Stanford AI 课程地图 EN GitHub ↗
← 返回课程地图
Stanford · 2026—27 CS 381 机器人、具身智能 ★★★★★

核心课程 · 机器人、具身智能

具身智能的感知运动学习

Sensorimotor Learning for Embodied Agents (EE 381)

具身智能的 sensorimotor learning:从原始感知到决策,持续适应物理世界。

3 学分 2027 冬 Letter or Credit/No Credit ★★★★★
具身智能机器人研究VLA

2026-27 冬季开设;官网暂未找到稳定链接。

课程定位

CS 381(EE 381)是 Shuran Song 的高级课,面向想做大模型+机器人研究的研究生。课程讨论 embodied AI 与 internet AI 的区别、从原始感知到决策的学习、以及通过硬件/软件持续适应物理世界,重点是读论文、批判性讨论和项目。

主要内容

  1. Embodied AI:定义、与互联网 AI 的差异
  2. 感知运动学习:视觉、触觉、本体感觉
  3. 策略学习:模仿、RL、world model
  4. 持续适应:在线学习、domain shift
  5. 硬件/软件协同:传感器、执行器、形态
  6. 论文阅读与辩论
  7. 研究项目

先修

深度学习、机器人/RL 基础;研究导向。

考核与工作量

论文阅读/展示/辩论 + 项目。具体以当季官网为准。

适合谁

想做具身智能研究、机器人学习、VLA 的人;准备读博的学生。

学习建议

先修 CS 227A/CS 237B/CS 234。项目要有真实的机器人或高保真仿真实验。

相关课程

官方课程描述(英文原文)

This is an advanced course that will focus on modern machine learning algorithms for autonomous robots as an embodied intelligent agent. It covers advanced topics that center around 1. what is embodied AI and how it differs from internet AI, 2. how embodied agents perceive their environment from raw sensory data and make decisions, and 3. continually adapt to the physical world through both hardware and software improvements. By the end of the course, we hope to prepare you for conducting research in this area, knowing how to formulate the problem, design the algorithm, critically validate the idea through experimental designs and finally clearly present and communicate the findings. Students are expected to read, present, and debate the latest research papers on embodied AI, as well as obtain hands-on experience through the course projects.