English
Related papers

Related papers: Can Vision Foundation Models Navigate? Zero-Shot R…

200 papers

Zero-shot object navigation is a challenging task for home-assistance robots. This task emphasizes visual grounding, commonsense inference and locomotion abilities, where the first two are inherent in foundation models. But for the…

Robotics · Computer Science 2023-09-22 Wenzhe Cai , Siyuan Huang , Guangran Cheng , Yuxing Long , Peng Gao , Changyin Sun , Hao Dong

Vision-and-language navigation (VLN) is a challenging task that requires an agent to navigate in real-world environments by understanding natural language instructions and visual information received in real-time. Prior works have…

Robotics · Computer Science 2021-01-20 Ting Wang , Zongkai Wu , Donglin Wang

Vision-Language Models (VLMs) trained on web-scale corpora excel at natural image tasks and are increasingly repurposed for healthcare; however, their competence in medical tasks remains underexplored. We present a comprehensive evaluation…

Computer Vision and Pattern Recognition · Computer Science 2025-07-21 Che Liu , Jiazhen Pan , Weixiang Shen , Wenjia Bai , Daniel Rueckert , Rossella Arcucci

Navigation is a fundamental skill of agents with visual-motor capabilities. We introduce a Navigation World Model (NWM), a controllable video generation model that predicts future visual observations based on past observations and…

Computer Vision and Pattern Recognition · Computer Science 2025-04-15 Amir Bar , Gaoyue Zhou , Danny Tran , Trevor Darrell , Yann LeCun

High success rates on navigation-related tasks do not necessarily translate into reliable decision making by foundation models. To examine this gap, we evaluate current models on six diagnostic tasks spanning three settings: reasoning under…

Artificial Intelligence · Computer Science 2026-04-09 Jua Han , Jaeyoon Seo , Jungbin Min , Sieun Choi , Huichan Seo , Jihie Kim , Jean Oh

Visual navigation by mobile robots is classically tackled through SLAM plus optimal planning, and more recently through end-to-end training of policies implemented as deep networks. While the former are often limited to waypoint planning,…

Artificial Intelligence · Computer Science 2021-11-30 Assem Sadek , Guillaume Bono , Boris Chidlovskii , Christian Wolf

This paper presents novel benchmarks for evaluating vision-language models (VLMs) in zero-shot recognition, focusing on granularity and specificity. Although VLMs excel in tasks like image captioning, they face challenges in open-world…

Computer Vision and Pattern Recognition · Computer Science 2024-06-19 Zhenlin Xu , Yi Zhu , Tiffany Deng , Abhay Mittal , Yanbei Chen , Manchen Wang , Paolo Favaro , Joseph Tighe , Davide Modolo

Robot navigation in dynamic, human-centered environments requires socially-compliant decisions grounded in robust scene understanding. Recent Vision-Language Models (VLMs) exhibit promising capabilities such as object recognition,…

Navigation is one of the fundamental tasks for automated exploration in Virtual Reality (VR). Existing technologies primarily focus on path optimization in 360-degree image datasets and 3D simulators, which cannot be directly applied to…

Software Engineering · Computer Science 2026-01-07 Xue Qin , Matthew DiGiovanni

Navigating unknown environments with a single RGB camera is challenging, as the lack of depth information prevents reliable collision-checking. While some methods use estimated depth to build collision maps, we found that depth estimates…

Robotics · Computer Science 2025-11-27 Basant Sharma , Prajyot Jadhav , Pranjal Paul , K. Madhava Krishna , Arun Kumar Singh

Hand-drawn maps can be used to convey navigation instructions between humans and robots in a natural and efficient manner. However, these maps can often contain inaccuracies such as scale distortions and missing landmarks which present…

Robotics · Computer Science 2025-04-30 Aaron Hao Tan , Angus Fung , Haitong Wang , Goldie Nejat

Metric ground navigation addresses the problem of autonomously moving a robot from one point to another in an obstacle-occupied planar environment in a collision-free manner. It is one of the most fundamental capabilities of intelligent…

Robotics · Computer Science 2020-11-04 Daniel Perille , Abigail Truong , Xuesu Xiao , Peter Stone

Recent developments in foundation models, like Large Language Models (LLMs) and Vision-Language Models (VLMs), trained on extensive data, facilitate flexible application across different tasks and modalities. Their impact spans various…

Vision language models (VLMs) can simultaneously reason about images and texts to tackle many tasks, from visual question answering to image captioning. This paper focuses on map parsing, a novel task that is unexplored within the VLM…

Robotics · Computer Science 2025-11-26 David DeFazio , Hrudayangam Mehta , Meng Wang , Ping Yang , Jeremy Blackburn , Shiqi Zhang

We propose a novel visual localization and navigation framework for real-world environments directly integrating observed visual information into the bird-eye-view map. While the renderable neural radiance map (RNR-Map) shows considerable…

Image and Video Processing · Electrical Eng. & Systems 2024-10-10 Minsoo Kim , Obin Kwon , Howoong Jun , Songhwai Oh

We present a novel approach for image-goal navigation, where an agent navigates with a goal image rather than accurate target information, which is more challenging. Our goal is to decouple the learning of navigation goal planning,…

Robotics · Computer Science 2022-02-23 Qiaoyun Wu , Jun Wang , Jing Liang , Xiaoxi Gong , Dinesh Manocha

We study the challenging problem of releasing a robot in a previously unseen environment, and having it follow unconstrained natural language navigation instructions. Recent work on the task of Vision-and-Language Navigation (VLN) has…

Computer Vision and Pattern Recognition · Computer Science 2020-11-10 Peter Anderson , Ayush Shrivastava , Joanne Truong , Arjun Majumdar , Devi Parikh , Dhruv Batra , Stefan Lee

Robots must adapt to diverse human instructions and operate safely in unstructured, open-world environments. Recent Vision-Language models (VLMs) offer strong priors for grounding language and perception, but remain difficult to steer for…

Learning to navigate in dynamic and complex open-world environments is a critical yet challenging capability for autonomous robots. Existing approaches often rely on cascaded modular frameworks, which require extensive hyperparameter tuning…

Robotics · Computer Science 2025-12-25 Wenzhe Cai , Jiaqi Peng , Yuqiang Yang , Yujian Zhang , Meng Wei , Hanqing Wang , Yilun Chen , Tai Wang , Jiangmiao Pang

This paper highlights the significance of including memory structures in neural networks when the latter are used to learn perception-action loops for autonomous robot navigation. Traditional navigation approaches rely on global maps of the…

Robotics · Computer Science 2017-05-24 Steven W Chen , Nikolay Atanasov , Arbaaz Khan , Konstantinos Karydis , Daniel D. Lee , Vijay Kumar