PAC-MAN: Perception-Aware CBF-RL for Whole-Body Safety in Humanoid Dodgeball - 2026-07-30 - Research Publication - PAC-MAN couples onboard depth perception with control-barrier-guided reinforcement learning for humanoid ball evasion. A Link-CBF policy was deployed zero-shot on a physical Unitree G1 and succeeded on 95% of seeded… - source: arxiv.org
Learning Reusable Hybrid Motion Priors for Humanoid Locomotion from Motion Imitation - 2026-07-27 - Research Publication - The method distils motion-imitation skills into a frozen hybrid motion prior with a residual vector-quantized codebook. A zero-shot physical Unitree G1 deployment tracked forward and lateral commands, in-place turns… - source: arxiv.org
What Matters in Humanoid General Motion Tracking? An Empirical Study - 2026-07-22 - Research Publication - YAHMP provides an open modular framework for controlled comparisons of humanoid motion-tracking design choices. Selected policies were deployed zero-shot on a physical Unitree G1 for diverse whole-body reference tracking.… - source: arxiv.org
Closing the Lab-to-Store Gap: A Data-Efficient Post-Training and Experience-Driven Learning VLA Framework for Retail Humanoids - 2026-07-22 - Research Publication - DEED combines data curation, control-frequency alignment and experience-driven refinement for retail humanoid VLA deployment. The framework was evaluated on a physical Unitree G1-Edu performing a supermarket… - source: arxiv.org
Learning Adaptive Safety Margins for Visual Navigation - 2026-07-20 - Research Publication - The method learns context-dependent navigation clearance preferences from privileged simulation geometry. A perception-only selector transfers from simulation to a physical Unitree G1. The G1 navigated cluttered indoor… - source: arxiv.org
Closing the Loop in Humanoid VLA: Persistent 3D Object Tokens for Verifiable Loco-Manipulation - 2026-07-20 - Research Publication - POT-VLA maintains persistent role-indexed 3D object records for closed-loop humanoid action and verification. On a physical Unitree G1, POT-VLA achieved 71 of 80 successes across eight real-world task families. The paper… - source: arxiv.org
EgoHTR: Egocentric 4D Demonstrations of Human Terrain Traversal - 2026-07-15 - Research Publication - EgoHTR contains 55 scene-aligned 4D human-motion sequences and more than 150,000 frames captured with portable egocentric and 3D sensing. The dataset supplies terrain-aligned reference motion and foot-contact annotations… - source: arxiv.org
RoboTacDex: A Dexterous Visual-Tactile-Action Dataset for Humanoid Manipulation - 2026-06-30 - Research Publication - In the field of robot learning, large-scale and diverse demonstration trajectories provide the fundamental basis for enhancing robotic manipulation ability. Built on the publicly accessible humanoid robot Unitree G1… - source: arxiv.org
ReactiveBFM: Reactive Closed-Loop Motion Planning Towards Universal Humanoid Whole-Body Control - 2026-06-29 - Research Publication - While current Behavior Foundation Models (BFMs) provide robust control priors for humanoids, they only execute pre-defined reference motions. Deployed on the Unitree G1 humanoid, ReactiveBFM demonstrates unprecedented… - source: arxiv.org
VLK: Learning Humanoid Loco-Manipulation from Synthetic Interactions in Reconstructed Scenes - 2026-06-29 - Research Publication - Learning this mapping requires synchronized egocentric images, language commands, and robot-compatible kinematic trajectories, yet no existing data source provides this complete tuple at scale. A whole-body tracker… - source: arxiv.org
TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes - 2026-06-24 - Research Publication - The paper “TaskNPoint: How to Teach Your Humanoid to Hit a Backhand in Minutes” was published on June 24, 2026. The arXiv paper teaches dynamic backhand-hitting skills on a Unitree G1 humanoid. The study’s named evaluation… - source: arxiv.org
Learning Asynchronous Upper-body Task-space Trajectory Tracking Policy for Humanoid Robots - 2026-06-24 - Research Publication - The paper “Learning Asynchronous Upper-body Task-space Trajectory Tracking Policy for Humanoid Robots” was published on June 24, 2026. The arXiv paper studies asynchronous upper-body task-space tracking on Unitree G1. The… - source: arxiv.org
RGB: RL Guided Whole-Body MPPI for Humanoid Control - 2026-06-23 - Research Publication - The arXiv paper combines reinforcement learning and MPPI for whole-body humanoid control on Unitree G1. The study’s named evaluation platform is G1 from Unitree. - source: arxiv.org
LP-NavOA: Integrated Local Navigation and Obstacle Avoidance for Humanoid Robots under Limited Perception - 2026-06-22 - Research Publication - The arXiv paper evaluates local navigation and obstacle avoidance on Unitree G1 under limited perception. The study’s named evaluation platform is G1 from Unitree. - source: arxiv.org
CoorDex: Coordinating Body and Hand Priors for Continuous Dexterous Humanoid Loco-Manipulation - 2026-06-22 - Research Publication - The arXiv paper coordinates body and hand priors for continuous dexterous loco-manipulation on Unitree G1. The study’s named evaluation platform is G1 from Unitree. - source: arxiv.org
TEXEDO: Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation - 2026-06-22 - Research Publication - The paper “TEXEDO: Test Time Scaling for Controller-aware Language-conditioned Humanoid Motion Generation” was published on June 22, 2026. The arXiv paper studies controller-aware language-conditioned humanoid motion… - source: arxiv.org
VQActFlow: Vector-Quantized Action Mode Steering for Multi-Task Robot Manipulation - 2026-06-19 - Research Publication - The paper “VQActFlow: Vector-Quantized Action Mode Steering for Multi-Task Robot Manipulation” was published on June 19, 2026. The arXiv paper studies vector-quantized action-mode steering for multi-task robot manipulation… - source: arxiv.org
Duet: Dual-Robot Understanding via Efficient Teaching - 2026-06-18 - Research Publication - The paper “Duet: Dual-Robot Understanding via Efficient Teaching” was published on June 18, 2026. The arXiv paper studies dual-robot understanding via efficient teaching with Unitree G1. The study’s named evaluation… - source: arxiv.org
HALOMI: Learning Humanoid Loco-Manipulation with Active Perception from Human Demonstrations - 2026-06-17 - Research Publication - The arXiv paper learns humanoid loco-manipulation with active perception from human demonstrations on Unitree G1. The study’s named evaluation platform is G1 from Unitree. - source: arxiv.org
ADAPT: Analytical Disturbance-Aware Policy Training for Humanoid Locomotion - 2026-06-15 - Research Publication - Humanoids deployed in human-centered environments must handle force-interactive tasks, where external contacts introduce unexpected disturbances that disrupt locomotion accuracy and stability. Experiments on a Unitree G1… - source: arxiv.org
Steering Generative Reinforcement Learning into Stable Robotic Controller - 2026-06-15 - Research Publication - The paper “Steering Generative Reinforcement Learning into Stable Robotic Controller” was published on June 15, 2026. The arXiv paper studies stable generative reinforcement-learning controllers on Unitree G1. The study’s… - source: arxiv.org
Identification of a Physics-Based Electrical Power Consumption Model for the Unitree G1 Humanoid Arm - 2026-06-14 - Research Publication - Accurate prediction of electrical power consumption is essential for energy-aware motion planning, battery management, and thermal monitoring in battery-powered humanoid robots. This letter presents a physics-based… - source: arxiv.org
Energy-Efficient Arm Reaching for a Humanoid Robot via Deep Reinforcement Learning with Identified Power Models - 2026-06-14 - Research Publication - The paper presents an end-to-end, energy-aware reinforcement learning framework for the 7-degree-of-freedom left arm of the Unitree G1 humanoid robot, combining a physics-based, experimentally identified electrical power… - source: arxiv.org
Whole-Body Impedance Model Predictive Control for Safe Physical Human--Robot Interaction on Floating-Base Platforms - 2026-06-12 - Research Publication - The authors develop a contact-consistent normalization in which the residual end-effector channel is represented as a linear double integrator in acceleration coordinates. MuJoCo experiments on a 17-DOF biped and a… - source: arxiv.org