中文
相关论文

相关论文: PIG-Nav: Key Insights for Pretrained Image Goal Na…

200 篇论文

Object Navigation (ObjectNav) is a fundamental task in embodied artificial intelligence. Although significant progress has been made in semantic map construction and target direction prediction in current research, redundant exploration and…

计算机视觉与模式识别 · 计算机科学 2025-06-04 Junjie Li , Nan Zhang , Xiaoyang Qu , Kai Lu , Guokuan Li , Jiguang Wan , Jianzong Wang

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

Recent embodied navigation approaches leveraging Vision-Language Models (VLMs) demonstrate strong generalization in versatile Vision-Language Navigation (VLN). However, reliable path planning in complex environments remains challenging due…

机器人学 · 计算机科学 2026-03-11 Jiahang Liu , Tianyu Xu , Jiawei Chen , Lu Yue , Jiazhao Zhang , Zhiyong Wang , Minghan Li , Qisheng Zhao , Anqi Li , Qi Su , Zhizheng Zhang , He Wang

UAV vision-language navigation (VLN) requires an agent to navigate complex 3D environments from an egocentric perspective while following ambiguous multi-step instructions over long horizons. Existing zero-shot methods remain limited, as…

计算机视觉与模式识别 · 计算机科学 2026-04-20 Dian Shao , Zhengzheng Xu , Peiyang Wang , Like Liu , Yule Wang , Jieqi Shi , Jing Huo

How can we build general-purpose robot systems for open-world semantic navigation, e.g., searching a novel environment for a target object specified in natural language? To tackle this challenge, we introduce OSG Navigator, a modular system…

机器人学 · 计算机科学 2025-08-07 Joel Loo , Zhanxin Wu , David Hsu

Embodied navigation holds significant promise for real-world applications such as last-mile delivery. However, most existing approaches are confined to either indoor or outdoor environments and rely heavily on strong assumptions, such as…

计算机视觉与模式识别 · 计算机科学 2026-02-09 Yuxiang Zhao , Yirong Yang , Yanqing Zhu , Yanfen Shen , Chiyu Wang , Zhining Gu , Pei Shi , Wei Guo , Mu Xu

The objective in this paper is to improve the performance of text-to-image retrieval. To this end, we introduce a new framework that can boost the performance of large-scale pre-trained vision-language models, so that they can be used for…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Guanqi Zhan , Yuanpei Liu , Kai Han , Weidi Xie , Andrew Zisserman

Autonomous navigation based on precise localization has been widely developed in both academic research and practical applications. The high demand for localization accuracy has been essential for safe robot planing and navigation while it…

机器人学 · 计算机科学 2019-06-07 Huifang Ma , Yue Wang , Li Tang , Sarath Kodagoda , Rong Xiong

Recent vision transformer based video models mostly follow the ``image pre-training then finetuning" paradigm and have achieved great success on multiple video benchmarks. However, full finetuning such a video model could be computationally…

计算机视觉与模式识别 · 计算机科学 2023-02-07 Taojiannan Yang , Yi Zhu , Yusheng Xie , Aston Zhang , Chen Chen , Mu Li

2D top-down maps are commonly used for the navigation and exploration of mobile robots through unknown areas. Typically, the robot builds the navigation maps incrementally from local observations using onboard sensors. Recent works have…

机器人学 · 计算机科学 2024-03-27 Vishnu Dutt Sharma , Anukriti Singh , Pratap Tokekar

Learning to navigate in a visual environment following natural-language instructions is a challenging task, because the multimodal inputs to the agent are highly variable, and the training data on a new task is often limited. In this paper,…

计算机视觉与模式识别 · 计算机科学 2020-04-07 Weituo Hao , Chunyuan Li , Xiujun Li , Lawrence Carin , Jianfeng Gao

Visual target navigation is a critical capability for autonomous robots operating in unknown environments, particularly in human-robot interaction scenarios. While classical and learning-based methods have shown promise, most existing…

机器人学 · 计算机科学 2025-05-07 Bangguo Yu , Qihao Yuan , Kailai Li , Hamidreza Kasaei , Ming Cao

Navigating complex indoor environments requires a deep understanding of the space the robotic agent is acting into to correctly inform the navigation process of the agent towards the goal location. In recent learning-based navigation…

机器人学 · 计算机科学 2023-10-05 Marco Rosano , Antonino Furnari , Luigi Gulino , Corrado Santoro , Giovanni Maria Farinella

Zero-shot object-goal navigation aims to find target objects in unseen environments using only egocentric observation. Recent methods leverage foundation models' comprehension and reasoning capabilities to enhance navigation performance.…

计算机视觉与模式识别 · 计算机科学 2026-03-20 Leyuan Fang , Zan Mao , Zijing Wang , Yinlong Yan

Existing image-to-image transformation approaches primarily focus on synthesizing visually pleasing data. Generating images with correct identity labels is challenging yet much less explored. It is even more challenging to deal with image…

计算机视觉与模式识别 · 计算机科学 2020-06-16 Wei Xiong , Yutong He , Yixuan Zhang , Wenhan Luo , Lin Ma , Jiebo Luo

Existing research studies on vision and language grounding for robot navigation focus on improving model-free deep reinforcement learning (DRL) models in synthetic environments. However, model-free DRL models do not consider the dynamics in…

计算机视觉与模式识别 · 计算机科学 2018-07-27 Xin Wang , Wenhan Xiong , Hongmin Wang , William Yang Wang

Mobile robots exploring indoor environments increasingly rely on vision-language models to perceive high-level semantic cues in camera images, such as object categories. Such models offer the potential to substantially advance robot…

机器人学 · 计算机科学 2025-10-09 Utkarsh Bajpai , Julius Rückin , Cyrill Stachniss , Marija Popović

Image-goal navigation steers an agent to a target location specified by an image in unseen environments. Existing methods primarily handle this task by learning an end-to-end navigation policy, which compares the similarities of target and…

机器人学 · 计算机科学 2026-04-21 Pengna Li , Kangyi Wu , Shaoqing Xu , Fang Li , Lin Zhao , Long Chen , Zhi-Xin Yang , Nanning Zheng

Navigation is a fundamental capability for mobile robots. While the current trend is to use learning-based approaches to replace traditional geometry-based methods, existing end-to-end learning-based policies often struggle with 3D spatial…

机器人学 · 计算机科学 2026-01-21 Wangtian Shen , Ziyang Meng , Jinming Ma , Mingliang Zhou , Diyun Xiang

Recent works have shown that large models pretrained on common visual learning tasks can provide useful representations for a wide range of specialized perception problems, as well as a variety of robotic manipulation tasks. While prior…

机器学习 · 计算机科学 2023-04-14 Mohit Sharma , Claudio Fantacci , Yuxiang Zhou , Skanda Koppula , Nicolas Heess , Jon Scholz , Yusuf Aytar