Public research sourceStanfordSVL / ARISE Initiative
Stanford robomimic: Learning Robot Actions from Demonstrations
First understand what Stanford researchers are trying to learn through SVL / ARISE Initiative, why the question matters, how they test it, and what the result cannot prove. Teach a robot to copy a demonstrated pick-up action, then see whether more demonstrations improve its success rate. The student then completes A robot-demonstration app for selecting examples, checking quality, and tracking learning results. For a college application or interview, the student separates the source research from their feature, interface, tests, failures, and revisions. Available online or in person in Apgujeong, in one-to-one or small-group formats.
University and lab names show where each public project came from. CIT independently designed these courses; they are not official university courses, partnerships, or endorsements.
8guided sessions
4-8 hoursto the first small project
Intermediaterecommended level
Not requiredphysical robot
Primary routes
Choose the student's primary AI education and portfolio route
CIT keeps the international-school route first, followed by the separate science and gifted-school route.
CIT lessons can run online across Korea and overseas or in person in Apgujeong. The student owns the question, code, tests and explanation; classes do not guarantee admission, selection or awards, and online delivery never changes an institution's submission rules.
Does a robot copy the same action more successfully when it sees more human demonstrations?
Replay robot actions demonstrated by people, then compare how the number of examples and camera information affect learning success.
Students first use a small working example to understand the researchers' question, method, and evidence. A controlled change helps identify what the student's extension must solve. The student then implements a useful feature, connects an operator interface, and tests the integrated application in normal, boundary, and failure cases.
What will the student complete?
A robot-demonstration app for selecting examples, checking quality, and tracking learning results
The final package includes runnable instructions, the feature and interface design, normal and failure tests, one documented revision, and a three-minute explanation in the student's own words.
Feature
A feature that tags demonstrations as successful, shaky, or interrupted and builds a training set from selected demonstrations
Operator interface
A demonstration-management screen connecting video segments, inclusion choices, robot success rate, and representative failures
Optional LLM boundary
Optional: an LLM reads student notes and run records to suggest draft quality tags. Only student-confirmed tags are used.
Integrated result
A robot-demonstration app for selecting examples, checking quality, and tracking learning results
Four ideas explained in this course
01human demonstrations
02copying demonstrated actions
03learning from saved examples
04checking success and failure
Eight introductory sessions
Understand the research, then build and test a working robotics application
The 20 courses are eight-session CIT studios in which students understand a public university or lab project, confirm a working example, and then turn it into a small robotics application with a useful feature and an operator interface. Selected courses add an optional LLM explanation tool that can read run records but cannot control the robot. RoboMaster has 28 sessions, and implementation scope is adjusted to each student's experience and computer access.
Understand the source
01
Run a prepared robot demonstration
02
See how one action is stored from start to finish
Measure and compare
03
Replay human demonstrations
04
Compare number data with camera images
Build a feature
05
Change only the number of demonstrations
06
Implement the student-owned feature: A feature that tags demonstrations as successful, shaky, or interrupted and builds a training set from selected demonstrations
Integrate and demonstrate
07
Build the operator interface: A demonstration-management screen connecting video segments, inclusion choices, robot success rate, and representative failures. Add the bounded assistant: Optional: an LLM reads student notes and run records to suggest draft quality tags. Only student-confirmed tags are used.
08
Integrate, test, and demonstrate: A robot-demonstration app for selecting examples, checking quality, and tracking learning results
Public project used in class
See the exact version CIT reviewed
Public projects can change over time. To keep the class example consistent, CIT uses version d309eaecc18a of ARISE-Initiative/robomimic. CIT checked it on 2026-08-14; it was created on 2026-08-09. Usage-rights note: MIT.
The student compares directly how the amount and quality of demonstration data change what a robot learns. In class the project is separated into five boxes (input, memory, process, output, control). The lesson opens one of them, changes one value, and leaves the rest closed.
InputWhat comes in?
The demonstration file and the training configuration
Memoryopened hereWhat persists?
The dataset of demonstrations, the rules for which observations count, and the weights that training changes
ProcessWhat transforms?
The training step that nudges weights toward predicting the action from the observation
OutputWhat leaves, and who uses it?
The saved policy file, and the success rate from running it in the environment
ControlWhat decides when anything runs?
The loop that decides how many epochs to run, when to evaluate and when to save
The files the lesson opens, by name. The course is not a walk through the repository; it opens a chosen few and says which.
One value moves and everything else stays. The right-hand column is the prediction written before the run, not a result; the work is reconciling the two.
The universities and labs named here made the open projects this course reads. CIT designed the course independently; it is not an official, affiliated, or endorsed course.
Clear answers about what students do, what they need, and where the project came from.
Is Stanford robomimic: Learning Robot Actions from Demonstrations an official course from Originated at Stanford SVL, maintained by the ARISE Initiative?
University and lab names show where each public project came from. CIT independently designed these courses; they are not official university courses, partnerships, or endorsements.
Is hardware required?
Not required. The course starts with a robot on the computer or a saved recording of a completed run. Computer guidance: CPU replay possible, GPU recommended for training.
What background should a student have?
Recommended level: Intermediate. Students should be able to follow a guided Python example, test one controlled change, and then build and explain a small feature and interface.
What will the student make?
The completed project is A robot-demonstration app for selecting examples, checking quality, and tracking learning results. The student implements A feature that tags demonstrations as successful, shaky, or interrupted and builds a training set from selected demonstrations and A demonstration-management screen connecting video segments, inclusion choices, robot success rate, and representative failures. Optional: an LLM reads student notes and run records to suggest draft quality tags. Only student-confirmed tags are used.
How can the student use this project in a college application?
Explain the source research question, method, evidence, and limits first. Then separate the student's own feature and interface decisions, normal and failure tests, revisions, and next question. The source institution's name does not imply affiliation or guarantee admission.
Which project version does the course use?
CIT reviewed version d309eaecc18a of ARISE-Initiative/robomimic on 2026-08-14. That version was created on 2026-08-09. We keep this version during class so the example does not change unexpectedly, and we check the setup again before teaching.
Can Stanford robomimic: Learning Robot Actions from Demonstrations be taken online or in person, one-to-one or in a small group?
Yes. This course is offered online and in person at CIT in Apgujeong, Gangnam-gu, Seoul, with one-to-one and small-group options. Placement and current availability are confirmed after a readiness consultation.
Is this a good first project for this student?
Before placement, we check the student's coding and math experience, available computer, interests, and ability to explain what happened.
UCSD ManiSkill: Teaching Many Simulated Robots at OnceTrain many simulated robots at the same time and compare how object size, friction, and goal position affect...→
Georgia Tech MimicLabs: Creating Robot Practice DataTurn a small number of robot demonstrations into many practice scenes, then check whether the larger set adds...→
Princeton AdaptSim: Closing the Simulation-to-Reality GapA simulated robot behaves differently when its weight or friction does not match reality. Test which adjustment...→