Papers

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.

HumanoidTable TennisWhole-Body ControlZhi Su, Bike Zhang, Nima Rahmanian·Aug 28, 2025

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.

Unitree G1MoESim-to-RealShihao Ma, Hongjin Chen, Zijun Xu·Mar 3, 2026

First Deployable Dynamic-CoM: A Unified Policy and Method-Agnostic Benchmark for Humanoid Single-Leg Balance

FDDC embeds the first deployable dynamic center-of-mass (xCoM) observation directly into the on-hardware actor and pairs it with a reward library translated from human postural control, holding clean single-leg balance on 86 of 90 motions and transferring to a real Unitree G1.

xCoMSim-to-RealUnitree G1Yikai Zhou, Xingyun Wang, Jieming Cui·Aug 1, 2026

Cross-Embodiment Robot Manipulation via a Unified Hand Action Space

Robot manipulation policies are typically tied to specific robotic hand embodiments, limiting the transfer of learned behaviors across platforms with different kinematic structures. In this work, we propose the Unified Hand Action Space (UHAS), a sphere-based unified action representation for cross-embodiment dexterous manipulation. UHAS represents robotic hand actions as geometric deformations of a canonical sphere and uses a Cascade Inverse Kinematics (CIK) algorithm to map the shared representation to embodiment-specific joint configurations. Using reinforcement learning, we train dexterous manipulation policies directly in the proposed action space for in-hand cube reorientation tasks. We evaluate our method in both simulation and real-world experiments across multiple robotic hands, including the Allegro Hand, LEAP Hand, Shadow Hand, and MANO Human Hand. Experimental results demonstrate effective dexterous manipulation, zero-shot transfer to unseen hands, rapid finetuning across embodiments, and successful real-world deployment.

Dexterous ManipulationCross-EmbodimentReinforcement LearningLuis Felipe Casas, Robert Teal, Keval Shah·Jul 3, 2026

SimWAM: A Simple World Action Model for End-to-End Autonomous Driving

World-Action Models (WAMs) improve end-to-end autonomous driving by transferring video dynamics priors to action prediction, but existing methods require costly future generation at inference. We present SimWAM, a simple yet effective WAM that uses video generation purely as a training signal. It co-trains a pretrained video expert and a lightweight action expert with joint flow matching. An isolated attention mask keeps action prediction independent of future frames, allowing the video branch to be discarded after training and leaving a self-contained planner that directly predicts trajectories. Since the two experts share no parameters and interact only through a unified attention interface, the video backbone could be replaced and the action expert scaled independently without modifying the learning objective or inference pipeline. We further apply reinforcement learning to optimize a compositional driving reward beyond trajectory imitation. Our SimWAM achieves $91.5$ PDMS on NAVSIM, surpasses state-of-the-art WAM-based planners with substantially lower latency, and transfers zero-shot to nuScenes. These results position SimWAM as a simple yet solid baseline that could readily benefit from advances in video generation for efficient autonomous driving. The code and model weights are available at https://github.com/H-EmbodVis/SimWAM/

NAVSIMSimWAMWorld-action modelsZongchuang Zhao, Xin Zhou, Tianyang Xu·Aug 7, 2026

Learning a Unified Policy for Position and Force Control in Legged Loco-Manipulation

Robotic loco-manipulation tasks often involve contact-rich interactions, requiring joint modeling of contact force and robot position. We propose a unified policy for legged robots that jointly models force and position control without relying on force sensors, and improves contact-rich imitation learning by approximately 39.5%.

UnitreeCoRL 2025Legged robotsPeiyuan Zhi, Peiyang Li, Jianqin Yin·May 27, 2025

RL²-VLA: Adaptive RL Latent Compositional Steering with Test-Time Scaling for Vision-Language-Action Models

Despite the impressive visuomotor capabilities enabled by Vision-Language-Action (VLA) models, their performance often degrades on challenging and out-of-domain tasks. Recent test-time steering and scaling methods improve performance without extensive data collection and retraining, but action samples often remain concentrated around similar behaviors and therefore inherit correlated failure modes. Moreover, existing methods apply the same intervention strategy at every timestep, regardless of whether the base policy is already likely to succeed. To address these limitations, we introduce RL², an adaptive inference-time steering framework that leverages Reinforcement Learning on VLA Latents. First, we train a lightweight offline RL policy conditioned on expressive latents extracted from the VLA action expert and compose its flow velocity with that of the frozen VLA during inference. This compositional steering strategy combines the behavioral priors of large-scale imitation learning with the action diversity induced by offline RL beyond dominant demonstration modes. We further discover that inference-time steering follows fundamentally different scaling laws under success and failure states, revealing that action diversity is most beneficial when the base VLA is likely to fail, but can unnecessarily perturb already-accurate actions when success is likely. Building on this insight, RL² activates compositional steering only when failure is predicted. Across the SIMPLER and PolaRiS benchmarks, RL² improves success rates by up to +17.3% in out-of-domain settings, while ablations and scaling studies demonstrate the importance of latent representations and RL training. Finally, real-world experiments demonstrate that these gains transfer beyond simulation, establishing RL² as a practical and modular steering framework for VLA deployment.

VLARL2-VLAReinforcement LearningDerek Ming Siang Tan, Shailesh Shailesh, Srikrishna Iyer·Jul 29, 2026

X-NavDP: Generalizing Navigation Diffusion Policy to Novel Behavior and Embodiments with Group Q-score Reweighted Matching

Proposes GQRM, a data-efficient diffusion RL post-training framework with self-bootstrapped exploration and group Q-score normalization for cross-embodiment visual navigation. Improves success rate from 61.20% to 84.28% in simulation and 10% to 65% in real-world hard cases.

NavDPVLANavigationTianyu Yang, Yiming Zeng, Wenzhe Cai·Jul 30, 2026

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/.

Sim-to-RealUnitree G1Fall RecoveryTao Huang, Junli Ren, Huayi Wang·Feb 12, 2025

Learning Whole-Body Humanoid Locomotion via Motion Generation and Motion Tracking

Whole-body humanoid locomotion is challenging due to high-dimensional control, morphological instability, and the need for real-time adaptation to various terrains using onboard perception. Directly applying reinforcement learning (RL) with reward shaping to humanoid locomotion often leads to lower-body-dominated behaviors, whereas imitation-based RL can learn more coordinated whole-body skills but is typically limited to replaying reference motions without a mechanism to adapt them online from perception for terrain-aware locomotion. To address this gap, we propose a whole-body humanoid locomotion framework that combines skills learned from reference motions with terrain-aware adaptation. We first train a diffusion model on retargeted human motions for real-time prediction of terrain-aware reference motions. Concurrently, we train a whole-body reference tracker with RL using this motion data. To improve robustness under imperfectly generated references, we further fine-tune the tracker with a frozen motion generator in a closed-loop setting. The resulting system supports directional goal-reaching control with terrain-aware whole-body adaptation, and can be deployed on a Unitree G1 humanoid robot with onboard perception and computation. The hardware experiments demonstrate successful traversal over boxes, hurdles, stairs, and mixed terrain combinations. Quantitative results further show the benefits of incorporating online motion generation and fine-tuning the motion tracker for improved generalization and robustness.

HumanoidWhole-body locomotionMotion GenerationZewei Zhang, Kehan Wen, Michael Xu·Apr 19, 2026

Multi-Gait Learning for Humanoid Robots Using Reinforcement Learning with Selective Adversarial Motion Prior

Learning diverse locomotion skills for humanoid robots in a unified reinforcement learning framework remains challenging due to the conflicting requirements of stability and dynamic expressiveness across different gaits. We present a multi-gait learning approach that enables a humanoid robot to master five distinct gaits – walking, goose-stepping, running, stair climbing, and jumping – using a consistent policy structure, action space, and reward formulation. The key contribution is a selective Adversarial Motion Prior (AMP) strategy: AMP is applied to periodic, stability-critical gaits (walking, goose-stepping, stair climbing) where it accelerates convergence and suppresses erratic behavior, while being deliberately omitted for highly dynamic gaits (running, jumping) where its regularization would over-constrain the motion. Policies are trained via PPO with domain randomization in simulation and deployed on a physical 12-DOF humanoid robot through zero-shot sim-to-real transfer. Quantitative comparisons demonstrate that selective AMP outperforms a uniform AMP policy across all five gaits, achieving faster convergence, lower tracking error, and higher success rates on stability-focused gaits without sacrificing the agility required for dynamic ones.

HumanoidMultigaitReinforcement LearningYuanye Wu, Keyi Wang, Linqi Ye·Apr 21, 2026

Learning Humanoid Locomotion with Perceptive Internal Model

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, incorporating perceptual signals often introduces additional disturbances to the system, potentially reducing its robustness, generalizability, and efficiency. This paper presents the Perceptive Internal Model (PIM), which relies on onboard, continuously updated elevation maps centered around the robot to perceive its surroundings. We train the policy using ground-truth obstacle heights surrounding the robot in simulation, optimizing it based on the Hybrid Internal Model (HIM), and perform inference with heights sampled from the constructed elevation map. Unlike previous methods that directly encode depth maps or raw point clouds, our approach allows the robot to perceive the terrain beneath its feet clearly and is less affected by camera movement or noise. Furthermore, since depth map rendering is not required in simulation, our method introduces minimal additional computational costs and can train the policy in 3 hours on an RTX 4090 GPU. We verify the effectiveness of our method across various humanoid robots, various indoor and outdoor terrains, stairs, and various sensor configurations. Our method can enable a humanoid robot to continuously climb stairs and has the potential to serve as a foundational algorithm for the development of future humanoid control methods.

HumanoidInternal Perception ModelReinforcement LearningJunfeng Long, Junli Ren, Moji Shi·Nov 21, 2024