Cross-Scene Trajectory Level Intention Inference using Gaussian Process Regression and Naive Registration

Human intention inference is the ability of an artificial system to predict the intention of a person. It is important in the context of human-robot interaction and homeland security, where proactive decision making is necessary. Human intention inference systems at test time is given a partial sequence of observations rather than a complete one. At a trajectory level, the observations are 2D/3D spatial human trajectories and intents are 2D/3D spatial locations where these human trajectories might end up. We study a learning approach where we train a model from complete spatial trajectories, and use partial spatial trajectories to test intention predictions early and accurately. We use non-parametric Gaussian Process Regression (GPR) as the learning model since GPR has been shown to model subtle aspects of human trajectory very well. We also develop a simple geometric transfer technique called Naive Registration (NR) that allows us to learn the model using training data in a source scene and then reuse that model for testing data in a target scene. Our results on synthetic and real data suggests that our transfer technique achieves comparable results as the technique of training from scratch in the target scene.