Why can't we speak to robots?
Household robots need to move beyond simple programmed tasks like those a Roomba performs and become full-fledged digital assistants. A robotic agent that exists (physically) in the world, gains access to rich and personalized knowledge of its environment. For example, they might be able to answer questions like: How much do things weigh? What's fragile? Or where you store the extra chocolates that you don't want anyone to find?
This course is intended for graduate students. Background with physical hardware or simulators is recommended and knowledge of Deep Learning + one specialty (NLP/CV/Robotics).
Contact Yonatan (ybisk@cs) if you're unsure.
- Instruction following & Dialogue
- Large Language Models
- Task and Motion Planning
- End-Effector & real-valued control
- Semantic Mapping (2D and 3D)
- World Models
- How do you define or evaluate Dialogue?
- Limitations of offline and unimodal pretraining
- How does embodiment shape meaning?
- Is space semantic, dynamic, and/or euclidean?
- Discrete vs continuous spaces and representations.
- When is Sim2Real possible? What's about manipulation?
- Time & Place: 11:00am - 11:50am Tu/Th in POS A35
- Canvas
- Instructor: Yonatan Bisk
6 Credit Seminar | 12 Credit Project | |
---|---|---|
Paper Summaries | 5pts * 8 papers | 5pts * 8 papers |
- Student Paper | 5pts * 1 papers | 5pts * 1 papers |
- Paper Presentation | 10 pts | 10 pts |
Project | ||
- Proposal | 15 pts (theoretical) | 15 pts (practical) |
- Final Report | 30 pts | 30 pts (include implementation details or demo) |
Groups: Both seminar and project based assignments will be done in groups. Groups will likely be capped at five people.
Equal Participation: All reports must include a breakdown of each teammate's contributions.
Paper Summary (5/3pts)
- What is the key insight of this paper and problem they are addressing?
- What assumptions or simplifications do they make about the world or information flow?
- What changes might enable better generalization to more realistic settings?
Project Proposal (15pts)
- Task, Environment, and Skills Definitions
- Minimal language covered and stretch goals
- Failure recovery and replanning/feedback strategy
Midsemester Presentation (15pts)
- Interactive demo of basic skills
- Example of successful composition
- Demonstration and analysis of failures
- Proposal of changes for final demo (including rescoping)
Final Presentation (10pts)
- Interactive demo of compositional instructions
- Example of successful corrections/feedback
- Demonstration and analysis of failures
Final Report (30pts)
- 12 Credit: Technical write-up and specification of system (including code)
- 12 Credit: Technical write-up of model design (including code)
- All: Literature Review of state of the field
- All: Discussion of key limitations to progress in this space
There are a couple other simulators/platforms I also like, which we can discuss as options.
Platform | Type | Notes |
---|---|---|
VLN-CE | Simulated Navigation![]() |
Minimal hardware experience Proj: Language to Angle/Distance Teams:No limit on teams |
DexArm | Simple gripper![]() |
Basic manipulation platform Proj: Language to 3D Space Teams: Two teams of ~4 |
Hello Robot Stretch | Mobile Manipulator![]() |
Requires skill specifications Proj: Language to ... let's decide Teams (Probably) one team -- Let's see Control Code: Meta Home-Robot Collaborator: Chris Paxton |
Late Assignments
- All teams have 5 late days, these are only applicable to reports (not demos).
- Paper summaries lose 1pt per day late
COVID Details:
In the event a student tests positive for COVID-19, they will be invited to attend discussion virtually and will be expected to participate as usual. This includes participation points for raising their hands with questions/answers and submission of lab-notebooks. Note, that students who attend class while exhibiting symptoms will be told to leave and join virtually for the protection of all others present.
Accommodations for Students with Disabilities:
If you have a disability and have an accommodations letter from the Disability Resources office, we encourage you to discuss your accommodations and needs with the instructors as early in the semester as possible. We will work with you to ensure that accommodations are provided as appropriate. If you suspect that you may have a disability and would benefit from accommodations but are not yet registered with the Office of Disability Resources, we encourage you to contact them at access@andrew.cmu.edu.
- Can we use other platforms? Yes! What robots do you have? Also checkout AI Maker Space
- What about custom sensors and hardware? Same answer :)
- What about other simulators? Same answer :)
- LTI Curriculum Categories? 12 Hour version can be counted for a Task and a Lab
- Do I /need/ simulator experience? No, but plan to spend some time getting the engineering setup
- Can I attend discussion without registering? It's best to register (6hrs) even if you've finished your classes, since I need to prioritize time, energy, and space on registered students. I'll try and update this once I have a room confirmed with the registrar and see how much space we have in the class.