Personalized Pose Forecasting
This work addresses the need for personalized motion forecasting in human-interacting systems like delivery robots, though it appears incremental as it builds on existing benchmarks and methods.
The paper tackles the problem of human pose forecasting by highlighting that existing benchmarks fail to account for individual movement patterns, and it presents a model-agnostic personalization method that personalizes neural network predictions using a low-parametric time-series analysis model.
Human pose forecasting is the task of predicting articulated human motion given past human motion. There exists a number of popular benchmarks that evaluate an array of different models performing human pose forecasting. These benchmarks do not reflect that a human interacting system, such as a delivery robot, observes and plans for the motion of the same individual over an extended period of time. Every individual has unique and distinct movement patterns. This is however not reflected in existing benchmarks that evaluate a model's ability to predict an average human's motion rather than a particular individual's. We reformulate the human motion forecasting problem and present a model-agnostic personalization method. Motion forecasting personalization can be performed efficiently online by utilizing a low-parametric time-series analysis model that personalizes neural network pose predictions.