles published in relevant conferences and journals. We performed a systematic review of articles of the last 10 years from the following databases: IEEE Xplore, Science Direct, ACM digital library, Springer Link, MDPI and Web of Science. We observe from the collected articles that most of them are relying on several sensors, with a predominance including video. They mostly try to obtain the probability of crossing or the trajectory of the pedestrian/cyclist, mostly using a Recurrent Neural Network. In addition to their algorithmic contribution, 4 studies also provide a dataset. We conclude this article by talking about the remaining open challenges.
- 著者
- 加藤 咲季 山野辺 夏樹 Gentiane Venture Gowrishankar Ganesh
- 出版者
- 一般社団法人 日本機械学会
- 雑誌
- ロボティクス・メカトロニクス講演会講演概要集
- 巻号頁・発行日
- vol.2018, pp.2A1-C16, 2018
<p>A good understanding of the handovers between humans is critical for the development of robots in the service industry. In this work, we analyzed the human handover motion to determine to what extent they adapt their handovers to individual partners and whether they can predict the handover positions of a partner. To analyze this issue, motivated by motor control studies, we analyzed handovers by humans in the absence of visual feedback. Our results show that humans have the surprising ability to modulate their handover location according to partners they have just met, and their distance from the partner. The resulting handover errors are relatively small, suggesting that they can predict each other's handover behavior.</p>