# Uncertainty-Aware Data Aggregation for Deep Imitation Learning

## TL;DR

UAIL enhances autonomous control systems by estimating uncertainties with Monte Carlo Dropout, enabling selective data collection and improved safety in autonomous driving tasks.

## Contribution

This paper introduces UAIL, a novel uncertainty-aware imitation learning algorithm that anticipates mistakes and improves data aggregation in autonomous control systems.

## Key findings

- UAIL reliably predicts infractions in simulated driving tasks.
- UAIL outperforms existing data aggregation algorithms.
- Uncertainty estimation improves safety and efficiency.

## Abstract

Estimating statistical uncertainties allows autonomous agents to communicate their confidence during task execution and is important for applications in safety-critical domains such as autonomous driving. In this work, we present the uncertainty-aware imitation learning (UAIL) algorithm for improving end-to-end control systems via data aggregation. UAIL applies Monte Carlo Dropout to estimate uncertainty in the control output of end-to-end systems, using states where it is uncertain to selectively acquire new training data. In contrast to prior data aggregation algorithms that force human experts to visit sub-optimal states at random, UAIL can anticipate its own mistakes and switch control to the expert in order to prevent visiting a series of sub-optimal states. Our experimental results from simulated driving tasks demonstrate that our proposed uncertainty estimation method can be leveraged to reliably predict infractions. Our analysis shows that UAIL outperforms existing data aggregation algorithms on a series of benchmark tasks.