Universal Motion Generator: Trajectory Autocompletion by Motion Prompts

Abstract

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.