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

    Microduck robot reportedly finds its position again after being carried across a room

    A tester says Microduck uses leg odometry and an 8×8 depth sensor to locate itself without external tracking.

    Chris PaxtonCP
    Antoine PirroneAP
    2 Sources, 5h ago, first seen 5h ago

    TLDR

    A tester says Microduck's SLAM runs onboard using leg odometry and an 8×8 depth sensor, with camera-tracked tags used only to check accuracy. Its position at each stop was off by a median 4.8 cm; when it claimed to know its location, it was within 15 cm 94% of the time. The tester reports it relocalized after two 1.5 m carries and a fall, and never picked the wrong place across benchmark sessions.

    Combined views

    3.8K

    2 Sources, first seen 5h ago

    99 likes2 comments31 saves22 reposts

    Combined views

    3.8K

    2 Sources, first seen 5h ago

    99 likes2 comments31 saves22 reposts
    Image: @antoinepirrone on X

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    Featured Source

    Sentiment

    Positive——Negative

    Summary

    Not enough discussion yet.

    No sentiment analysis available yet.

    2 Sources

    Antoine Pirrone@antoinepirroneTesting Microduck's SLAM! It runs fully onboard, with just its leg odometry and the 8×8 ToF sensor in its head, 64 pixels of depth. Carry it across the room and it finds itself again after a few steps. The ArUco tags are only there for ground truth: a fixed camera tracks the one on its head, and the duck never uses them. Against that ground truth, its position at each stop is off by 4.8 cm on median, and 94% of the time it claims to know where it is, it's within 15 cm. In this session it relocalized after a 1.5 m carry (2 cm off), a seated 1.5 m carry (11 cm) and a fall (3 cm), and across our benchmark sessions it never relocalized to the wrong place.5h
    Chris Paxton@chris_j_paxtonRT @antoinepirrone: Testing Microduck's SLAM! It runs fully onboard, with just its leg odometry and the 8×8 ToF sensor in its head, 64 pix…1h
    • Home
    • Technology
    • Gaming
    • Entertainment
    • World & Business
    • Science
    • Sports
    • AI

    2 Sources

    Antoine Pirrone@antoinepirroneTesting Microduck's SLAM! It runs fully onboard, with just its leg odometry and the 8×8 ToF sensor in its head, 64 pixels of depth. Carry it across the room and it finds itself again after a few steps. The ArUco tags are only there for ground truth: a fixed camera tracks the one on its head, and the duck never uses them. Against that ground truth, its position at each stop is off by 4.8 cm on median, and 94% of the time it claims to know where it is, it's within 15 cm. In this session it relocalized after a 1.5 m carry (2 cm off), a seated 1.5 m carry (11 cm) and a fall (3 cm), and across our benchmark sessions it never relocalized to the wrong place.5h
    Chris Paxton@chris_j_paxtonRT @antoinepirrone: Testing Microduck's SLAM! It runs fully onboard, with just its leg odometry and the 8×8 ToF sensor in its head, 64 pix…1h
    Today's Rank

    —

    Not ranked yet

    Today's Rank

    —

    Not ranked yet