Multiple AI models help robots execute complex plans more tr

MIT's HiP system helps robots complete long-horizon goals using three foundation models: a large language model, a video diffusion model, and an egocentric action model. Iterative refinement improves the plan at each step for household and manufacturing tasks.

Related Keywords

Joshua Tenenbaum , Prakash Srivastava , Pulkit Agrawal , Abhishek Gupta , Anurag Ajay , Seungwook Han , University Of Washington , Compositional Foundation Models For Hierarchical Planning Hi , Improbable Ai Lab , National Science Foundation , Us Defense Advanced Research Projects Agency , Artificial Intelligence Laboratory , Watson Ai Lab , Department Of Electrical Engineering , Us Army Research Office , Zai Lab , Computer Science , Compositional Foundation Models , Hierarchical Planning , Bing Chat , Jim Fan , Action Diffuser , Electrical Engineering , Tommi Jaakkola , Leslie Pack Kaelbling , Shuang Li Phd , Advanced Research Projects Agency , Research Office , Neural Information Processing Systems , Mit Csail , It Improbable Ai Lab , Ompositional Foundation Models For Hierarchical Planning Hip , Ultimodal Ai System , Large Language Models , Ideo Diffusion Model , Gocentric Action Model , Ong Horizon Goals , Obot Planning ,