Universal Motion Generator: Trajectory Autocompletion by Motion Prompts
Author(s)
Wang, Yanwei; Shah, Julie![Thumbnail](/bitstream/handle/1721.1/143430/Universal_Motion_Generator.pdf.jpg?sequence=5&isAllowed=y)
DownloadUniversal_Motion_Generator.pdf (4.705Mb)
Terms of use
Metadata
Show full item recordAbstract
Foundation models, which are large neural networks trained on massive datasets, have shown
impressive generalization in both the language and the vision domain. While fine-tuning foundation
models for new tasks at test-time is impractical due to billions of parameters in those models, prompts
have been employed to re-purpose models for test-time tasks on the fly. In this report, we ideate the equivalent foundation model for motion generation and the corresponding formats of prompt that can condition such a model. The central goal is to learn a behavior prior for motion generation that can be re-used in a novel scene.
Date issued
2022-06-15Keywords
Robot Learning, Large Language Models, Motion Generation
Collections
The following license files are associated with this item: