中文
相关论文

相关论文: POINav: Benchmarking and Enhancing Final-Meters Ar…

200 篇论文

Vision-Language Navigation (VLN) is evolving from single-point pathfinding toward the more challenging Multi-Goal VLN. This task requires agents to accurately identify multiple entities while collaboratively reasoning over their…

人工智能 · 计算机科学 2026-03-05 Ling Luo , Qiangian Bai

Answering real-world tourism questions that seek Point-of-Interest (POI) recommendations is challenging, as it requires both spatial and non-spatial reasoning, over a large candidate pool. The traditional method of encoding each pair of…

计算与语言 · 计算机科学 2024-01-05 Haonan Li , Martin Tomko , Timothy Baldwin

Vision-and-Language Navigation in Continuous Environments (VLN-CE) is one of the most intuitive yet challenging embodied AI tasks. Agents are tasked to navigate towards a target goal by executing a set of low-level actions, following a…

As multimodal large language models (MLLMs) continue to demonstrate increasingly competitive performance across a broad spectrum of tasks, more intricate and comprehensive benchmarks have been developed to assess these cutting-edge models.…

计算与语言 · 计算机科学 2024-10-10 Haoran Zhang , Hangyu Guo , Shuyue Guo , Meng Cao , Wenhao Huang , Jiaheng Liu , Ge Zhang

For people affected by blindness and low vision (BLV), safe and independent navigation remains a major challenge, impacting over 2.2 billion individuals worldwide. Although multimodal large language models (MLLMs) offer new opportunities…

计算机视觉与模式识别 · 计算机科学 2026-05-01 Junhyeok Kim , Jaewoo Park , Junhee Park , Sangeyl Lee , Jiwan Chung , Jisung Kim , Ji Hoon Joung , Youngjae Yu

Geometric problem solving constitutes a critical branch of mathematical reasoning, requiring precise analysis of shapes and spatial relationships. Current evaluations of geometric reasoning in vision-language models (VLMs) face limitations,…

计算机视觉与模式识别 · 计算机科学 2026-01-01 Yuan Feng , Yue Yang , Xiaohan He , Jiatong Zhao , Jianlong Chen , Zijun Chen , Daocheng Fu , Qi Liu , Renqiu Xia , Bo Zhang , Junchi Yan

Vision-language Navigation (VLN) requires an agent to understand visual observations and language instructions to navigate in unseen environments. Most existing approaches rely on static scene assumptions and struggle to generalize in…

机器人学 · 计算机科学 2026-03-24 Xiangchen Liu , Hanghan Zheng , Jeil Jeong , Minsung Yoon , Lin Zhao , Zhide Zhong , Haoang Li , Sung-Eui Yoon

Vision-Language-Action (VLA) models excel at robotic tasks by leveraging large-scale 2D vision-language pretraining, but their reliance on RGB images limits spatial reasoning critical for real-world interaction. Retraining these models with…

机器人学 · 计算机科学 2025-03-11 Chengmeng Li , Junjie Wen , Yan Peng , Yaxin Peng , Feifei Feng , Yichen Zhu

The emerging vision-and-language navigation (VLN) problem aims at learning to navigate an agent to the target location in unseen photo-realistic environments according to the given language instruction. The main challenges of VLN arise…

计算机视觉与模式识别 · 计算机科学 2020-11-24 Weixia Zhang , Chao Ma , Qi Wu , Xiaokang Yang

In a busy city street, a pedestrian surrounded by distractions can pick out a single sign if it is relevant to their route. Artificial agents in outdoor Vision-and-Language Navigation (VLN) are also confronted with detecting supervisory…

机器学习 · 计算机科学 2022-11-21 Jason Armitage , Leonardo Impett , Rico Sennrich

This paper presents a novel approach to image-goal navigation by integrating 3D Gaussian Splatting (3DGS) with Visual Navigation Models (VNMs), a method we refer to as GSplatVNM. VNMs offer a promising paradigm for image-goal navigation by…

机器人学 · 计算机科学 2025-07-29 Kohei Honda , Takeshi Ishita , Yasuhiro Yoshimura , Ryo Yonetani

Navigation tasks in photorealistic 3D environments are challenging because they require perception and effective planning under partial observability. Recent work shows that map-like memory is useful for long-horizon navigation tasks.…

计算机视觉与模式识别 · 计算机科学 2020-12-08 Saim Wani , Shivansh Patel , Unnat Jain , Angel X. Chang , Manolis Savva

Enabling robotic assistants to navigate complex environments and locate objects described in free-form language is a critical capability for real-world deployment. While foundation models, particularly Vision-Language Models (VLMs), offer…

机器人学 · 计算机科学 2026-04-16 Naoki Yokoyama , Sehoon Ha

Vision-Language Models (VLMs) have made significant progress in explicit instruction-based navigation; however, their ability to interpret implicit human needs (e.g., "I am thirsty") in dynamic urban environments remains underexplored. This…

人工智能 · 计算机科学 2025-12-19 Siqi Wang , Chao Liang , Yunfan Gao , Erxin Yu , Sen Li , Yushi Li , Jing Li , Haofen Wang

Vision-Language Navigation (VLN) requires the agent to follow language instructions to reach a target position. A key factor for successful navigation is to align the landmarks implied in the instruction with diverse visual observations.…

计算机视觉与模式识别 · 计算机科学 2024-06-06 Bingqian Lin , Yunshuang Nie , Ziming Wei , Yi Zhu , Hang Xu , Shikui Ma , Jianzhuang Liu , Xiaodan Liang

Text-goal instance navigation (TGIN) asks an agent to resolve a single, free-form description into actions that reach the correct object instance among same-category distractors. We present \textit{Context-Nav}, which elevates long,…

计算机视觉与模式识别 · 计算机科学 2026-03-19 Won Shik Jang , Ue-Hwan Kim

Training-free Vision-Language Navigation (VLN) agents powered by foundation models can follow instructions and explore 3D environments. However, existing approaches rely on greedy frontier selection and passive spatial memory, leading to…

机器人学 · 计算机科学 2026-04-03 Xueying Li , Feng Lyu , Hao Wu , Mingliu Liu , Jia-Nan Liu , Guozi Liu

Humans excel at forming mental maps of their surroundings, equipping them to understand object relationships and navigate based on language queries. Our previous work, SI Maps (Nanwani L, Agarwal A, Jain K, et al. Instance-level semantic…

计算机视觉与模式识别 · 计算机科学 2025-10-28 Laksh Nanwani , Kumaraditya Gupta , Aditya Mathur , Swayam Agrawal , A. H. Abdul Hafez , K. Madhava Krishna

This works presents a formulation for visual navigation that unifies map based spatial reasoning and path planning, with landmark based robust plan execution in noisy environments. Our proposed formulation is learned from data and is thus…

计算机视觉与模式识别 · 计算机科学 2017-12-22 Saurabh Gupta , David Fouhey , Sergey Levine , Jitendra Malik

Navigating to instance-level targets in complex environments is a challenging problem. Many existing zero-shot methods achieve strong performance by modeling the entire environment and leveraging large language models for scene…

机器人学 · 计算机科学 2026-05-20 Jingyu Li , Zhe Liu , Wenxiao Wu , Li Zhang