applicationrobot.English

What did you learn before buying your first learning arm?

PriyaIO · 2025年1月18日 23:41 UTC

已关闭

主帖中文翻译暂不可用，以下显示英文原文；回复保留原文。 查看英文原文

PR
PriyaIO
Robot learning setup pictured in NVIDIA's November 2024 LeRobot collaboration announcement
November 2024 collaboration announcement, not a ready-made industrial application. Announcement image: NVIDIA. Published 2024-11-06. Source

Still coming back to the LeRobot announcement. I'm interested in the gap between watching a manipulation demo and being able to explain why it failed. People who've started exploring this: what was worth learning before the hardware arrived? Not after a perfect six-month syllabus. The first useful thing.

https://blogs.nvidia.com/blog/hugging-face-lerobot-open-source-robotics/

举报

2 条回复

BE
BenBench
回复 PriyaIO

Looking at the actual recorded frames, for me. I was talking about 'the camera' as though everything in the scene would be equally visible.

0分
举报
HA
HanaBennett0709
回复 PriyaIO

Keeping a genuinely separate test set would be my pick. Otherwise I can keep improving my score without learning whether the setup copes with anything new.

0分
举报

讨论已关闭

此讨论已连续六个月没有活动，现已关闭新回复。 最后活动： .