In the field of autonomous vehicles (AVs), accurately discerning commander intent and
executing linguistic commands within a visual context presents a significant challenge. This …

We investigate the Vision-and-Language Navigation (VLN) problem in the context of
autonomous driving in outdoor settings. We solve the problem by explicitly grounding the …

Referring image segmentation aims to segment the instance corresponding to the given
language description, which requires aligning information from two modalities. Existing …

In this study, we develop a model that enables mobilities to have more friendly interactions
with users. Specifically, we focus on the referring navigable regions task in which a model …

Existing Vision-Language models (VLMs) estimate either long-term trajectory waypoints or a
set of control actions as a reactive solution for closed-loop planning based on their rich …

Autonomous driving requires efficient reasoning about the location and appearance of the
different agents in the scene, which aids in downstream tasks such as object detection …

Recent advancement of vehicle automation technology is expected to improve the
interaction between human and mobility modes. As the promising means, language …

抄録 本研究では, 画像, ナビゲーション指示, セマンティックセグメンテーションマスクの 3
つのモダリティを扱うことができる Trimodal Navigable Region Segmentation Model (TNRSM) …