中文
相关论文

相关论文: NavHint: Vision and Language Navigation Agent with…

200 篇论文

Visual navigation in unknown environments based solely on natural language descriptions is a key capability for intelligent robots. In this work, we propose a navigation framework built upon off-the-shelf Visual Language Models (VLMs),…

机器人学 · 计算机科学 2025-08-08 Weifan Zhang , Tingguang Li , Yuzhen Liu

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

Agent systems powered by large language models (LLMs) have demonstrated impressive performance on repository-level code-generation tasks. However, for tasks such as website codebase generation, which depend heavily on visual effects and…

计算与语言 · 计算机科学 2025-09-29 Zimu Lu , Houxing Ren , Yunqiao Yang , Ke Wang , Zhuofan Zong , Junting Pan , Mingjie Zhan , Hongsheng Li

Recent advances in Generative AI have transformed how users interact with data analysis through natural language interfaces. However, many systems rely too heavily on LLMs, creating risks of hallucination, opaque reasoning, and reduced user…

人机交互 · 计算机科学 2025-09-04 Ratanond Koonchanok , Alex Kale , Khairi Reda

Navigating unfamiliar environments presents significant challenges for blind and low-vision (BLV) individuals. In this work, we construct a dataset of images and goals across different scenarios such as searching through kitchens or…

计算与语言 · 计算机科学 2024-07-12 Zain Merchant , Abrar Anwar , Emily Wang , Souti Chattopadhyay , Jesse Thomason

Image-goal navigation aims to steer an agent towards the goal location specified by an image. Most prior methods tackle this task by learning a navigation policy, which extracts visual features of goal and observation images, compares their…

计算机视觉与模式识别 · 计算机科学 2025-02-18 Pengna Li , Kangyi Wu , Jingwen Fu , Sanping Zhou

Visual navigation for autonomous agents is a core task in the fields of computer vision and robotics. Learning-based methods, such as deep reinforcement learning, have the potential to outperform the classical solutions developed for this…

计算机视觉与模式识别 · 计算机科学 2021-03-23 Zachary Seymour , Kowshik Thopalli , Niluthpol Mithun , Han-Pang Chiu , Supun Samarasekera , Rakesh Kumar

Vision-and-Language Navigation (VLN) requires an embodied agent to navigate in a complex 3D environment according to natural language instructions. Recent progress in large language models (LLMs) has enabled language-driven navigation with…

机器人学 · 计算机科学 2026-01-27 Zijun Li , Shijie Li , Zhenxi Zhang , Bin Li , Shoujun Zhou

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

Visual navigation is often cast as a reinforcement learning (RL) problem. Current methods typically result in a suboptimal policy that learns general obstacle avoidance and search behaviours. For example, in the target-object navigation…

计算机视觉与模式识别 · 计算机科学 2021-03-02 Mahdi Kazemi Moghaddam , Ehsan Abbasnejad , Qi Wu , Javen Shi , Anton Van Den Hengel

Computational thinking, and by extension, computer programming, is notoriously challenging to learn. Conversational agents and generative artificial intelligence (genAI) have the potential to facilitate this learning process by offering…

人机交互 · 计算机科学 2024-06-17 Jacob Penney , João Felipe Pimentel , Igor Steinmacher , Marco A. Gerosa

We present the Frontier Aware Search with backTracking (FAST) Navigator, a general framework for action decoding, that achieves state-of-the-art results on the Room-to-Room (R2R) Vision-and-Language navigation challenge of Anderson et. al.…

计算与语言 · 计算机科学 2019-04-03 Liyiming Ke , Xiujun Li , Yonatan Bisk , Ari Holtzman , Zhe Gan , Jingjing Liu , Jianfeng Gao , Yejin Choi , Siddhartha Srinivasa

Autonomous driving systems have made significant advances in Q&A, perception, prediction, and planning based on local visual information, yet they struggle to incorporate broader navigational context that human drivers routinely utilize. We…

机器人学 · 计算机科学 2025-11-04 Qucheng Peng , Chen Bai , Guoxiang Zhang , Bo Xu , Xiaotong Liu , Xiaoyin Zheng , Chen Chen , Cheng Lu

Vision-Language Navigation (VLN) tasks require an agent to follow human language instructions to navigate in previously unseen environments. This challenging field involving problems in natural language processing, computer vision,…

计算机视觉与模式识别 · 计算机科学 2022-04-05 Wansen Wu , Tao Chang , Xinmeng Li

Model based reinforcement learning has proven to be more sample efficient than model free methods. On the other hand, the construction of a dynamics model in model based reinforcement learning has increased complexity. Data processing tasks…

天体物理仪器与方法 · 物理学 2023-01-11 Sarod Yatawatta

Web agents struggle to adapt to new websites due to the scarcity of environment specific tasks and demonstrations. Recent works have explored synthetic data generation to address this challenge, however, they suffer from data quality issues…

Two key challenges within Reinforcement Learning involve improving (a) agent learning within environments with sparse extrinsic rewards and (b) the explainability of agent actions. We describe a curious subgoal focused agent to address both…

机器学习 · 计算机科学 2021-04-20 Connor van Rossum , Candice Feinberg , Adam Abu Shumays , Kyle Baxter , Benedek Bartha

Vision-and-Language Navigation (VLN) tasks such as Room-to-Room (R2R) require machine agents to interpret natural language instructions and learn to act in visually realistic environments to achieve navigation goals. The overall task…

计算机视觉与模式识别 · 计算机科学 2019-08-14 Haoshuo Huang , Vihan Jain , Harsh Mehta , Alexander Ku , Gabriel Magalhaes , Jason Baldridge , Eugene Ie

Humans routinely leverage semantic hints provided by signage to navigate to destinations within novel Large-Scale Indoor (LSI) environments, such as hospitals and airport terminals. However, this capability remains underexplored within the…

机器人学 · 计算机科学 2026-03-18 Jian Sun , Yuming Huang , He Li , Shuqi Xiao , Shenyan Guo , Maani Ghaffari , Qingbiao Li , Chengzhong Xu , Hui Kong

When deployed, AI agents will encounter problems that are beyond their autonomous problem-solving capabilities. Leveraging human assistance can help agents overcome their inherent limitations and robustly cope with unfamiliar situations. We…

机器学习 · 计算机科学 2022-06-24 Khanh Nguyen , Yonatan Bisk , Hal Daumé