Text-driven Affordance Learning from Egocentric Vision

• URL: http://arxiv.org/abs/2404.02523v1
• Date: Wed, 3 Apr 2024 07:23:03 GMT
• Title: Text-driven Affordance Learning from Egocentric Vision
• Authors: Tomoya Yoshida, Shuhei Kurita, Taichi Nishimura, Shinsuke Mori,
• Abstract summary: We present a text-driven affordance learning approach for robots. We aim to learn contact points and manipulation trajectories from an egocentric view following textual instruction. Our approach robustly handles multiple affordances, serving as a new standard for affordance learning in real-world scenarios.
• Score: 6.699930460835963
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Visual affordance learning is a key component for robots to understand how to interact with objects. Conventional approaches in this field rely on pre-defined objects and actions, falling short of capturing diverse interactions in realworld scenarios. The key idea of our approach is employing textual instruction, targeting various affordances for a wide range of objects. This approach covers both hand-object and tool-object interactions. We introduce text-driven affordance learning, aiming to learn contact points and manipulation trajectories from an egocentric view following textual instruction. In our task, contact points are represented as heatmaps, and the manipulation trajectory as sequences of coordinates that incorporate both linear and rotational movements for various manipulations. However, when we gather data for this task, manual annotations of these diverse interactions are costly. To this end, we propose a pseudo dataset creation pipeline and build a large pseudo-training dataset: TextAFF80K, consisting of over 80K instances of the contact points, trajectories, images, and text tuples. We extend existing referring expression comprehension models for our task, and experimental results show that our approach robustly handles multiple affordances, serving as a new standard for affordance learning in real-world scenarios.

Related papers

• Flex: End-to-End Text-Instructed Visual Navigation with Foundation Models [59.892436892964376]
  We investigate the minimal data requirements and architectural adaptations necessary to achieve robust closed-loop performance with vision-based control policies. Our findings are synthesized in Flex (Fly-lexically), a framework that uses pre-trained Vision Language Models (VLMs) as frozen patch-wise feature extractors. We demonstrate the effectiveness of this approach on quadrotor fly-to-target tasks, where agents trained via behavior cloning successfully generalize to real-world scenes.
  arXiv  Detail & Related papers  (2024-10-16T19:59:31Z)
• Spatio-Temporal Context Prompting for Zero-Shot Action Detection [13.22912547389941]
  We propose a method which can effectively leverage the rich knowledge of visual-language models to perform Person-Context Interaction. To address the challenge of recognizing distinct actions by multiple people at the same timestamp, we design the Interest Token Spotting mechanism. Our method achieves superior results compared to previous approaches and can be further extended to multi-action videos.
  arXiv  Detail & Related papers  (2024-08-28T17:59:05Z)
• Learning Manipulation by Predicting Interaction [85.57297574510507]
  We propose a general pre-training pipeline that learns Manipulation by Predicting the Interaction. The experimental results demonstrate that MPI exhibits remarkable improvement by 10% to 64% compared with previous state-of-the-art in real-world robot platforms.
  arXiv  Detail & Related papers  (2024-06-01T13:28:31Z)
• Generating Human Interaction Motions in Scenes with Text Control [66.74298145999909]
  We present TeSMo, a method for text-controlled scene-aware motion generation based on denoising diffusion models. Our approach begins with pre-training a scene-agnostic text-to-motion diffusion model. To facilitate training, we embed annotated navigation and interaction motions within scenes.
  arXiv  Detail & Related papers  (2024-04-16T16:04:38Z)
• Mitigating Object Dependencies: Improving Point Cloud Self-Supervised Learning through Object Exchange [50.45953583802282]
  We introduce a novel self-supervised learning (SSL) strategy for point cloud scene understanding. Our approach leverages both object patterns and contextual cues to produce robust features. Our experiments demonstrate the superiority of our method over existing SSL techniques.
  arXiv  Detail & Related papers  (2024-04-11T06:39:53Z)
• DiffH2O: Diffusion-Based Synthesis of Hand-Object Interactions from Textual Descriptions [15.417836855005087]
  We propose DiffH2O, a novel method to synthesize realistic, one or two-handed object interactions. We decompose the task into a grasping stage and a text-based interaction stage. In the grasping stage, the model only generates hand motions, whereas in the interaction phase both hand and object poses are synthesized.
  arXiv  Detail & Related papers  (2024-03-26T16:06:42Z)
• InterTracker: Discovering and Tracking General Objects Interacting with Hands in the Wild [40.489171608114574]
  Existing methods rely on frame-based detectors to locate interacting objects. We propose to leverage hand-object interaction to track interactive objects. Our proposed method outperforms the state-of-the-art methods.
  arXiv  Detail & Related papers  (2023-08-06T09:09:17Z)
• Object-agnostic Affordance Categorization via Unsupervised Learning of Graph Embeddings [6.371828910727037]
  Acquiring knowledge about object interactions and affordances can facilitate scene understanding and human-robot collaboration tasks. We address the problem of affordance categorization for class-agnostic objects with an open set of interactions. A novel depth-informed qualitative spatial representation is proposed for the construction of Activity Graphs.
  arXiv  Detail & Related papers  (2023-03-30T15:04:04Z)
• Where2Act: From Pixels to Actions for Articulated 3D Objects [54.19638599501286]
  We extract highly localized actionable information related to elementary actions such as pushing or pulling for articulated objects with movable parts. We propose a learning-from-interaction framework with an online data sampling strategy that allows us to train the network in simulation. Our learned models even transfer to real-world data.
  arXiv  Detail & Related papers  (2021-01-07T18:56:38Z)
• COBE: Contextualized Object Embeddings from Narrated Instructional Video [52.73710465010274]
  We propose a new framework for learning Contextualized OBject Embeddings from automatically-transcribed narrations of instructional videos. We leverage the semantic and compositional structure of language by training a visual detector to predict a contextualized word embedding of the object and its associated narration. Our experiments show that our detector learns to predict a rich variety of contextual object information, and that it is highly effective in the settings of few-shot and zero-shot learning.
  arXiv  Detail & Related papers  (2020-07-14T19:04:08Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.