Uncertainty-Aware Learning from Demonstration Using Mixture Density Networks with Sampling-Free Variance Modeling
- Authors
- Choi, Sungjoon; Lee, Kyungjae; Lim, Sungbin; Oh, Songhwai
- Issue Date
- May-2018
- Publisher
- IEEE COMPUTER SOC
- Citation
- 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA), pp 6915 - 6922
- Pages
- 8
- Journal Title
- 2018 IEEE INTERNATIONAL CONFERENCE ON ROBOTICS AND AUTOMATION (ICRA)
- Start Page
- 6915
- End Page
- 6922
- URI
- https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59371
- DOI
- 10.1109/ICRA.2018.8462978
- ISSN
- 1050-4729
2577-087X
- Abstract
- 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. Then, we show that it can be decomposed into explained variance and unexplained variance where the connections between aleatoric and epistemic uncertainties are addressed. 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 learning from demonstration method for 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.
- Files in This Item
- There are no files associated with this item.
- Appears in
Collections - College of Software > Department of Artificial Intelligence > 1. Journal Articles
![qrcode](https://api.qrserver.com/v1/create-qr-code/?size=55x55&data=https://scholarworks.bwise.kr/cau/handle/2019.sw.cau/59371)
Items in ScholarWorks are protected by copyright, with all rights reserved, unless otherwise indicated.