相关论文: VGGT-DP: Generalizable Robot Control via Vision Fo…

Existing RGB-based imitation learning approaches typically employ traditional vision encoders such as ResNet or ViT, which lack explicit 3D reasoning capabilities. Recent geometry-grounded vision models, such as VGGT~\cite{wang2025vggt},…

The field of visual representation learning has seen explosive growth in the past years, but its benefits in robotics have been surprisingly limited so far. Prior work uses generic visual representations as a basis to learn (task-specific)…

Transformer-based general visual geometry frameworks have shown promising performance in camera pose estimation and 3D scene understanding. Recent advancements in Visual Geometry Grounded Transformer (VGGT) models have shown great promise…

Visual representations play a crucial role in developing generalist robotic policies. Previous vision encoders, typically pre-trained with single-image reconstruction or two-image contrastive learning, tend to capture static information,…

In this paper, we leverage self-supervised vision transformer models and their emergent semantic abilities to improve the generalization abilities of imitation learning policies. We introduce DVK, an imitation learning algorithm that…

Imitation learning has emerged as a crucial ap proach for acquiring visuomotor skills from demonstrations, where designing effective observation encoders is essential for policy generalization. However, existing methods often struggle to…

Learning robust and generalizable manipulation skills from demonstrations remains a key challenge in robotics, with broad applications in industrial automation and service robotics. While recent imitation learning methods have achieved…

We present VGGT, a feed-forward neural network that directly infers all key 3D attributes of a scene, including camera parameters, point maps, depth maps, and 3D point tracks, from one, a few, or hundreds of its views. This approach is a…

General 3D foundation models have started to lead the trend of unifying diverse vision tasks, yet most assume RGB-only inputs and ignore readily available geometric cues (e.g., camera intrinsics, poses, and depth maps). To address this…

General visual representations learned from web-scale datasets for robotics have achieved great success in recent years, enabling data-efficient robot learning on manipulation tasks; yet these pre-trained representations are mostly on 2D…

Perceiving and reconstructing 3D scene geometry from visual inputs is crucial for autonomous driving. However, there still lacks a driving-targeted dense geometry perception model that can adapt to different scenarios and camera…

Robot learning holds tremendous promise to unlock the full potential of flexible, general, and dexterous robot systems, as well as to address some of the deepest questions in artificial intelligence. However, bringing robot learning to the…

Effective robotic manipulation relies on a precise understanding of 3D scene geometry, and one of the most straightforward ways to acquire such geometry is through multi-view observations. Motivated by this, we present GP3 -- a 3D…

Perceptive locomotion for legged robots requires anticipating and adapting to complex, dynamic environments. Model Predictive Control (MPC) serves as a strong baseline, providing interpretable motion planning with constraint enforcement,…

Achieving generalizable and precise robotic manipulation across diverse environments remains a critical challenge, largely due to limitations in spatial perception. While prior imitation-learning approaches have made progress, their…

At its core, robotic manipulation is a problem of vision-to-geometry mapping ($f(v) \rightarrow G$). Physical actions are fundamentally defined by geometric properties like 3D positions and spatial relationships. Consequently, we argue that…

Vision-based learning methods provide promise for robots to learn complex manipulation tasks. However, how to generalize the learned manipulation skills to real-world interactions remains an open question. In this work, we study robotic…

Large, general-purpose robotic policies trained on diverse demonstration datasets have been shown to be remarkably effective both for controlling a variety of robots in a range of different scenes, and for acquiring broad repertoires of…

Visual target navigation is a critical capability for autonomous robots operating in unknown environments, particularly in human-robot interaction scenarios. While classical and learning-based methods have shown promise, most existing…

Robotic manipulation requires understanding both the 3D spatial structure of the environment and its temporal evolution, yet most existing policies overlook one or both. They typically rely on 2D visual observations and backbones pretrained…