paper-with-me

홈 › Papers

ManipulaTHOR: A Framework for Visual Object Manipulation

2021-04-22 · CVPR 2021 1 · Kiana Ehsani, Winson Han, Alvaro Herrasti, Eli VanderBilt, Luca Weihs, Eric Kolve, Aniruddha Kembhavi, Roozbeh Mottaghi

The domain of Embodied AI has recently witnessed substantial progress, particularly in navigating agents within their environments. These early successes have laid the building blocks for the community to tackle tasks that require agents to actively interact with objects in their environment. Object manipulation is an established research domain within the robotics community and poses several challenges including manipulator motion, grasping and long-horizon planning, particularly when dealing with oft-overlooked practical setups involving visually rich and complex scenes, manipulation using mobile agents (as opposed to tabletop manipulation), and generalization to unseen environments and objects. We propose a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and present a new challenge to the Embodied AI community known as ArmPointNav. This task extends the popular point navigation task to object manipulation and offers new challenges including 3D obstacle avoidance, manipulating objects in the presence of occlusion, and multi-object manipulation that necessitates long term planning. Popular learning paradigms that are successful on PointNav challenges show promise, but leave a large room for improvement.

📄 PDF Abstract BibTeX arXiv:2104.11213

Code (1)

allenai/manipulathor pytorch

Tasks

Object

Similar Papers 제목 키워드 기반

Towards Disturbance-Free Visual Mobile Manipulation

2021-12-17 · Tianwei Ni, Kiana Ehsani, Luca Weihs, Jordi Salvador

Deep reinforcement learning has shown promising results on an abundance of robotic tasks in simulation, including visual navigation and manipulation. Prior work generally aims to build embodied agents that solve their as…

Collision AvoidanceDeep Reinforcement LearningKnowledge DistillationVisual Navigation

Selective Visual Representations Improve Convergence and Generalization for Embodied AI

2023-11-07 · Ainaz Eftekhar, Kuo-Hao Zeng, Jiafei Duan, Ali Farhadi 외

Embodied AI models often employ off the shelf vision backbones like CLIP to encode their visual observations. Although such general purpose representations encode rich syntactic and semantic information about the scene, …

ObjectObject Recognition

Learning Predictive Representations for Deformable Objects Using Contrastive Estimation

2020-03-11 · Wilson Yan, Ashwin Vangipuram, Pieter Abbeel, Lerrel Pinto

Using visual model-based learning for deformable object manipulation is challenging due to difficulties in learning plannable visual representations along with complex dynamic models. In this work, we propose a new learn…

Deformable Object Manipulation

Latent Space Roadmap for Visual Action Planning of Deformable and Rigid Object Manipulation

2020-03-19 · Martina Lippi, Petra Poklukar, Michael C. Welle, Anastasiia Varava 외

We present a framework for visual action planning of complex manipulation tasks with high-dimensional state spaces such as manipulation of deformable objects. Planning is performed in a low-dimensional latent state space…

VCA: Vision-Click-Action Framework for Precise Manipulation of Segmented Objects in Target Ambiguous Environments

2026-02-27 · Donggeon Kim, Seungwon Jan, Hyeonjun Park, Daegyu Lim arxiv

The reliance on language in Vision-Language-Action (VLA) models introduces ambiguity, cognitive overhead, and difficulties in precise object identification and sequential task execution, particularly in environments with…