English
Related papers

Related papers: Multi-Modal 3D Scene Graph Updater for Shared and …

200 papers

3D mapping in dynamic environments poses a challenge for modern researchers in robotics and autonomous transportation. There are no universal representations for dynamic 3D scenes that incorporate multimodal data such as images, point…

Computer Vision and Pattern Recognition · Computer Science 2025-08-26 Dmitry Yudin

Dynamic Scene Graph Generation (DSGG) for videos is a challenging task in computer vision. While existing approaches often focus on sophisticated architectural design and solely use recall during evaluation, we take a closer look at their…

Computer Vision and Pattern Recognition · Computer Science 2025-03-21 Xuanming Cui , Jaiminkumar Ashokbhai Bhoi , Chionh Wei Peng , Adriel Kuek , Ser Nam Lim

We present a solution to multi-robot distributed semantic mapping of novel and unfamiliar environments. Most state-of-the-art semantic mapping systems are based on supervised learning algorithms that cannot classify novel observations…

Robotics · Computer Science 2021-03-30 Stewart Jamieson , Kaveh Fathian , Kasra Khosoussi , Jonathan P. How , Yogesh Girdhar

Large Language Models (LLMs) trained using massive text datasets have recently shown promise in generating action plans for robotic agents from high level text queries. However, these models typically do not consider the robot's…

Robotics · Computer Science 2023-05-03 Maitrey Gramopadhye , Daniel Szafir

Graph-based representations such as Scene Graphs enable localization in structured indoor environments by matching a locally observed graph, constructed from sensor data, to a prior map. This process is particularly challenging in…

While 2D occupancy maps commonly used in mobile robotics enable safe navigation in indoor environments, in order for robots to understand and interact with their environment and its inhabitants representing 3D geometry and semantic…

Robotics · Computer Science 2025-01-09 Krishnananda Prabhu Sivananda , Francesco Verdoja , Ville Kyrki

Recent progress in vision-language models (VLMs) has opened new possibilities for robot task planning, but these models often produce incorrect action sequences. To address these limitations, we propose VeriGraph, a novel framework that…

Robotics · Computer Science 2026-04-20 Daniel Ekpo , Mara Levy , Saksham Suri , Chuong Huynh , Archana Swaminathan , Abhinav Shrivastava

Recently, Large Language Models (LLMs) and Multimodal Large Language Models (MLLMs) have shown promise in instruction following and 2D image understanding. While these models are powerful, they have not yet been developed to comprehend the…

Computer Vision and Pattern Recognition · Computer Science 2023-12-22 Senqiao Yang , Jiaming Liu , Ray Zhang , Mingjie Pan , Zoey Guo , Xiaoqi Li , Zehui Chen , Peng Gao , Yandong Guo , Shanghang Zhang

Designing robotic agents to perform open vocabulary tasks has been the long-standing goal in robotics and AI. Recently, Large Language Models (LLMs) have achieved impressive results in creating robotic agents for performing open vocabulary…

In remote and hybrid work contexts, the integration of physical and digital environments is revolutionizing spatial experiences, collaboration, and interpersonal interactions. This study examines three fundamental spatial conditions: the…

Autonomous operation of service robotics in human-centric scenes remains challenging due to the need for understanding of changing environments and context-aware decision-making. While existing approaches like topological maps offer…

Robotics · Computer Science 2025-06-03 Jiawei Hou , Xiangyang Xue , Taiping Zeng

The analysis of events in dynamic environments poses a fundamental challenge in the development of intelligent agents and robots capable of interacting with humans. Current approaches predominantly utilize visual models. However, these…

Computer Vision and Pattern Recognition · Computer Science 2025-05-07 Sergey Linok , Vadim Semenov , Anastasia Trunova , Oleg Bulichev , Dmitry Yudin

Multimodal Large Language Models (MLLMs) have made significant progress in tasks such as image captioning and question answering. However, while these models can generate realistic captions, they often struggle with providing precise…

Computer Vision and Pattern Recognition · Computer Science 2025-04-07 Chun-Peng Chang , Alain Pagani , Didier Stricker

The task of image captioning demands an algorithm to generate natural language descriptions of visual inputs. Recent advancements have seen a convergence between image captioning research and the development of Large Language Models (LLMs)…

Computer Vision and Pattern Recognition · Computer Science 2024-12-06 Davide Bucciarelli , Nicholas Moratelli , Marcella Cornia , Lorenzo Baraldi , Rita Cucchiara

The Multi-Modal Large Language Model (MLLM) refers to an extension of the Large Language Model (LLM) equipped with the capability to receive and infer multi-modal data. Spatial awareness stands as one of the crucial abilities of MLLM,…

Artificial Intelligence · Computer Science 2023-11-02 Yongqiang Zhao , Zhenyu Li , Zhi Jin , Feng Zhang , Haiyan Zhao , Chengfeng Dou , Zhengwei Tao , Xinhai Xu , Donghong Liu

For intelligent robots to interact in meaningful ways with their environment, they must understand both the geometric and semantic properties of the scene surrounding them. The majority of research to date has addressed these mapping…

Robotics · Computer Science 2017-08-04 Niko Sünderhauf , Trung T. Pham , Yasir Latif , Michael Milford , Ian Reid

Recent advances in data-driven models for grounded language understanding have enabled robots to interpret increasingly complex instructions. Two fundamental limitations of these methods are that most require a full model of the environment…

Robotics · Computer Science 2019-10-23 Siddharth Patki , Ethan Fahnestock , Thomas M. Howard , Matthew R. Walter

Modern tools for class-agnostic image segmentation (e.g., SegmentAnything) and open-set semantic understanding (e.g., CLIP) provide unprecedented opportunities for robot perception and mapping. While traditional closed-set metric-semantic…

The most common way for robots to handle environmental information is by using maps. At present, each kind of data is hosted on a separate map, which complicates planning because a robot attempting to perform a task needs to access and…

Robotics · Computer Science 2020-05-25 Francesco Verdoja , Ville Kyrki

A scene graph is a semantic representation that expresses the objects, attributes, and relationships between objects in a scene. Scene graphs play an important role in many cross modality tasks, as they are able to capture the interactions…

Computer Vision and Pattern Recognition · Computer Science 2022-09-20 Xuming Hu , Zhijiang Guo , Yu Fu , Lijie Wen , Philip S. Yu