kumyu.Learn
← Kumyu home日本語 ↗

REGISTERED TAG

Robotics and embodied AI

Connect perception, action and physical constraints.

Published Updated
Beginner

Introduction to Physical AI: Connecting the history of VLA from perception to safe behavior

Instead of viewing Vision-Language-Action as the magic of a universal robot, understand it as a connection between observation, coordinates, strategy, and control.

15 min↗
Published Updated
Intermediate

2025 VLA map: read SmolVLA, π0/π0.5, OpenVLA, and GR00T using the same yardstick

Updated notes that interpret each presentation in terms of openness, body, data, behavioral expression, and evaluation boundaries, rather than ranking each presentation in a comparison table.

12 min↗
Published Updated
Intermediate

LeRobot practice: Make dataset, imitation learning, evaluation, and Sim2Real into one quality loop

Starting with LeRobot's data format and unified interface, learn the points of contact that are likely to fail from collection to actual machine evaluation.

15 min↗
Published Updated
Beginner

Starting Physical AI without a robot: Safe learning procedure and decision not to proceed to the actual machine

It clearly states that the hardware is not running, and touches on the core of Physical AI just through data observation, simulation, and evaluation design.

15 min↗
Published Updated
Intermediate

Physical AI coordinate transformation and camera calibration: do not treat image pixels as safe robot commands

Learn camera, robot base, and hand coordinate systems and calibration as verifiable contracts outside of VLA.

15 min↗
Published Updated
Intermediate

Reading VLA papers to implementable designs: Comparative reading exercise of π0, SmolVLA, and GR00T

The novelty of a paper is not confused with performance ranking, but is broken down into behavioral expression, data, body, evaluation, and unverified boundaries.

16 min↗
Published Updated
Intermediate

Physical AI workshop: from data splits to policy evaluation and Sim2Real decisions

Turn public or synthetic episodes into reproducible splits, baseline and adaptation evaluations, failure analysis, and a justified decision not to proceed to hardware.

12 min↗
Published Updated
Evaluation fixture → offline safety boundary

Action chunks: measure recovery after a small perturbation

A strictly offline fixture for separating error propagation in a replayed action chunk from recovery after replanning.

9 min↗