AI Research 技术调研

标签: quadruped-manipulation

此标签下有3条笔记。

  • 2026年7月16日

    Deep Whole-Body Control: Learning a Unified Policy for Manipulation and Locomotion

    • whole-body-control
    • legged-manipulator
    • quadruped-manipulation
    • reinforcement-learning
    • sim-to-real
    • advantage-mixing
    • regularized-online-adaptation
    • ppo
    • isaac-gym
    • unitree-go1
  • 2026年7月16日

    Helpful DoggyBot: Open-World Object Fetching using Legged Robots and Vision-Language Models

    • legged-locomotion
    • quadruped-manipulation
    • unitree-go2
    • vision-language-model
    • zero-shot-generalization
    • sim-to-real
    • florence-2
    • sam2
    • whole-body-control
    • open-vocabulary
  • 2026年7月16日

    UMI on Legs: Making Manipulation Policies Mobile with Manipulation-Centric Whole-body Controllers

    • quadruped-manipulation
    • whole-body-control
    • umi
    • diffusion-policy
    • cross-embodiment
    • sim2real
    • reinforcement-learning
    • end-effector-trajectory
    • task-frame-tracking
    • corl-2024

  • GitHub