Human Motion Prediction using Interacting Multiple Model Filtering enhanced by a Kinematic Model

Predicting human motion enhances safety and efficiency in human–robot collaboration. We evaluate a predictor based on an Interacting Multiple Model (IMM) estimator combined with a human dynamics and control model. This approach is compared against a baseline Unscented Kalman Filter (UKF) using a constant acceleration model (CA). Additionally, we introduce a human kinematic model to predict joint angles instead of keypoints, enforcing kinematic constraints.