中文
相关论文

相关论文: UniTeam: Open Vocabulary Mobile Manipulation Chall…

200 篇论文

``Bring me a plate.'' For domestic service robots, this simple command reveals a complex challenge: inferring where everyday items are stored, often out of sight in drawers, cabinets, or closets. Despite advances in vision and manipulation,…

计算与语言 · 计算机科学 2026-01-01 Michaela Levi-Richter , Reuth Mirsky , Oren Glickman

Utilizing Vision-Language Models (VLMs) for robotic manipulation represents a novel paradigm, aiming to enhance the model's ability to generalize to new objects and instructions. However, due to variations in camera specifications and…

机器人学 · 计算机科学 2024-09-13 Fanfan Liu , Feng Yan , Liming Zheng , Chengjian Feng , Yiyang Huang , Lin Ma

Vision language model (VLM)-based mobile agents show great potential for assisting users in performing instruction-driven tasks. However, these agents typically struggle with personalized instructions -- those containing ambiguous,…

Search engines enable the retrieval of unknown information with texts. However, traditional methods fall short when it comes to understanding unfamiliar visual content, such as identifying an object that the model has never seen before.…

计算机视觉与模式识别 · 计算机科学 2024-10-29 Zhixin Zhang , Yiyuan Zhang , Xiaohan Ding , Xiangyu Yue

Large Language Model (LLM) agents are increasingly deployed to automate complex workflows in mobile and desktop environments. However, current model-centric agent architectures struggle to self-evolve post-deployment: improving…

人工智能 · 计算机科学 2025-12-19 Zibin Liu , Cheng Zhang , Xi Zhao , Yunfei Feng , Bingyu Bai , Dahu Feng , Erhu Feng , Yubin Xia , Haibo Chen

Real-world deployment of new technology and capabilities can be daunting. The recent DARPA Subterranean (SubT) Challenge, for instance, aimed at the advancement of robotic platforms and autonomy capabilities in three one-year development…

With the advancement of multimodal large language models (MLLMs), building GUI agent systems has become an increasingly promising direction--especially for mobile platforms, given their rich app ecosystems and intuitive touch interactions.…

人工智能 · 计算机科学 2026-02-10 Yangqin Jiang , Chao Huang

Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities across a wide range of vision-language tasks. However, their performance as embodied agents, which requires multi-round dialogue spatial reasoning and…

计算机视觉与模式识别 · 计算机科学 2026-01-07 Xunyi Zhao , Gengze Zhou , Qi Wu

Current mobile manipulation research predominantly follows an instruction-driven paradigm, where agents rely on predefined textual commands to execute tasks. However, this setting confines agents to a passive role, limiting their autonomy…

机器人学 · 计算机科学 2026-04-16 Hao Ju , Shaofei Huang , Hongyu Li , Zihan Ding , Si Liu , Meng Wang , Zhedong Zheng

Safe, agile, and socially compliant multi-robot navigation in cluttered and constrained environments remains a critical challenge. This is especially difficult with self-interested agents with unique, unknown priorities in decentralized…

机器人学 · 计算机科学 2026-05-12 Vagul Mahadevan , Shangtong Zhang , Rohan Chandra

Hallucinations remain a significant challenge in current Generative AI models, undermining trust in AI systems and their reliability. This study investigates how orchestrating multiple specialized Artificial Intelligent Agents can help…

计算与语言 · 计算机科学 2025-01-27 Diego Gosmar , Deborah A. Dahl

One key challenge in augmented reality is the placement of virtual content in natural locations. Existing automated techniques are only able to work with a closed-vocabulary, fixed set of objects. In this paper, we introduce a new…

计算机视觉与模式识别 · 计算机科学 2023-12-21 Luke Yoffe , Aditya Sharma , Tobias Höllerer

Large Reasoning Models (LRMs) like o3 and DeepSeek-R1 have achieved remarkable progress in reasoning tasks with long cot. However, they remain computationally inefficient and struggle with accuracy when solving problems requiring complex…

人工智能 · 计算机科学 2026-03-03 Haipeng Luo , Huawen Feng , Qingfeng Sun , Can Xu , Kai Zheng , Yufei Wang , Tao Yang , Han Hu , Yansong Tang

Advancements in Multimodal Large Language Models (MLLMs) have improved human motion understanding. However, these models remain constrained by their "instruct-only" nature, lacking interactivity and adaptability for diverse analytical…

人工智能 · 计算机科学 2025-02-28 Lei Li , Sen Jia , Jianhao Wang , Zhaochong An , Jiaang Li , Jenq-Neng Hwang , Serge Belongie

Recent open-vocabulary robot mapping methods enrich dense geometric maps with pre-trained visual-language features, achieving a high level of detail and guiding robots to find objects specified by open-vocabulary language queries. While the…

机器人学 · 计算机科学 2026-03-04 Fujing Xie , Sören Schwertfeger , Hermann Blum

A central challenge in explainable AI, particularly in the visual domain, is producing explanations grounded in human-understandable concepts. To tackle this, we introduce OCEAN (Object-Centric Explananda via Agent Negotiation), a novel,…

人工智能 · 计算机科学 2025-09-30 Benjamin Teoh , Ben Glocker , Francesca Toni , Avinash Kori

A grand goal in AI is to build a robot that can accurately navigate based on natural language instructions, which requires the agent to perceive the scene, understand and ground language, and act in the real-world environment. One key…

计算与语言 · 计算机科学 2019-04-09 Hao Tan , Licheng Yu , Mohit Bansal

Object manipulation for rearrangement into a specific goal state is a significant task for collaborative robots. Accurately determining object placement is a key challenge, as misalignment can increase task complexity and the risk of…

机器人学 · 计算机科学 2025-03-06 Guanqun Cao , Ryan Mckenna , Erich Graf , John Oyekan

One key challenge in Augmented Reality is the placement of virtual content in natural locations. Most existing automated techniques can only work with a closed-vocabulary, fixed set of objects. In this paper, we introduce and evaluate…

计算机视觉与模式识别 · 计算机科学 2024-01-18 Aditya Sharma , Luke Yoffe , Tobias Höllerer

Object-goal navigation (Object-nav) entails searching, recognizing and navigating to a target object. Object-nav has been extensively studied by the Embodied-AI community, but most solutions are often restricted to considering static…