Skip to content

ToddlerBot-based humanoid curriculum instantiation for grades 9-12 with eight CS+AI sessions

Design · All designs
Evidence · no claims cited

Description

The curriculum targets grades 9-12 with four students in two pairs, one ToddlerBot per pair, a recommended mentor-to-student ratio of 1:4, and "Eight three-hour computer science and AI (CS+AI) sessions (24 contact hours)" accompanying assembly, electrical checks, and a closing demonstration. ToddlerBot provides open hardware and software with a reported parts cost under USD 6,000. Five intended learning outcomes (LO1-LO5) span safe startup, explaining reward-based learning, simulation-physical comparison, failure diagnosis, and collaboration.

Design Implications

Context

Requirements

  • A revised prerequisite of running and modifying a short Python program before RL labs
  • Shared computers for training runs
  • Mentor supervision for all physical trials

Constraints

  • Additional build, preparation, and training time is not quantified
  • If hardware is unavailable, simulation work preserves conceptual tasks but does not substitute for the safe startup outcome

Target Learners

  • High-school students in grades 9-12, paired with one robot per pair

Learning Goals

  • Assembling and safely starting a robot
  • Explaining how rewards and trying different actions guide learning
  • Comparing simulation with physical measurements

Claims

Examples

-

Key Sources

  • Yuanzhe Dong, Jie Cao, Shuman Wang. (2026). Teaching Reinforcement Learning and Humanoid Robotics to High-School Students: An Expert-Validated Curriculum Design on a Low-Cost Open Platform. arXiv. https://arxiv.org/abs/2609.25674
Page metadata
Field Value
type design
id toddlerbot-high-school-rl-curriculum
title ToddlerBot-based humanoid curriculum instantiation for grades 9-12 with eight CS+AI sessions
description The curriculum targets grades 9-12 with four students in two pairs, one ToddlerBot per pair, a recommended mentor-to-student ratio of 1:4, and "Eight three-hour computer science and AI (CS+AI) sessions (24 contact hou...
status review
generated by process:settle-candidates on 2026-10-12
trust unverified — no one has confirmed this page's content
sources 1 — yuanzhe-dong-2026

Frontmatter is the page's machine-readable record — see the Schema & Guide.