paper-with-me

홈 › Papers

DINOBot: Robot Manipulation via Retrieval and Alignment with Vision Foundation Models

2024-02-20 · Norman Di Palo, Edward Johns

We propose DINOBot, a novel imitation learning framework for robot manipulation, which leverages the image-level and pixel-level capabilities of features extracted from Vision Transformers trained with DINO. When interacting with a novel object, DINOBot first uses these features to retrieve the most visually similar object experienced during human demonstrations, and then uses this object to align its end-effector with the novel object to enable effective interaction. Through a series of real-world experiments on everyday tasks, we show that exploiting both the image-level and pixel-level properties of vision foundation models enables unprecedented learning efficiency and generalisation. Videos and code are available at https://www.robot-learning.uk/dinobot.

📄 PDF Abstract BibTeX arXiv:2402.13181

Code (0)

등록된 구현이 없습니다.

Tasks

Imitation LearningObjectRetrievalRobot Manipulation

Methods 이 논문이 사용한 방법론

Linear Layer A Linear Layer is a projection $\mathbf{XW + b}$.
Attention 설명 없음
Softmax The Softmax output function transforms a previous layer's output into a vector of probabilities. It is commonly used for multiclass classification. Given an input vector $x$…
Multi-Head Attention 설명 없음
Layer Normalization Unlike batch normalization, Layer Normalization directly estimates the normalization statistics from the summed inputs…
Residual Connection 설명 없음
Dense Connections Dense Connections, or Fully Connected Connections, are a type of layer in a deep neural network that use a linear operation where every input is connected to every output…
Vision Transformer The Vision Transformer, or ViT, is a model for image classification that employs a Transformer-like architecture over…

Similar Papers 제목 키워드 기반

RoboTok: An Internet-Scale Data Engine for Human Demonstration Retrieval and Dexterous Manipulation Learning

2026-09-02 · Howard Qian, Yiting Chen, Yunfei Xie, Kejia Ren 외 hf

Robot learning increasingly depends on broad and diverse demonstrations, yet collecting robot data remains expensive and poorly suited to covering the long tail of real-world tasks. To address this bottleneck, we introdu…

On the Effectiveness of Retrieval, Alignment, and Replay in Manipulation

2023-12-19 · Norman Di Palo, Edward Johns

Imitation learning with visual observations is notoriously inefficient when addressed with end-to-end behavioural cloning methods. In this paper, we explore an alternative paradigm which decomposes reasoning into three p…

Behavioural cloningImitation LearningObjectRetrieval

ReGIL: Retrieval-Guided Imitation Learning from a Single Demonstration

2026-06-08 · Yuying Zhang, Francesco Verdoja, Wenyan Yang, Ville Kyrki arxiv

Learning robot manipulation policies with deep neural networks from a single demonstration remains highly challenging, as even small deviations from the demonstrated trajectory can quickly compound into failure, while co…

Robot Manipulation

Learning a Thousand Tasks in a Day

2025-11-13 · Kamil Dreczkowski, Pietro Vitiello, Vitalis Vosylius, Edward Johns arxiv

Humans are remarkably efficient at learning tasks from demonstrations, but today's imitation learning methods for robot manipulation often require hundreds or thousands of demonstrations per task. We investigate two fund…

Robot Manipulation

Qwen-RobotManip Technical Report: Alignment Unlocks Scale for Robotic Manipulation Foundation Models

2026-06-16 · Haoqi Yuan, Zhixuan Liang, Anzhe Chen, Ye Wang 외 arxiv

Foundation models in language and multimodality achieve strong generalization by aligning heterogeneous data under a unified formulation and training at scale. In this report, we investigate whether this scaling recipe c…

Instruction Following