rdk-embodied-lerobot

rdk-embodied-lerobot is an Embedded, IoT & robotics skill for AI agents, published by D-Robotics in the moss repository on GitHub. Skillspace rates rdk-embodied-lerobot C (72/100) and it passed the safety scan; the rating is based on static analysis only.

Deploy a trained embodied-AI policy onto an RDK board — LeRobot ACT imitation policies and Pi0 VLA (openpi) — by exporting to ONNX, compiling to a BPU `.hbm`, and running the on-board control loop that drives a robot arm. Use whenever the user has an ACT checkpoint or a Pi0 model and wants it on RDK S100/S100P/S600, mentions export_bpu_actpolicy.py / bpu_control_robot.py / build_all.sh / hbm-runtime / openpi_runtime / piper_node, or asks "怎么把 ACT 部署到板上 / Pi0 怎么跑". 触发词:具身智能、ACT 部署、模仿学习策略上板、LeRobot 上 RDK、Pi0、openpi、VLA、视觉语言动作、机械臂策略、bpu_control_robot、export_bpu_actpolicy、SO-101 跑到 S100、双臂 mango。Routing — generic .onnx→.bin/.hbm quantization (non-policy models) → rdk-device; ros2 commands/env → rdk-ros; on-board LLM/VLM chat & voice → rdk-llm-deployment; S100 CPU/BPU/MCU heterogeneous split, firmware burn, board-agent handoff → rdk-board-delegate; raw error-code lookup → rdk-board-knowledge.

Grade

C

Quality

72 / 100

Safety

Passed

GitHub stars

73

Unproven: rated by static analysis only, not yet compared head-to-head.

This rating describes the version of the repository we crawled; it may have changed since, so go by its current files.

Skillspace indexes and rates this skill; it does not host or endorse it. Run third-party skills at your own risk.