We are the People and Robots Teaching and Learning (PoRTaL) group at Cornell Computer Science.

We build everyday robots for everyday users.

Our mission is to make robots accessible, user-friendly and practical for everyday tasks from cooking to cleaning. To this end, our research focuses on imitation learning, decision making and human-robot interaction. We are passionate about both theory and algorithms that equip robots with skills to work with people.

If you are interested in joining our fantastic team, apply here!.


Jul 14, 2023 Exciting new work, Demo2Code, on learning from demonstrations with LLMs! Check out the explainer tweet.
May 22, 2023 Big plans for the summer with our new undergraduate researchers Max Pace, Atiksh Bhardwaj, Vivian Fan and Lisa Asriev! :muscle:
May 8, 2023 We had an amaaazing end-of-semester social! :tada: HAL and DORA, for the first time ever, showed off how to collaboratively cook with our human user, Neha. Checkout the demo and behind the scenes!
May 3, 2023 Two very cool papers :sunglasses: at ICML: The Virtue of Laziness in MBRL and IRL without RL. Reset distributions are back this summer!
May 1, 2023 Here’s a sneak peek :eyes: of HAL and DORA getting ready to cook together with humans for the first time! This was a massive engineering effort combining the power of large language models, speech detection, visual imitation learning, motion capture, forecasting, model predictive control and more!
Apr 27, 2023 We had a blast showing off HAL at BOOM, back after 3 years at Cornell! Checkout pictures!
Feb 5, 2023 Welcome the newest PoRTaLites :sparkles: - David Wu, Prithwish Dan, Neha Sunkara, Gonzalo Gonzalez and Yash Sharma!
Jan 29, 2023 Kicking off the new year with new papers! Impossibly Good Experts and How to Follow Them at ICLR 2023, Guided Incremental Local Densification at ICRA 2023.
Dec 9, 2022 Thanks everyone for coming to PORTAL’s first holiday social! We had a blast showing you our wonderful robots, HAL and DORA, and our plans to take over the world ;)
Dec 6, 2022 HAL’s first autonomy run! They grow so fast …