相关论文: Video2Policy: Scaling up Manipulation Tasks in Sim…

Robots operating in complex and uncertain environments face considerable challenges. Advanced robotic systems often rely on extensive datasets to learn manipulation tasks. In contrast, when humans are faced with unfamiliar tasks, such as…

Reinforcement Learning (RL) has shown great potential in refining robotic manipulation policies, yet its efficacy remains strongly bottlenecked by the difficulty of designing generalizable reward functions. In this paper, we propose a…

Humans are adept at learning new tasks by watching a few instructional videos. On the other hand, robots that learn new actions either require a lot of effort through trial and error, or use expert demonstrations that are challenging to…

Learning from visual data opens the potential to accrue a large range of manipulation behaviors by leveraging human demonstrations without specifying each of them mathematically, but rather through natural task specification. In this paper,…

The goal of this paper is to improve the performance and reliability of vision-language-action (VLA) models through iterative online interaction. Since collecting policy rollouts in the real world is expensive, we investigate whether a…

Vision and learning have made significant progress that could improve robotics policies for complex tasks and environments. Learning deep neural networks for image understanding, however, requires large amounts of domain-specific visual…

Imitation Learning (IL) has emerged as a powerful approach in robotics, allowing robots to acquire new skills by mimicking human actions. Despite its potential, the data collection process for IL remains a significant challenge due to the…

Imitation learning for robotic manipulation often suffers from limited generalization and data scarcity, especially in complex, long-horizon tasks. In this work, we introduce a hierarchical framework that leverages code-generating…

Autonomous execution of long-horizon, contact-rich manipulation tasks traditionally requires extensive real-world data and expert engineering, posing significant cost and scalability challenges. This paper proposes a novel framework…

Vision-language-action (VLA) models typically rely on large-scale real-world videos, whereas simulated data, despite being inexpensive and highly parallelizable to collect, often suffers from a substantial visual domain gap and limited…

Recent advances in behavior cloning (BC) have enabled impressive visuomotor control policies. However, these approaches are limited by the quality of human demonstrations, the manual effort required for data collection, and the diminishing…

The field of robotics has made significant advances towards generalist robot manipulation policies. However, real-world evaluation of such policies is not scalable and faces reproducibility challenges, which are likely to worsen as policies…

Large-scale multi-task robotic manipulation systems often rely on text to specify the task. In this work, we explore whether a robot can learn by observing humans. To do so, the robot must understand a person's intent and perform the…

Simulation offers a scalable and efficient alternative to real-world data collection for learning visuomotor robotic policies. However, the simulation-to-reality, or Sim2Real distribution shift -- introduced by employing simulation-trained…

The field of robotics has made significant strides toward developing generalist robot manipulation policies. However, evaluating these policies in real-world scenarios remains time-consuming and challenging, particularly as the number of…

Training general-purpose robots requires learning from large and diverse data sources. Current approaches rely heavily on teleoperated demonstrations which are difficult to scale. We present a scalable framework for training manipulation…

Acquiring large-scale, high-fidelity robot demonstration data remains a critical bottleneck for scaling Vision-Language-Action (VLA) models in dexterous manipulation. We propose a Real-Sim-Real data collection and data editing pipeline that…

We present WebGym, the largest-to-date open-source environment for training realistic visual web agents. Real websites are non-stationary and diverse, making artificial or small-scale task sets insufficient for robust policy learning.…

Learning from Demonstrations, particularly from biological experts like humans and animals, often encounters significant data acquisition challenges. While recent approaches leverage internet videos for learning, they require complex,…

Reinforcement learning is a powerful framework for robots to acquire skills from experience, but often requires a substantial amount of online data collection. As a result, it is difficult to collect sufficiently diverse experiences that…