Related papers: SuperSuit: An Isomorphic Bimodal Interface for Sca…
Mobile imitation learning on portable demonstration interfaces faces two coupled bottlenecks: locomotion-contaminated action labels and inference-induced execution latency on a continuously moving base. Recent wrist-mounted interfaces lower…
Bimanual robotic manipulation is an emerging and critical topic in the robotics community. Previous works primarily rely on integrated control models that take the perceptions and states of both arms as inputs to directly predict their…
We present a universal motion representation that encompasses a comprehensive range of motor skills for physics-based humanoid control. Due to the high dimensionality of humanoids and the inherent difficulties in reinforcement learning,…
Quadrupedal robots have demonstrated exceptional locomotion capabilities through Reinforcement Learning (RL), including extreme parkour maneuvers. However, integrating locomotion skills with navigation in quadrupedal robots has not been…
Learning whole-body mobile manipulation via imitation is essential for generalizing robotic skills to diverse environments and complex tasks. However, this goal is hindered by significant challenges, particularly in effectively processing…
We present UMI-3D, a multimodal extension of the Universal Manipulation Interface (UMI) for robust and scalable data collection in embodied manipulation. While UMI enables portable, wrist-mounted data acquisition, its reliance on monocular…
Large-scale data has driven breakthroughs in robotics, from language models to vision-language-action models in bimanual manipulation. However, humanoid robotics lacks equally effective data collection frameworks. Existing humanoid…
Recent advancements in robotics have underscored the need for effective collaboration between humans and robots. Traditional interfaces often struggle to balance robot autonomy with human oversight, limiting their practical application in…
Efficient and intuitive Human-Robot interfaces are crucial for expanding the user base of operators and enabling new applications in critical areas such as precision agriculture, automated construction, rehabilitation, and environmental…
Robots operating in human environments need various skills, like slow and fast walking, turning, side-stepping, and many more. However, building robot controllers that can exhibit such a large range of behaviors is a challenging problem…
Scaling Vision-Language-Action models for embodied manipulation demands large volumes of diverse manipulation data, yet the high cost of commercial mobile manipulators and teleoperation interfaces that are difficult to deploy at scale…
While data-driven imitation learning has revolutionized robotic manipulation, current approaches remain constrained by the scarcity of large-scale, diverse real-world demonstrations. Consequently, the ability of existing models to…
This paper presents Adaptive Whole-body Loco-Manipulation, AdaptManip, a fully autonomous framework for humanoid robots to perform integrated navigation, object lifting, and delivery. Unlike prior imitation learning-based approaches that…
Achieving versatile humanoid locomotion with a single policy presents a critical scalability challenge. Prevailing methods often rely on distilling multiple terrain-specific teacher policies into a unified student policy. However, while…
UMI-style interfaces enable scalable robot learning, but existing systems remain largely visuomotor, relying primarily on RGB observations and trajectory while providing only limited access to physical interaction signals. This becomes a…
Imitation learning from large-scale, diverse human demonstrations has been shown to be effective for training robots, but collecting such data is costly and time-consuming. This challenge intensifies for multi-step bimanual mobile…
Building general-purpose intelligent robots has long been a fundamental goal of robotics. A promising approach is to mirror the evolutionary trajectory of humans: learning through continuous interaction with the environment, with early…
Human teams are able to easily perform collaborative manipulation tasks. However, for a robot and human to simultaneously manipulate an extended object is a difficult task using existing methods from the literature. Our approach in this…
We present a fully autonomous real-world RL framework for mobile manipulation that can learn policies without extensive instrumentation or human supervision. This is enabled by 1) task-relevant autonomy, which guides exploration towards…
Despite the rise of billion-parameter foundation models trained across thousands of GPUs, similar scaling gains have not been shown for humanoid control. Current neural controllers for humanoids remain modest in size, target a limited set…