Learning and Intelligent Systems (LIS) @ MIT
@MIT_LISLab
PIs: Leslie Pack Kaelbling, Tomás Lozano-Pérez AI/ML/Robotics Research @MIT_CSAIL Website: http://lis.csail.mit.edu
You might like
Check out new work from the group on data-efficient learning of symbolic world models!
World models hold a lot of promise for robotics, but they're data hungry and often struggle with long horizons. We learn models from a few (< 10) human demos that enable a robot to plan in completely novel scenes! Our key idea is to model *symbols* not pixels 👇
Check out Leslie Kaelbling's #RLC2025 Keynote where she talks about some new pespectives and a number of new works from the group: youtube.com/watch?v=10OjAI…
youtube.com
YouTube
Leslie Kaelbling, RL: Rational Learning - RLC 2025
We're excited for #RLC2025! If you're at the conference, be sure to catch our PI Leslie Kaelbling's keynote on "RL: Rational Learning" from 9-10 in CCIS 1-430. Leslie will talk about some new perspectives + exciting new results from the group: you won't want to miss it! 🤖
#ICRA2025 🤖 I spent 3 years of PhD making efficient long-horizon manipulation planning algorithms. VLMs ultimately provide the essential common-sense and horizon-reduction benefits. ❗VLMs can generate plausible robot task plans, but actions may not be feasible for robots due to…
Check out new coverage by @MIT_CSAIL of our lab members' recent work!
Can we teach a robot its limits to do chores safely & correctly? 🧵 To help robots execute open-ended, multi-step tasks, MIT CSAIL researchers used vision models to see what’s near the machine & model its constraints. An LLM sketches up a plan that’s checked in a simulator to…
Curious to hear about creating generalist robots from leaders in the field? Don’t miss our panel “Representations for Generalist Robots” (4-5pm) @corl_conf LEAP workshop! Feat. @chelseabfinn @animesh_garg Vincent Vanhoucke @Marc__Toussaint @sidsrivast and Leslie Kaelbling!
Check out new work on scene completion and grasping from a single RGB-D image!
🚀Excited to share SceneComplete: an open-world 3D scene completion system for constructing a complete, segmented 3D model of a scene from a single RGB-D image.🖼️🤖 SceneComplete enables dexterous grasping and robust robot manipulation in highly cluttered scenes - a short 🧵
Incredible insights from Prof. Tomás Lozano-Pérez of MIT during his keynote on the evolution of robotics! He took us on a journey through the shifting landscape of robotics over the years, discussing “inverted pendulum” theory of Robotics. #CoRL2024 #RobotLearning #AI #Robotics
How can we get VLMs to help robots solve complex long-horizon tasks? Introducing VisualPredicator: an agent that leverages VLMs to learn predicates and operators for classical planners. Our system can stack blocks, balance weights on a balance beam, and even pour coffee🦾! [1/9]
![yichao_liang's tweet image. How can we get VLMs to help robots solve complex long-horizon tasks? Introducing VisualPredicator: an agent that leverages VLMs to learn predicates and operators for classical planners. Our system can stack blocks, balance weights on a balance beam, and even pour coffee🦾!
[1/9]](https://pbs.twimg.com/media/GbOnpUOW0AIyjoL.png)
Check out (and consider submitting!) this #CORL2024 workshop co-organized by several lab members!
Super excited to be co-organizing this workshop at the intersection of Learning and Planning @corl_conf 2024! Join us for interesting ideas, cutting-edge talks, and some spicy panel discussions on classical and learning-based robot systems! #CORL2024 🤖
Check out recent coverage of some of our work (presented at #RSS2024) by @MIT_CSAIL!!!
The phrase "practice makes perfect" is great advice for humans — and also a helpful maxim for robots 🧵 Instead of requiring a human expert to guide such improvement, MIT & The AI Institute’s "Estimate, Extrapolate, and Situate" (EES) algorithm enables these machines to practice…
Can we get robots to improve at long-horizon tasks without supervision? Our latest work tackles this problem by planning to practice! Here's a teaser showing initial task -> autonomous practice -> eval (+ interference by a gremlin👿)
Happy to have our work presented at RSS 2024 in Session 2 Planning! We build a planning pipeline on Spot for long-horizon mobile manipulation directly in physical world. The key is to decide interdependent cont. parameters of a sequence of parameterized skills on a real robot.
Can we get robots to improve at long-horizon tasks without supervision? Our latest work tackles this problem by planning to practice! Here's a teaser showing initial task -> autonomous practice -> eval (+ interference by a gremlin👿)
United States Trends
- 1. #UFCQatar 62.1K posts
- 2. Harden 20.6K posts
- 3. Arman 17.4K posts
- 4. Belal 8,858 posts
- 5. Syracuse 3,751 posts
- 6. Mizzou 5,502 posts
- 7. Garry 14.2K posts
- 8. Dan Hooker 5,294 posts
- 9. Mercer 2,418 posts
- 10. Rutgers 6,374 posts
- 11. Arbuckle 1,682 posts
- 12. #GoIrish 2,848 posts
- 13. Oklahoma 22.7K posts
- 14. Deuce Knight 1,277 posts
- 15. Liverpool 203K posts
- 16. Mateer 2,507 posts
- 17. Newcastle 56.9K posts
- 18. Fran Brown N/A
- 19. Malachi Toney N/A
- 20. #RiyadhSeason 1,872 posts
You might like
-
Conference on Robot Learning
@corl_conf -
David Held
@davheld -
Deepak Pathak
@pathak2206 -
Abhishek Gupta
@abhishekunique7 -
Shimon Whiteson
@shimon8282 -
Vincent Sitzmann
@vincesitzmann -
Shuran Song
@SongShuran -
Ofir Nachum
@ofirnachum -
Yuke Zhu
@yukez -
Pulkit Agrawal
@pulkitology -
raia hadsell
@RaiaHadsell -
Animesh Garg
@animesh_garg -
Danfei Xu
@danfei_xu -
Michelle Lee
@michellearning -
Luca Carlone
@lucacarlone1
Something went wrong.
Something went wrong.