cs.RONov 15, 2026

Cleanly-DINO: Efficiently Learning Visual Task Spaces for Robotics

Authors: Adrian Röfer, Melika Shekarriz, José Arce y de la Borbolla, Iman Nematollahi, Abhinav Valada

Organizations: University of Freiburg

Abstract

Learning manipulation tasks from few demonstrations requires abstractions that capture the changes relevant to task completion, such as object poses in rigid-body manipulation. However, tasks such as cleaning are defined by changes in visual state rather than object pose, making the choice of task representation less clear. In this work, we propose Cleanly-DINO to learn visual task spaces from few demonstrations. Given a mask of a task-relevant region and frozen ViT features, Cleanly-DINO fits a projection to isolate a task space and fit a progression metric to it. We train the model on diverse cleaning examples and evaluate its ability to localize incomplete task regions and transfer across visual domains. We also study its utility for robot learning by using it as an observation encoder and reward signal in a reinforcement learning setting. Finally, we deploy our fitted model within a real-world robotic wiping pipeline to evaluate its use in guiding task execution.

Figures & tables

Explore similar work

CardsList
  1. RoboMP-DINOv2: Prompts, Not Filters for Robust Robot Manipulation

    Sep 22, 2026Han Qi, Heng YangGeneralization in Robotic ManipulationVisuomotor Policy Learning

  2. Rewarding DINO: Predicting Dense Rewards with Vision Foundation Models

    Mar 17, 2026Pierre Krack, Tobias Jülg, Wolfram Burgard +1Reward ModelingReward Design for RL

  3. TLC-DiT: Task-Aligned Local Visual Conditioning for Robust Multitask Robot Manipulation

    Sep 28, 2026Xianbo Cai, Hideyuki Ichiwara, Zihang Wang +2Language-Conditioned Robot ManipulationMulti-Task Robotic Manipulation