Uncertainty-Aware Learning from Demonstration using Mixture Density Networks with Sampling-Free Variance Modeling

نویسندگان

  • Sungjoon Choi
  • Kyungjae Lee
  • Sungbin Lim
  • Songhwai Oh
چکیده

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 learning 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.

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

منابع مشابه

Time-dependent series variance learning with recurrent mixture density networks

This paper presents an improved nonlinear mixture density approach to modeling the time-dependent variance in time series. First, we elaborate a recurrent mixture density network for explicit modeling of the time conditional mixing coefficients, as well as the means and variances of its Gaussian mixture components. Second, we derive training equations with which all the network weights are infe...

متن کامل

Prediction of monthly rainfall using artificial neural network mixture approach, Case Study: Torbat-e Heydariyeh

Rainfall is one of the most important elements of water cycle used in evaluating climate conditions of each region. Long-term forecast of rainfall for arid and semi-arid regions is very important for managing and planning of water resources. To forecast appropriately, accurate data regarding humidity, temperature, pressure, wind speed etc. is required.This article is analytical and its database...

متن کامل

A Surface Water Evaporation Estimation Model Using Bayesian Belief Networks with an Application to the Persian Gulf

Evaporation phenomena is a effective climate component on water resources management and has special importance in agriculture. In this paper, Bayesian belief networks (BBNs) as a non-linear modeling technique provide an evaporation estimation  method under uncertainty. As a case study, we estimated the surface water evaporation of the Persian Gulf and worked with a dataset of observations ...

متن کامل

A Surface Water Evaporation Estimation Model Using Bayesian Belief Networks with an Application to the Persian Gulf

Evaporation phenomena is a effective climate component on water resources management and has special importance in agriculture. In this paper, Bayesian belief networks (BBNs) as a non-linear modeling technique provide an evaporation estimation  method under uncertainty. As a case study, we estimated the surface water evaporation of the Persian Gulf and worked with a dataset of observations ...

متن کامل

Uncertainty Quality | Uncertainty in Deep Learning

In this chapter we assess the techniques developed in the previous chapters, concentrating on questions such as what our model uncertainty looks like. We experiment with different model architectures and approximating distributions, and use various regression and classification settings. Assessing the models’ confidence quantitatively we can see how much we sacrifice in our attempt at deriving ...

متن کامل

ذخیره در منابع من


  با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید

برای دانلود متن کامل این مقاله و بیش از 32 میلیون مقاله دیگر ابتدا ثبت نام کنید

ثبت نام

اگر عضو سایت هستید لطفا وارد حساب کاربری خود شوید

عنوان ژورنال:
  • CoRR

دوره abs/1709.02249  شماره 

صفحات  -

تاریخ انتشار 2017