9 papers
Opening the Sim-to-Real Door for Humanoid Pixel-to-Action Policy Transfer
Haoru Xue, Tairan He, Zi Wang +9
Recent progress in GPU-accelerated, photorealistic simulation has opened a scalable data-generation path for robot learning, where massive physics and visual randomization allow po…
VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation
Tairan He, Zi Wang, Haoru Xue +11
A key barrier to the real-world deployment of humanoid robots is the lack of autonomous loco-manipulation skills. We introduce VIRAL, a visual sim-to-real framework that learns hum…
Gallant: Voxel Grid-based Humanoid Locomotion and Local-navigation across 3D Constrained Terrains
Qingwei Ben, Botian Xu, Kailin Li +6
Robust humanoid locomotion requires accurate and globally consistent perception of the surrounding 3D environment. However, existing perception modules, mainly based on depth image…
SMAP: Self-supervised Motion Adaptation for Physically Plausible Humanoid Whole-body Control
Haoyu Zhao, Sixu Lin, Qingwei Ben +5
This paper presents a novel framework that enables real-world humanoid robots to maintain stability while performing human-like motion. Current methods train a policy which allows…
TeleOpBench: A Simulator-Centric Benchmark for Dual-Arm Dexterous Teleoperation
Hangyu Li, Qin Zhao, Haoran Xu +10
Teleoperation is a cornerstone of embodied-robot learning, and bimanual dexterous teleoperation in particular provides rich demonstrations that are difficult to obtain with fully a…
VB-Com: Learning Vision-Blind Composite Humanoid Locomotion Against Deficient Perception
Junli Ren, Tao Huang, Huayi Wang +6
The performance of legged locomotion is closely tied to the accuracy and comprehensiveness of state observations. Blind policies, which rely solely on proprioception, are considere…