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.
Intention Inference, Gaussian Process Regression, Transfer Learning, Trajectory Prediction
Date of this Version