Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling
This work addresses uncertainty-aware learning for real-time robotics applications, particularly in autonomous driving, though it appears incremental as it builds on existing mixture density network approaches.
The paper tackles the problem of uncertainty estimation in learning from demonstration for robotics by proposing a novel method using mixture density networks with sampling-free variance modeling, which outperforms other methods in safety metrics on a real-world driving dataset.
In this paper, we propose an uncertainty-aware learning from demonstration method by presenting a novel uncertainty estimation method utilizing a mixture density network appropriate for modeling complex and noisy human behaviors. The proposed uncertainty acquisition can be done with a single forward path without Monte Carlo sampling and is suitable for real-time robotics applications. The properties of the proposed uncertainty measure are analyzed through three different synthetic examples, absence of data, heavy measurement noise, and composition of functions scenarios. We show that each case can be distinguished using the proposed uncertainty measure and presented an uncertainty-aware learn- ing from demonstration method of an autonomous driving using this property. The proposed uncertainty-aware learning from demonstration method outperforms other compared methods in terms of safety using a complex real-world driving dataset.