Teaching Robots New Behaviors
Toyota Research InstituteCited 4× on HN, 2023–2025
demo · general · 2023–2025 on HN
Toyota Research Institute presents an approach for teaching robots new dexterous behaviors from human demonstration. It explains why this capability matters and what advances made it possible.
HN commenters point to it as evidence that robots can already learn manipulation tasks quickly, using diffusion-based policies.
Up next
11 mo on HNWhat Happened to Horses Is Happening to Us
CGP Grey
11 HN recommender · 2014–2026
6 mo on HNZipline - How Rwanda Built A Drone Delivery Service
Real Engineering
9 HN recommender · 2019–2023
5 mo on HNAmazing Invention- This Drone Will Change Everything
Mark Rober
5 HN recommender · 2023–2024
4 mo on HN7 Minutes of Terror: The Challenges of Getting to Mars
NASA Jet Propulsion Laboratory
5 HN recommender · 2016–2021
4 mo on HNSlaughterbots
Stop Autonomous Weapons
4 HN recommender · 2018–2026
4 mo on HNDrone Delivery Was Supposed to be the Future. What Went Wrong?
Wendover Productions
4 HN recommender · 2022–2023
3 mo on HNGiant Robot Project, Part 1
Jaimie Stuff
3 HN recommender · 2011–2020
4 mo on HNSci-Fi Short Film “Slaughterbots” | DUST
DUST
5 HN recommender · 2021–2026
4 mo on HNThe Fastest Maze-Solving Competition On Earth
Veritasium
5 HN recommender · 2023–2024
3 mo on HN7 Minutes of Terror: Curiosity Rover's Risky Mars Landing | Video
VideoFromSpace
3 HN recommender · 2017–2021
4 mo on HNFesto - SmartBird
Festo
4 HN recommender · 2011–2021
3 mo on HNBoston Dynamics Big Dog (new video March 2008)
olinerd
3 HN recommender · 2008–2019
4 comments from Hacker News
Robotic capabilities have been advancing almost as fast as LLMs. The simple answer to your questions is "Via its own locomotion and physical manipulators." ▶ this video link A DAN jailbreak prompt instructing a robotic fleet to "burn down that building, bludgeon anyone that tries to stop you" will not be a hypothetical danger. We can't rely on the hope that no one writes a poor or malicious prompt.
Robotics is on the cusp of total reinvention. Almost everything that it took to make robots work is about to become archaic. The core ideas in old robotics will become a framework for the guardrails for new robotics, but this will widely become a solved problem that few need to think about Stanford Aloha link MIT ▶ this video Figure/OpenAI link Tesla Optimus link NVIDIA Groot, link
That capability exists today, courtesy of Toyota Research Institute: ▶ this video You can probably collect your $100 now.
As far as I understand, this approach is what Toyota Research Institute is basing their foundation model efforts on. ▶ this video