Attention from Action, for Action: Emergent Visual Bottlenecks for Policy Learning
Authors: Zheyu Zhuang, Ruiyu Wang, Nick Heppert, Johannes Fabian Hahn, Abhinav Valada, Florian T. Pokorny, Danica Kragic
Organizations: Department of Robotics, Perception and Learning, KTH Royal Institute of Technology, Sweden · Department of Computer Science, University of Freiburg, Germany · Department of Informatics, Universität Hamburg, Germany
Abstract
Visual bottlenecks that focus policy inputs on regions of interest (ROIs) can improve data-efficient visuomotor learning by separating where to look from how to act. Many ROI interfaces rely on external spatial labels, such as gaze, object classes, or affordance annotations. Label-free alternatives often derive crops from trajectories by detecting gripper or motion events and centering a fixed crop at the projected end-effector. Such action-derived crops are useful spatial priors that require no additional labels, but they encode fixed choices about event timing, proxy points, and crop scale. When the visual evidence needed for control lies away from the end-effector or changes continuously with task progress, these crops can become misaligned. We propose Seeker, a task- and state-conditioned readout that learns attention from action. Starting from frozen DINOv3 features, Seeker iteratively updates a query with gathered visual evidence, producing progression-aware ROIs solely from action supervision. The learned ROI serves as a spatial interface for RGB cropping, mask-guided background augmentation, and point-cloud filtering. In simulation and the real world, Seeker improves data efficiency and robustness over no-crop, augmentation, and action-derived crop baselines. On real robots, Seeker raises average in-domain success from the best baseline's 48.3% to 76.7% and success under lighting/background shifts from 20.0% to 60.0%.
Focusing on spatially localized, control-relevant visual cues has been shown to improve data efficiency in visuomotor policies by reducing the need to model task-irrelevant visual variation. Existing methods often impose this focus through input preprocessing, such as cropping control- or object-centric regions in RGB images or point-clouds. However, it remains underexplored whether such localized features can be exposed directly from commonly used convolutional neural network (CNN) encoded features. In this paper, we show that intermediate CNN features preserve localized visual context for control, but existing pooling methods fail to aggregate it effectively. We introduce FocusPool, an attention pooling module that selectively aggregates intermediate visual features according to their relevance to the robot's current proprioceptive context. The resulting pooled representation captures task-progressive, control-relevant local information and is used directly for policy learning. Across simulation and real-world experiments, FocusPool improves policy success rates over pooling and explicit local focus methods by 36.2% and 41.2%, with training only 5.8% of encoder parameters.
End-to-end visuomotor policies provide little opportunity for humans to understand or correct the policy's visual attention. We propose GuidedAttention, a visuomotor imitation learning framework that introduces interpretable and correctable visual attention as an explicit intermediate representation. Task-relevant attention keypoints are predicted from camera images and condition a diffusion-based action policy. Users can inspect and optionally correct selected keypoints once at rollout initialization, after which the corrected attention is automatically propagated throughout execution by a tracking module. Experiments in simulation and the real world demonstrate that GuidedAttention consistently improves robot manipulation performance, particularly under positional and appearance out-of-distribution (OOD) conditions. https://mmurooka.github.io/guided-attention-project-page
Robot policy learning benefits from world-action models that capture environment dynamics, but pixel-level prediction entangles dynamics with nuisance factors such as lighting and texture, making learned representations vulnerable to task-irrelevant visual variation. We propose JOPAT, a JOint Pixel-And-Track World-Action Model that predicts latent visual observations, 2D point tracks with visibility, and actions in a single denoising diffusion transformer. The key insight is that tracks provide an explicit representation of motion that captures long-horizon dynamics and remains robust under occlusion or partial out-of-frame motion, offering greater utility than modeling pixel appearance alone. On LIBERO and real-world LeRobot tasks, JOPAT improves over pixel-based baselines, with the largest gains on long-horizon tasks involving occlusion, object interaction, and off-screen motion.