Robust Unsupervised Learning of Temporal Dynamic Interactions

TL;DR

This paper introduces geometric and optimal transport-based metrics for robust, unsupervised learning of temporal interactions, demonstrated on vehicle-to-vehicle data, to improve stability and comparison of interaction representations.

Contribution

It proposes novel model-free and distribution comparison metrics based on Procrustes distance and optimal transport for unsupervised learning of dynamic interactions.

Findings

Metrics effectively assess stability of learning algorithms.

Metrics enable comparison of different interaction learning outcomes.

Demonstrated on large vehicle interaction dataset.

Abstract

Robust representation learning of temporal dynamic interactions is an important problem in robotic learning in general and automated unsupervised learning in particular. Temporal dynamic interactions can be described by (multiple) geometric trajectories in a suitable space over which unsupervised learning techniques may be applied to extract useful features from raw and high-dimensional data measurements. Taking a geometric approach to robust representation learning for temporal dynamic interactions, it is necessary to develop suitable metrics and a systematic methodology for comparison and for assessing the stability of an unsupervised learning method with respect to its tuning parameters. Such metrics must account for the (geometric) constraints in the physical world as well as the uncertainty associated with the learned patterns. In this paper we introduce a model-free metric based on the Procrustes distance for robust representation learning of interactions, and an optimal transport based distance metric for comparing between distributions of interaction primitives. These distance metrics can serve as an objective for assessing the stability of an interaction learning algorithm. They are also used for comparing the outcomes produced by different algorithms. Moreover, they may also be adopted as an objective function to obtain clusters and representative interaction primitives. These concepts and techniques will be introduced, along with mathematical properties, while their usefulness will be demonstrated in unsupervised learning of vehicle-to-vechicle interactions extracted from the Safety Pilot database, the world's largest database for connected vehicles.