中文
相关论文

相关论文: See, Point, Fly: A Learning-Free VLM Framework for…

200 篇论文

Unmanned aerial vehicles (UAVs) are crucial tools for post-disaster search and rescue, facing challenges such as high information density, rapid changes in viewpoint, and dynamic structures, especially in long-horizon navigation. However,…

计算机视觉与模式识别 · 计算机科学 2025-12-29 Wen Jiang , Li Wang , Kangyao Huang , Wei Fan , Jinyuan Liu , Shaoyu Liu , Hongwei Duan , Bin Xu , Xiangyang Ji

Full autonomy for fixed-wing unmanned aerial vehicles (UAVs) requires the capability to autonomously detect potential landing sites in unknown and unstructured terrain, allowing for self-governed mission completion or handling of emergency…

机器人学 · 计算机科学 2018-02-27 Timo Hinzmann , Thomas Stastny , Cesar Cadena , Roland Siegwart , Igor Gilitschenski

While natural language is commonly used to guide embodied agents, the inherent ambiguity and verbosity of language often hinder the effectiveness of language-guided navigation in complex environments. To this end, we propose Visual Prompt…

计算机视觉与模式识别 · 计算机科学 2025-11-25 Shuo Feng , Zihan Wang , Yuchen Li , Rui Kong , Hengyi Cai , Shuaiqiang Wang , Gim Hee Lee , Piji Li , Shuqiang Jiang

The integration of language instructions with robotic control, particularly through Vision Language Action (VLA) models, has shown significant potential. However, these systems are often hindered by high computational costs, the need for…

机器人学 · 计算机科学 2025-02-04 Marie Samson , Bastien Muraccioli , Fumio Kanehiro

Autonomous navigation guided by natural language instructions is essential for improving human-robot interaction and enabling complex operations in dynamic environments. While large language models (LLMs) are not inherently designed for…

机器人学 · 计算机科学 2024-12-04 Pranav Doma , Aliasghar Arab , Xuesu Xiao

This paper presents a vision-only autonomous flight system for small UAVs operating in controlled indoor environments. The system combines semantic segmentation with monocular depth estimation to enable obstacle avoidance, scene…

计算机视觉与模式识别 · 计算机科学 2025-10-21 Sebastian Mocanu , Emil Slusanschi , Marius Leordeanu

In modern smart agriculture, object detection plays a crucial role by enabling automation, precision farming, and monitoring of resources. From identifying crop health and pest infestations to optimizing harvesting processes, accurate…

计算机视觉与模式识别 · 计算机科学 2025-10-22 Long Li , Jiajia Li , Dong Chen , Lina Pu , Haibo Yao , Yanbo Huang

As a long-term vision in the field of artificial intelligence, the core goal of embodied intelligence is to improve the perception, understanding, and interaction capabilities of agents and the environment. Vision-language navigation (VLN),…

机器人学 · 计算机科学 2024-03-21 Peng Gao , Peng Wang , Feng Gao , Fei Wang , Ruyue Yuan

Unmanned aerial vehicles (UAVs) have emerged as powerful embodied agents. One of the core abilities is autonomous navigation in large-scale three-dimensional environments. Existing navigation policies, however, are typically optimized for…

In the Vision-and-Language Navigation (VLN) task, the agent is required to navigate to a destination following a natural language instruction. While learning-based approaches have been a major solution to the task, they suffer from high…

人工智能 · 计算机科学 2024-08-13 Zhaohuan Zhan , Lisha Yu , Sijie Yu , Guang Tan

A visually-grounded navigation instruction can be interpreted as a sequence of expected observations and actions an agent following the correct trajectory would encounter and perform. Based on this intuition, we formulate the problem of…

计算机视觉与模式识别 · 计算机科学 2019-11-27 Peter Anderson , Ayush Shrivastava , Devi Parikh , Dhruv Batra , Stefan Lee

Humans can collaborate and complete tasks based on visual signals and instruction from the environment. Training such a robot is difficult especially due to the understanding of the instruction and the complicated environment. Previous…

人工智能 · 计算机科学 2023-05-12 Kairui Zhou

Autonomous navigation in highly constrained environments remains challenging for mobile robots. Classical navigation approaches offer safety assurances but require environment-specific parameter tuning; end-to-end learning bypasses…

机器人学 · 计算机科学 2026-03-11 Yuanjie Lu , Beichen Wang , Zhengqi Wu , Yang Li , Xiaomin Lin , Chengzhi Mao , Xuesu Xiao

Vision-language navigation (VLN), which entails an agent to navigate 3D environments following human instructions, has shown great advances. However, current agents are built upon panoramic observations, which hinders their ability to…

计算机视觉与模式识别 · 计算机科学 2023-08-15 Rui Liu , Xiaohan Wang , Wenguan Wang , Yi Yang

Humans have a natural ability to perform semantic associations with the surrounding objects in the environment. This allows them to create a mental map of the environment, allowing them to navigate on-demand when given linguistic…

Zero-shot object navigation requires agents to locate unseen target objects in unfamiliar environments without prior maps or task-specific training which remains a significant challenge. Although recent advancements in vision-language…

机器人学 · 计算机科学 2026-04-08 Feng Wu , Wei Zuo , Wenliang Yang , Jun Xiao , Yang Liu , Xinhua Zeng

The task of vision-and-language navigation in continuous environments (VLN-CE) aims at training an autonomous agent to perform low-level actions to navigate through 3D continuous surroundings using visual observations and language…

机器人学 · 计算机科学 2024-12-30 Lu Yue , Dongliang Zhou , Liang Xie , Feitian Zhang , Ye Yan , Erwei Yin

Following language instructions to navigate in unseen environments is a challenging task for autonomous embodied agents. With strong representation capabilities, pretrained vision-and-language models are widely used in VLN. However, most of…

计算机视觉与模式识别 · 计算机科学 2024-01-01 Ting Liu , Yue Hu , Wansen Wu , Youkai Wang , Kai Xu , Quanjun Yin

Vision-language models (VLMs) have recently emerged as powerful representation learning systems that align visual observations with natural language concepts, offering new opportunities for semantic reasoning in safety-critical autonomous…

计算机视觉与模式识别 · 计算机科学 2026-02-19 Ross Greer , Maitrayee Keskar , Angel Martinez-Sanchez , Parthib Roy , Shashank Shriram , Mohan Trivedi

Vision-and-Language Navigation (VLN) task aims to enable AI agents to accurately understand and follow natural language instructions to navigate through real-world environments, ultimately reaching specific target locations. We recognise a…

计算机视觉与模式识别 · 计算机科学 2023-12-27 Qi Chen , Dileepa Pitawela , Chongyang Zhao , Gengze Zhou , Hsiang-Ting Chen , Qi Wu