Physical AI

PAPERMar 3, 2026

CMoE: Contrastive Mixture of Experts for Motion Control and Terrain Adaptation of Humanoid Robots

CMoE uses contrastive learning to improve MoE expert specialization for humanoid terrain navigation. Validated on Unitree G1, achieving robust gait over 20cm steps and 80cm gaps.

Shihao Ma, Hongjin Chen, Zijun Xu

Unitree G1MoE

PAPERFeb 17, 2026

Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching

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 environments demands not only low-level robustness, but also human-like motion expressiveness, long-horizon skill composition, and perception-driven decision-making. In this paper, we present Perceptive Humanoid Parkour (PHP), a modular framework that enables humanoid robots to autonomously perform long-horizon, vision-based parkour across challenging obstacle courses. Our approach first leverages motion matching, formulated as nearest-neighbor search in a feature space, to compose retargeted atomic human skills into long-horizon kinematic trajectories. This framework enables the flexible composition and smooth transition of complex skill chains while preserving the elegance and fluidity of dynamic human motions. Next, we train motion-tracking reinforcement learning (RL) expert policies for these composed motions, and distill them into a single depth-based, multi-skill student policy, using a combination of DAgger and RL. Crucially, the combination of perception and skill composition enables autonomous, context-aware decision-making: using only onboard depth sensing and a discrete 2D velocity command, the robot selects and executes whether to step over, climb onto, vault or roll off obstacles of varying geometries and heights. We validate our framework with extensive real-world experiments on a Unitree G1 humanoid robot, demonstrating highly dynamic parkour skills such as climbing tall obstacles up to 1.25m (96% robot height), as well as long-horizon multi-obstacle traversal with closed-loop adaptation to real-time obstacle perturbations.

Zhen Wu, Xiaoyu Huang, Lujie Yang

HumanoidParkour

VIDEOFeb 9, 2026

Teaching Robots Like Dogs

A human-in-the-loop framework teaches quadruped robots agile navigation from luring, gesture, and speech using simulation-based scene reconstruction, data augmentation, and progressive goal cueing.

PAPERJan 30, 2026

ZEST: Zero-shot Embodied Skill Transfer for Athletic Robot Control

Achieving robust, human-like whole-body control on humanoid robots for agile, contact-rich behaviors remains a central challenge, demanding heavy per-skill engineering and a brittle process of tuning controllers. We introduce ZEST (Zero-shot Embodied Skill Transfer), a streamlined motion-imitation framework that trains policies via reinforcement learning from diverse sources – high-fidelity motion capture, noisy monocular video, and non-physics-constrained animation – and deploys them to hardware zero-shot. ZEST generalizes across behaviors and platforms while avoiding contact labels, reference or observation windows, state estimators, and extensive reward shaping. Its training pipeline combines adaptive sampling, which focuses training on difficult motion segments, and an automatic curriculum using a model-based assistive wrench, together enabling dynamic, long-horizon maneuvers. We further provide a procedure for selecting joint-level gains from approximate analytical armature values for closed-chain actuators, along with a refined model of actuators. Trained entirely in simulation with moderate domain randomization, ZEST demonstrates remarkable generality. On Boston Dynamics' Atlas humanoid, ZEST learns dynamic, multi-contact skills (e.g., army crawl, breakdancing) from motion capture. It transfers expressive dance and scene-interaction skills, such as box-climbing, directly from videos to Atlas and the Unitree G1. Furthermore, it extends across morphologies to the Spot quadruped, enabling acrobatics, such as a continuous backflip, through animation. Together, these results demonstrate robust zero-shot deployment across heterogeneous data sources and embodiments, establishing ZEST as a scalable interface between biological movements and their robotic counterparts.

Jean Pierre Sleiman, He Li, Alphonsus Adu-Bredu

ZESTSim-to-Real

PAPERDec 22, 2025

A Framework for Deploying Learning-based Quadruped Loco-Manipulation

Quadruped mobile manipulators offer strong potential for agile loco-manipulation but remain difficult to control and transfer reliably from simulation to reality. Reinforcement learning (RL) shows promise for whole-body control, yet most frameworks are proprietary and hard to reproduce on real hardware. We present an open pipeline for training, benchmarking, and deploying RL-based controllers on the Unitree B1 quadruped with a Z1 arm. The framework unifies sim-to-sim and sim-to-real transfer through ROS, re-implementing a policy trained in Isaac Gym, extending it to MuJoCo via a hardware abstraction layer, and deploying the same controller on physical hardware. Sim-to-sim experiments expose discrepancies between Isaac Gym and MuJoCo contact models that influence policy behavior, while real-world teleoperated object-picking trials show that coordinated whole-body control extends reach and improves manipulation over floating-base baselines. The pipeline provides a transparent, reproducible foundation for developing and analyzing RL-based loco-manipulation controllers and will be released open source to support future research.

Yadong Liu, Jianwei Liu, He Liang

Sim-to-RealROS

PAPERNov 30, 2025

Autonomous Grasping On Quadruped Robot With Task Level Interaction

Quadruped robots are increasingly used in various applications due to their high mobility and ability to operate in diverse terrains. However, most available quadruped robots are primarily focused on mobility without object manipulation capabilities. Equipping a quadruped robot with a robotic arm and gripper introduces a challenge in manual control, especially in remote scenarios that require complex commands. This research aims to develop an autonomous grasping system on a quadruped robot using a task-level interaction approach. The system includes hardware integration of a robotic arm and gripper onto the quadruped robot's body, a layered control system designed using ROS, and a web-based interface for human-robot interaction. The robot is capable of autonomously performing tasks such as navigation, object detection, and grasping using GraspNet. Testing was conducted through real-world scenarios to evaluate navigation, object selection and grasping, and user experience. The results show that the robot can perform tasks accurately and consistently, achieving a grasping success rate of 75 % from 12 trials. Therefore, the system demonstrates significant potential in enhancing the capabilities of quadruped robots as service robots in real-world environments.

Muhtadin, Mochammad Hilmi Rusydiansyah, Mauridhi Hery Purnomo

Quadruped robotsAut-Navigation

PAPERNov 19, 2025

VIRAL: Visual Sim-to-Real at Scale for Humanoid Loco-Manipulation

VIRAL is a visual sim-to-real framework from NVIDIA GEAR and CMU: a privileged RL teacher masters long-horizon loco-manipulation with a delta action space, staged rewards, and reference state initialization, then a student policy using only RGB is distilled at scale on 64 GPUs via a DAgger-BC mixture, with dexterous-hand SysID, camera extrinsics alignment, and four-axis visual randomization. Deployed zero-shot on a Unitree G1, it succeeds on 54 of 59 real trials at 20.2 s per cycle — faster than expert teleoperation — and generalizes across nine environment variations. Ablations show compute scale is a passing grade, not an accelerator; code, models, and the full reward table are open-sourced.

He, Tairan, Wang, Zi, Xue, Haoru

HumanoidSim-to-Real

PAPERAug 28, 2025

HITTER: A HumanoId Table TEnnis Robot via Hierarchical Planning and Learning

HITTER couples a model-based planner (ball trajectory prediction, strike position/velocity/timing) with an RL whole-body controller trained on human forehand/backhand motion references, enabling a Unitree G1 to sustain rallies of up to 106 consecutive shots against a human opponent.

Zhi Su, Bike Zhang, Nima Rahmanian

HumanoidTable Tennis

PAPERJun 15, 2025

KungfuBot: Physics-Based Humanoid Whole-Body Control for Learning Highly-Dynamic Skills

A physics-based whole-body control framework that combines contact-aware motion filtering, differentiable IK retargeting, and adaptive RL tracking to teach Unitree G1 highly dynamic skills from human motion.

Weiji Xie, Jinrui Han, Jiakun Zheng

HumanoidWhole-Body Control

PAPERFeb 12, 2025

Learning Humanoid Standing-up Control across Diverse Postures

Standing-up control is crucial for humanoid robots, with the potential for integration into current locomotion and loco-manipulation systems, such as fall recovery. Existing approaches are either limited to simulations that overlook hardware constraints or rely on predefined ground-specific motion trajectories, failing to enable standing up across postures in real-world scenes. To bridge this gap, we present HoST (Humanoid Standing-up Control), a reinforcement learning framework that learns standing-up control from scratch, enabling robust sim-to-real transfer across diverse postures. HoST effectively learns posture-adaptive motions by leveraging a multi-critic architecture and curriculum-based training on diverse simulated terrains. To ensure successful real-world deployment, we constrain the motion with smoothness regularization and implicit motion speed bound to alleviate oscillatory and violent motions on physical hardware, respectively. After simulation-based training, the learned control policies are directly deployed on the Unitree G1 humanoid robot. Our experimental results demonstrate that the controllers achieve smooth, stable, and robust standing-up motions across a wide range of laboratory and outdoor environments. Videos and code are available at https://taohuang13.github.io/humanoid-standingup.github.io/.

Tao Huang, Junli Ren, Huayi Wang

Sim-to-RealUnitree G1

PAPER

DexPoint: Generalizable Point Cloud Policies for Dexterous Manipulation

DexPoint uses point cloud representations for generalizable dexterous manipulation without CAD models, showing strong sim-to-real transfer.

CMU, UC Berkeley

Dexterous HandPoint clouds

As an Amazon Associate, we earn from qualifying purchases.