paper-with-me

홈 › Papers

Vision-based Navigation with Language-based Assistance via Imitation Learning with Indirect Intervention

2018-12-10 · CVPR 2019 6 · Khanh Nguyen, Debadeepta Dey, Chris Brockett, Bill Dolan

We present Vision-based Navigation with Language-based Assistance (VNLA), a grounded vision-language task where an agent with visual perception is guided via language to find objects in photorealistic indoor environments. The task emulates a real-world scenario in that (a) the requester may not know how to navigate to the target objects and thus makes requests by only specifying high-level end-goals, and (b) the agent is capable of sensing when it is lost and querying an advisor, who is more qualified at the task, to obtain language subgoals to make progress. To model language-based assistance, we develop a general framework termed Imitation Learning with Indirect Intervention (I3L), and propose a solution that is effective on the VNLA task. Empirical results show that this approach significantly improves the success rate of the learning agent over other baselines in both seen and unseen environments. Our code and data are publicly available at https://github.com/debadeepta/vnla .

📄 PDF Abstract BibTeX arXiv:1812.04155

Code (1)

debadeepta/vnla 공식 구현 pytorch

Tasks

Imitation LearningNavigateVision-based navigation with language-based assistanceVNLA

Similar Papers 제목 키워드 기반

Exploring the Use of VLMs for Navigation Assistance for People with Blindness and Low Vision

2026-01-26 · Yu Li, Yuchen Zheng, Giles Hamilton-Fletcher, Marco Mezzavilla 외 arxiv

This paper investigates the potential of vision-language models (VLMs) to assist people with blindness and low vision (pBLV) in navigation tasks. We evaluate state-of-the-art closed-source models, including GPT-4V, GPT-4…

Scene UnderstandingSpatial Reasoning

Fine-Tuning Vision-Language Models for Visual Navigation Assistance

2025-09-09 · Xiao Li, Bharat Gandhi, Ming Zhan, Mohit Nehra 외 arxiv

We address vision-language-driven indoor navigation to assist visually impaired individuals in reaching a target location using images and natural language guidance. Traditional navigation systems are ineffective indoors…

Visual Navigation

VisionGPT: LLM-Assisted Real-Time Anomaly Detection for Safe Visual Navigation

2024-03-19 · Hao Wang, Jiayou Qin, Ashish Bastola, Xiwen Chen 외

This paper explores the potential of Large Language Models(LLMs) in zero-shot anomaly detection for safe visual navigation. With the assistance of the state-of-the-art real-time open-world object detection model Yolo-Wor…

Anomaly Detectionobject-detectionObject DetectionOpen-vocabulary object detection+5

Help, Anna! Visual Navigation with Natural Multimodal Assistance via Retrospective Curiosity-Encouraging Imitation Learning

2019-09-04 · IJCNLP 2019 11 · Khanh Nguyen, Hal Daumé III

Mobile agents that can leverage help from humans can potentially accomplish more complex tasks than they could entirely on their own. We develop "Help, Anna!" (HANNA), an interactive photo-realistic simulator in which an…

Decision MakingImitation LearningVisual Navigation

Ordinal Neural Collapse as a Representation Prior for Visual Navigation

2026-06-25 · E-In Son, Jung-Taak Kim, Seung-Woo Seo arxiv

Learning robust navigation policies directly from visual observations remains a fundamental challenge in vision-based robotic navigation. In end-to-end imitation learning approaches, the visual encoder and action decoder…

Visual Navigation