Track 3, Ethan Yeang, BotverseX - #329
Open
metahubaifeel wants to merge 3 commits into
Open
Conversation
…ack 3) One website for the full loop: connect → teleoperate → record → train → deploy for real robot runtimes (SO-101, Reachy Mini, B601-RS, LeKiwi, Unitree G1). LeRobot-format parquet datasets; local training on AMD Radeon GPUs via ROCm (Strix Halo gfx1151, torch 2.10.0+rocm7.0); zero-install SO-101 control via Web Serial. See docs/hackathon-2026-07/technical-report.md and reproducibility.md.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
1 participant
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
BotverseX — embodied-AI data-loop platform (Track 3)
Team: Ethan Yeang (杨智超) · GitHub: metahubaifeel · ethanyeang / yeangethan
Contact: +86 19120810409 · https://botversex.feispace.me
License: AGPL-3.0 — Copyright (c) 2026 Ethan Yeang. All Rights Reserved.
One website for the full loop: connect → teleoperate → record → train → deploy for real robot runtimes (SO-101, Reachy Mini, B601-RS, LeKiwi, Unitree G1, AmazingHand).
LeRobot-format parquet datasets; local training on AMD Radeon GPUs via ROCm (Strix Halo gfx1151, torch 2.10.0+rocm7.0, 64 GB unified memory); zero-install SO-101 control via Web Serial API.
Materials
AMD Radeon / ROCm
Local training unblocked on Radeon 8060S (gfx1151) — torch 2.10.0+rocm7.0 / torchvision 0.25.0+rocm7.0 / pytorch-triton-rocm 3.5.1, one-command env (rocm_env.sh), crash-safe subprocess GPU probe endpoint.