• Home
  • Technology
  • Gaming
  • Entertainment
  • World & Business
  • Science
  • Sports
  • AI
HomeTechnologyGamingEntertainmentWorld & BusinessScienceSportsAI
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI
    AI
    Announcement

    EigenDEXplore uses human hand motion to guide robot exploration

    A post sharing the approach says it avoids confining robot hands to a low-dimensional “eigengrasp” space.

    Shuran SongSS
    Jeannette BohgJB
    Zhaoran WangZW
    6 Sources, ,

    TLDR

    Posts sharing EigenDEXplore describe adding exploration noise along directions learned from human hand motion. Unlike an approach that confines a robot hand to a low-dimensional “eigengrasp” space, they say this leaves robots free to discover motions of their own.

    Combined views

    14.2K

    6 Sources, first seen 5h ago

    Combined views

    14.2K

    6 Sources, first seen 5h ago

    211 likes
    5h ago
    first seen 5h ago
    211 likes
    5 comments
    107 saves
    49 reposts
    Featured Source
    5 comments
    107 saves
    49 reposts

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Today's Rank

    #20

    Today's Rank

    #20

    6 Sources

    Harsh Gupta@hgupt3Per-joint Gaussian noise is a terrible way to explore a 20+ DoF hand We introduce EigenDEXplore, which explores along coordinated patterns from human hand motion, while keeping full control of every joint Better learning, from tool use 🔨 to reorientation 🔄 to bimanual 👐5h
    Tyler Lum@tylerlum23Human fingers move in coordinated patterns. Can those patterns help robots explore? Excited to share EigenDEXplore! 🤖✋ Key idea: add exploration noise along directions learned from human hand motion, while leaving robots free to discover motions of their own See @hgupt3's 🧵5h
    Jeannette Bohg@leto__jeanA new take on an old idea: grasp synergies for learning dexterous manipulation. Instead of confining the hand to a low-dim eigengrasp space, we add exploration noise along directions learned from human hand motion, leaving the robot free to discover motions of its own.4h
    Zhaoran Wang@zhaoran_wangRT @hgupt3: Per-joint Gaussian noise is a terrible way to explore a 20+ DoF hand We introduce EigenDEXplore, which explores along coordina…2h
    Shuran Song@SongShuranIt’s really surprising to me that such a small change in the action exploration space can make such a big difference for dexterous manipulation -- across benchmarks, tasks, hands, and even different learning or optimization algorithms. @hgupt3 tested it on so many settings, and it seems to consistently help. Maybe you try it too!1h

    6 Sources

    Harsh Gupta@hgupt3Per-joint Gaussian noise is a terrible way to explore a 20+ DoF hand We introduce EigenDEXplore, which explores along coordinated patterns from human hand motion, while keeping full control of every joint Better learning, from tool use 🔨 to reorientation 🔄 to bimanual 👐5h
    Tyler Lum@tylerlum23Human fingers move in coordinated patterns. Can those patterns help robots explore? Excited to share EigenDEXplore! 🤖✋ Key idea: add exploration noise along directions learned from human hand motion, while leaving robots free to discover motions of their own See @hgupt3's 🧵5h
    Jeannette Bohg@leto__jeanA new take on an old idea: grasp synergies for learning dexterous manipulation. Instead of confining the hand to a low-dim eigengrasp space, we add exploration noise along directions learned from human hand motion, leaving the robot free to discover motions of its own.4h
    Zhaoran Wang@zhaoran_wangRT @hgupt3: Per-joint Gaussian noise is a terrible way to explore a 20+ DoF hand We introduce EigenDEXplore, which explores along coordina…2h
    Shuran Song@SongShuranIt’s really surprising to me that such a small change in the action exploration space can make such a big difference for dexterous manipulation -- across benchmarks, tasks, hands, and even different learning or optimization algorithms. @hgupt3 tested it on so many settings, and it seems to consistently help. Maybe you try it too!1h