Humanoid Robotics Comparison Hub

Reference Surfaces

Top Papers

• SCDP: Learning Humanoid Locomotion from Partial Observations via Mixed-Observation Distillation(8.0)

  SCDP enables humanoid locomotion using only onboard sensors, eliminating the need for complex state estimation.

• $Ψ_0$: An Open Foundation Model Towards Universal Humanoid Loco-Manipulation(8.0)

  Psi-Zero open sources a superior foundation model for humanoid robot loco-manipulation tasks with state-of-the-art performance using efficient training data.

• Perceptive Humanoid Parkour: Chaining Dynamic Human Skills via Motion Matching(7.0)

  Enable humanoid robots to autonomously perform agile parkour using motion matching and onboard perception.

• SPARK: Skeleton-Parameter Aligned Retargeting on Humanoid Robots with Kinodynamic Trajectory Optimization(7.0)

  A two-stage pipeline for generating natural and dynamically feasible motion references for humanoid robots using human motion data.

• Kinodynamic Motion Retargeting for Humanoid Locomotion via Multi-Contact Whole-Body Trajectory Optimization(7.0)

  KinoDynamic Motion Retargeting optimizes humanoid locomotion through advanced trajectory techniques, enhancing stability and performance.

• ZeroWBC: Learning Natural Visuomotor Humanoid Control Directly from Human Egocentric Video(7.0)

  ZeroWBC enables natural humanoid robot control from human egocentric videos, eliminating the need for costly teleoperation data.

• Learning Human-Like Badminton Skills for Humanoid Robots(6.0)

  Develop humanoid robots with human-like badminton skills using a reinforcement learning framework for real-world applications.

• Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning(5.0)

  AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

• Cybo-Waiter: A Physical Agentic Framework for Humanoid Whole-Body Locomotion-Manipulation(3.0)

  A humanoid agent framework for executing complex tasks through advanced locomotion and manipulation.