Georgia Tech MimicLabs: Creating Robot Practice Data
First understand what Georgia Tech researchers are trying to learn through RL2, why the question matters, how they test it, and what the result cannot prove. Expand a few human-made robot demonstrations into many practice scenes, then separate useful variety from repeated mistakes. The student then completes A robot-data review tool for selecting practice scenes and finding duplication, gaps, and bias. 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
8-16 hoursto the first small project
Intermediate to advancedrecommended 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.
Can turning a few demonstrations into many practice scenes help a robot learn?
Turn a small number of robot demonstrations into many practice scenes, then check whether the larger set adds useful variety or repeats mistakes.
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-data review tool for selecting practice scenes and finding duplication, gaps, and bias
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 for filtering generated practice scenes and warning when scenes are duplicated or important conditions are missing
Operator interface
A dataset-review screen comparing original and generated scenes and showing object layout, action diversity, and failure rate
Integrated result
A robot-data review tool for selecting practice scenes and finding duplication, gaps, and bias
Four ideas explained in this course
01original human demonstrations
02creating new practice scenes
03measuring action variety
04checking errors and bias in data
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
See how several public tools connect
02
Inspect original human demonstrations
Measure and compare
03
Understand the task and object starting positions
04
Create new practice scenes from demonstrations
Build a feature
05
Change only the number of practice scenes
06
Implement the student-owned feature: A feature for filtering generated practice scenes and warning when scenes are duplicated or important conditions are missing
Integrate and demonstrate
07
Build the operator interface: A dataset-review screen comparing original and generated scenes and showing object layout, action diversity, and failure rate
08
Integrate, test, and demonstrate: A robot-data review tool for selecting practice scenes and finding duplication, gaps, and bias
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 0b81d7e8cc07 of GaTech-RL2/mimiclabs. CIT checked it on 2026-08-14; it was created on 2026-03-13. Usage-rights note: MIT.
The student grows a few demonstrations into many layouts and checks whether the extra examples actually help. 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.
Inputopened hereWhat comes in?
The handful of demonstrations a person recorded, and the task file that says what success means
MemoryWhat persists?
The saved demonstrations, and the ranges that say where objects may be placed
ProcessWhat transforms?
Transplanting the demonstrated motion onto a new layout to make a new example
OutputWhat leaves, and who uses it?
The enlarged set of demonstrations, and the check that says which examples succeeded
ControlWhat decides when anything runs?
The settings that decide which task combinations are generated, and how many
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 Georgia Tech MimicLabs: Creating Robot Practice Data an official course from Georgia Tech RL2?
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: GPU recommended, storage check required.
What background should a student have?
Recommended level: Intermediate to advanced. 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-data review tool for selecting practice scenes and finding duplication, gaps, and bias. The student implements A feature for filtering generated practice scenes and warning when scenes are duplicated or important conditions are missing and A dataset-review screen comparing original and generated scenes and showing object layout, action diversity, and failure rate.
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 0b81d7e8cc07 of GaTech-RL2/mimiclabs on 2026-08-14. That version was created on 2026-03-13. We keep this version during class so the example does not change unexpectedly, and we check the setup again before teaching.
Can Georgia Tech MimicLabs: Creating Robot Practice Data 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...→
Stanford robomimic: Learning Robot Actions from DemonstrationsReplay robot actions demonstrated by people, then compare how the number of examples and camera information...→
Princeton AdaptSim: Closing the Simulation-to-Reality GapA simulated robot behaves differently when its weight or friction does not match reality. Test which adjustment...→