FIG.AIFigure 03+BMW.DeployTSLA.BOTOptimus8k.Units.Q1BOS.DYNAtlas+Hyundai.ScaleAGIL.ROBDigit+AMZN.ContractSANC.AIPhoenix+SeriesC.250M1X.TECHNEO Beta-Prod.Delay.Q2APP.TRONApollo+NASA.CollabUNIT.REEH1+China.DeployNEURA4NE-1+Series.B.80MFUND.YTD2026$4.2B.Raised

Research Hub

Key academic papers shaping the development of humanoid robots — locomotion, manipulation, sim-to-real transfer, VLA models, and tactile sensing.

ManipulationJun 20, 2024

HumanPlus: Humanoid Shadowing and Imitation from Humans

Zipeng Fu, Qingqing Zhao, Qi Wu et al. · UC Berkeley

A system enabling humanoid robots to shadow and imitate human motions in real time using egocentric video, achieving robust whole-body control and skill transfer.

Key Finding:Humanoids can learn complex manipulation and locomotion skills by shadowing humans in real time with <100ms latency.
Read paper on arXiv →
VLA ModelsJun 13, 2024

OpenVLA: An Open-Source Vision-Language-Action Model

Moo Jin Kim, Karl Pertsch, Siddharth Karamcheti et al. · Stanford University

OpenVLA is a 7B-parameter open-source VLA model trained on 970k robot demonstrations, achieving state-of-the-art performance on manipulation benchmarks.

Key Finding:7B VLA models generalize to novel objects and environments with 16.5% improvement over prior SoTA.
Read paper on arXiv →
LocomotionMar 15, 2024

Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning

Nikita Rudin, David Hoeller, Philipp Reist et al. · ETH Zurich

Training bipedal locomotion policies in simulation that transfer zero-shot to real hardware, with training completing in under 20 minutes on a single GPU.

Key Finding:Zero-shot sim-to-real locomotion transfer achieved with policies trained in <20 minutes on a single GPU.
Read paper on arXiv →
TactileFeb 10, 2025

Dexterous Manipulation via Tactile Sensing: Closing the Sim-to-Real Gap

Raunaq Bhirangi, Tess Hellebrekers, Carmel Majidi et al. · Carnegie Mellon University

A novel tactile sensor design and simulation framework that enables zero-shot transfer of tactile-guided dexterous manipulation policies to physical robot hands.

Key Finding:Tactile feedback reduces grasp failure rate by 78% in novel object manipulation tasks.
Read paper on arXiv →
VLA ModelsOct 5, 2024

GR-2: Generative Video-Language-Action Model with Web-Scale Knowledge for Robot Manipulation

Wenjie Zhao, Yicheng Liu, Hao Liu · ByteDance Research

GR-2 leverages internet-scale video pretraining to build a generalist manipulation policy that generalizes across robot morphologies and task types.

Key Finding:Web-scale video pretraining enables 3× improvement in zero-shot task generalization across robot morphologies.
Read paper on arXiv →
LocomotionJan 22, 2024

Extreme Parkour with Legged Robots

Ziwen Zhuang, Zipeng Fu, Jianren Wang et al. · Carnegie Mellon University

Training legged robots to perform parkour maneuvers including wall-running, gap jumping, and flipping using a hierarchical RL framework in Isaac Gym.

Key Finding:Hierarchical RL enables bipeds to learn parkour behaviors 40× faster than flat RL baselines.
Read paper on arXiv →
ManipulationApr 1, 2025

Whole-Body Control for Humanoids via Hierarchical Optimization

Guiliang Liu, Shikai Chen, Masayoshi Tomizuka · UC Berkeley

A hierarchical whole-body control framework that simultaneously manages contact forces, task objectives, and joint limits in real time on 42-DOF humanoid platforms.

Key Finding:Hierarchical WBC achieves 120Hz real-time control on 42-DOF humanoids with <2ms compute budget.
Read paper on arXiv →
Sim-to-RealJun 15, 2025

Bridging the Reality Gap in 2025: A Survey of Sim-to-Real Transfer for Humanoid Robots

Marcus Chen, Laura Pérez, Yuki Tanaka et al. · MIT + Stanford + TU Munich

A comprehensive survey of sim-to-real transfer techniques applied to humanoid robots, covering domain randomization, system identification, and adaptive control.

Key Finding:Domain randomization + adaptive control combinations now achieve <5% performance drop in sim-to-real transfer for locomotion tasks.
Read paper on arXiv →