仅需Python基础，从0构建自己的具身智能机器人；从0逐步构建VLA/OpenVLA/SmolVLA/Pi0， 深入理解具身智能

FastCrest Tether: the OSS edge-to-cloud AI deploy CLI. Optimize, verify, deploy across Jetson, RTX, Apple Silicon, AMD. Hybrid edge-cloud inference with parity certs.

This repository implements pi0, pi0fast and smolvla models on sim and real robots using Lerobot interface

实机部署so101流程和踩坑全记录，使用lerobot框架so101真机。在本地 ubuntu22+5070显卡 搭建环境，部署，录数据，训练smolvla，推理全流程。

Unified pipeline for collecting, labeling, converting, and training robot demonstration data with SmolVLA, Pi0, Pi0.5, or ACT policies - extended with Qwen3-VL offline phase annotation, a runtime FSM, and three phase-conditioned policy variants.

A heterogeneous dual-model robot navigation system pairing Falcon Mamba (SSM) as a fast reflex layer with SmolVLA (VLA) as a deliberate planning layer, arbitrated by a priority controller, fully simulatable in Wokwi on ESP32. as a part of learning project.

Manual real‑world benchmarking of ACT/SmolVLA on a physical SO101 robot using LeRobot.

Reproducing SmolVLA-450M on LIBERO benchmark with cross-embodiment experiments | LeRobot

RoboPwn — red-team open Vision-Language-Action (VLA) robot policies in simulation and report an Attack Success Rate (ASR). CPU-first, model-agnostic, Apache-2.0.

Per-Group Error, Not Total MSE. Fine-tuning VLAs on the Toyota HSR. ICRA 2026 Workshop From Data to Decisions, 1st place out of 36.

Robotics simulation project for SmolVLA policy inference in ALOHA insertion and vision-based VX300s teleoperation using MuJoCo, MediaPipe, YOLO, Depth Anything V2, and damped least-squares IK.