12 citations · 35 across the 27 of their papers we have counts for
27 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…
SONIC: Supersizing Motion Tracking for Natural Humanoid Whole-Body Control
Zhengyi Luo, Ye Yuan, Tingwu Wang +25
Despite the rise of billion-parameter foundation models trained across thousands of graphical processing units (GPUs), similar scaling gains have not been shown for humanoid contro…
Self-Improving Vision-Language-Action Models with Data Generation via Residual RL
Wenli Xiao, Haotian Lin, Andy Peng +9
Supervised fine-tuning (SFT) has become the de facto post-training strategy for large vision-language-action (VLA) models, but its reliance on costly human demonstrations limits sc…
HDMI: Learning Interactive Humanoid Whole-Body Control from Human Videos
Haoyang Weng, Yitang Li, Nikhil Sobanbabu +5
Enabling robust whole-body humanoid-object interaction (HOI) remains challenging due to motion data scarcity and the contact-rich nature. We present HDMI (HumanoiD iMitation for In…
Hold My Beer: Learning Gentle Humanoid Locomotion and End-Effector Stabilization Control
Yitang Li, Yuanhang Zhang, Wenli Xiao +5
Can your humanoid walk up and hand you a full cup of beer, without spilling a drop? While humanoids are increasingly featured in flashy demos like dancing, delivering packages, tra…
Sampling-Based System Identification with Active Exploration for Legged Robot Sim2Real Learning
Nikhil Sobanbabu, Guanqi He, Tairan He +2
Sim-to-real discrepancies hinder learning-based policies from achieving high-precision tasks in the real world. While Domain Randomization (DR) is commonly used to bridge this gap,…
Emergent Active Perception and Dexterity of Simulated Humanoids from Visual Reinforcement Learning
Zhengyi Luo, Chen Tessler, Toru Lin +8
Human behavior is fundamentally shaped by visual perception -- our ability to interact with the world depends on actively gathering relevant information and adapting our movements…
FALCON: Learning Force-Adaptive Humanoid Loco-Manipulation
Yuanhang Zhang, Yifu Yuan, Prajwal Gurunath +7
Humanoid loco-manipulation holds transformative potential for daily service and industrial tasks, yet achieving precise, robust whole-body control with 3D end-effector force intera…
Humanoid Policy ~ Human Policy
Ri-Zhao Qiu, Shiqi Yang, Xuxin Cheng +12
Training manipulation policies for humanoid robots with diverse data enhances their robustness and generalization across tasks and platforms. However, learning solely from robot de…
Bridging Adaptivity and Safety: Learning Agile Collision-Free Locomotion Across Varied Physics
Yichao Zhong, Chong Zhang, Tairan He +1
Real-world legged locomotion systems often need to reconcile agility and safety for different scenarios. Moreover, the underlying dynamics are often unknown and time-variant (e.g.,…
ASAP: Aligning Simulation and Real-World Physics for Learning Agile Humanoid Whole-Body Skills
Tairan He, Jiawei Gao, Wenli Xiao +15
Humanoid robots hold the potential for unparalleled versatility in performing human-like, whole-body skills. However, achieving agile and coordinated whole-body motions remains a s…
HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots
Tairan He, Wenli Xiao, Toru Lin +9
Humanoid whole-body control requires adapting to diverse tasks such as navigation, loco-manipulation, and tabletop manipulation, each demanding a different mode of control. For exa…
OmniH2O: Universal and Dexterous Human-to-Humanoid Whole-Body Teleoperation and Learning
Tairan He, Zhengyi Luo, Xialin He +6
We present OmniH2O (Omni Human-to-Humanoid), a learning-based system for whole-body humanoid teleoperation and autonomy. Using kinematic pose as a universal control interface, Omni…
WoCoCo: Learning Whole-Body Humanoid Control with Sequential Contacts
Chong Zhang, Wenli Xiao, Tairan He +1
Humanoid activities involving sequential contacts are crucial for complex robotic interactions and operations in the real world and are traditionally solved by model-based motion p…
Implicit Safe Set Algorithm for Provably Safe Reinforcement Learning
Weiye Zhao, Feihan Li, Changliu Liu
Deep reinforcement learning (DRL) has demonstrated remarkable performance in many continuous control tasks. However, a significant obstacle to the real-world application of DRL is…
Learning Human-to-Humanoid Real-Time Whole-Body Teleoperation
Tairan He, Zhengyi Luo, Wenli Xiao +4
We present Human to Humanoid (H2O), a reinforcement learning (RL) based framework that enables real-time whole-body teleoperation of a full-sized humanoid robot with only an RGB ca…
Agile But Safe: Learning Collision-Free High-Speed Legged Locomotion
Tairan He, Chong Zhang, Wenli Xiao +3
Legged robots navigating cluttered environments must be jointly agile for efficient task execution and safe to avoid collisions with obstacles or humans. Existing studies either de…
Safe Deep Policy Adaptation
Wenli Xiao, Tairan He, John Dolan +1
A critical goal of autonomy and artificial intelligence is enabling autonomous robots to rapidly adapt in dynamic and uncertain environments. Classic adaptive control and safe cont…
Safe Reinforcement Learning via Hierarchical Adaptive Chance-Constraint Safeguards
Zhaorun Chen, Zhuokai Zhao, Tairan He +4
Ensuring safety in Reinforcement Learning (RL), typically framed as a Constrained Markov Decision Process (CMDP), is crucial for real-world exploration applications. Current approa…
Visual Imitation Learning with Patch Rewards
Minghuan Liu, Tairan He, Weinan Zhang +2
Visual imitation learning enables reinforcement learning agents to learn to behave from expert visual demonstrations such as videos or image sequences, without explicit, well-defin…
State-wise Safe Reinforcement Learning: A Survey
Weiye Zhao, Tairan He, Rui Chen +2
Despite the tremendous success of Reinforcement Learning (RL) algorithms in simulation environments, applying RL to real-world applications still faces many challenges. A major con…
AutoCost: Evolving Intrinsic Cost for Zero-violation Reinforcement Learning
Tairan He, Weiye Zhao, Changliu Liu
Safety is a critical hurdle that limits the application of deep reinforcement learning (RL) to real-world control tasks. To this end, constrained reinforcement learning leverages c…
Reinforcement Learning with Automated Auxiliary Loss Search
Tairan He, Yuge Zhang, Kan Ren +5
A good state representation is crucial to solving complicated reinforcement learning (RL) challenges. Many recent works focus on designing auxiliary losses for learning informative…