Related papers: PHUMA: Physically-Grounded Humanoid Locomotion Dat…

Parkour tasks for quadrupeds have emerged as a promising benchmark for agile locomotion. While human athletes can effectively perceive environmental characteristics to select appropriate footholds for obstacle traversal, endowing legged…

Extracting physically plausible 3D human motion from videos is a critical task. Although existing simulation-based motion imitation methods can enhance the physical quality of daily motions estimated from monocular video capture, extending…

Scalable learning of humanoid robots is crucial for their deployment in real-world applications. While traditional approaches primarily rely on reinforcement learning or teleoperation to achieve whole-body control, they are often limited by…

Whole-body humanoid motion represents a fundamental challenge in robotics, requiring balance, coordination, and adaptability to enable human-like behaviors. However, existing methods typically require multiple training samples per motion,…

Physics-based humanoid control relies on training with motion datasets that have diverse data distributions. However, the fixed difficulty distribution of datasets limits the performance ceiling of the trained control policies.…

In contrast to quadruped robots that can navigate diverse terrains using a "blind" policy, humanoid robots require accurate perception for stable locomotion due to their high degrees of freedom and inherently unstable morphology. However,…

The estimation of 3D human motion from video has progressed rapidly but current methods still have several key limitations. First, most methods estimate the human in camera coordinates. Second, prior work on estimating humans in global…

High-quality, long-horizon demonstrations are essential for embodied AI, yet acquiring such data for tightly coupled wheeled mobile manipulators remains a fundamental bottleneck. Unlike fixed-base systems, mobile manipulators require…

Humanoid robots have achieved significant progress in motion generation and control, exhibiting movements that appear increasingly natural and human-like. Inspired by the Turing Test, we propose the Motion Turing Test, a framework that…

Current approaches for humanoid whole-body manipulation, primarily relying on teleoperation or visual sim-to-real reinforcement learning, are hindered by hardware logistics and complex reward engineering. Consequently, demonstrated…

While recent advances in humanoid locomotion have achieved stable walking on varied terrains, capturing the agility and adaptivity of highly dynamic human motions remains an open challenge. In particular, agile parkour in complex…

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,…

Synthesizing interaction-involved human motions has been challenging due to the high complexity of 3D environments and the diversity of possible human behaviors within. We present LAMA, Locomotion-Action-MAnipulation, to synthesize natural…

Human motion synthesis is an important problem with applications in graphics, gaming and simulation environments for robotics. Existing methods require accurate motion capture data for training, which is costly to obtain. Instead, we…

Imitation learning method has shown immense promise for robotic manipulation, yet its practical deployment is fundamentally constrained by the data scarcity. Despite prior work on collecting large-scale datasets, there still remains a…

A significant bottleneck in humanoid policy learning is the acquisition of large-scale, diverse datasets, as collecting reliable real-world data remains both difficult and cost-prohibitive. To address this limitation, we introduce…

Incorporating physics in human motion capture to avoid artifacts like floating, foot sliding, and ground penetration is a promising direction. Existing solutions always adopt kinematic results as reference motions, and the physics is…

This paper investigates humanoid whole-body dexterous manipulation, where the efficient collection of high-quality demonstration data remains a central bottleneck. Existing teleoperation systems often suffer from limited portability,…

Denoising diffusion models hold great promise for generating diverse and realistic human motions. However, existing motion diffusion models largely disregard the laws of physics in the diffusion process and often generate…

Motion understanding is fundamental to physical reasoning, enabling models to infer dynamics and predict future states. However, state-of-the-art models still struggle on recent motion benchmarks, primarily due to the scarcity of…