Uncertainty-Aware Data Aggregation for Deep Imitation Learning

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.

Accepted to International Conference on Robotics and Automation 2019

References in corpus (9)

• End to End Learning for Self-Driving Cars
• Bayesian Convolutional Neural Networks with Bernoulli Approximate Variational Inference
• Deep Bayesian Active Learning with Image Data
• Deep Exploration via Bootstrapped DQN
• Explaining How a Deep Neural Network Trained with End-to-End Learning Steers a Car
• Adversarial Training Methods for Semi-Supervised Text Classification
• Query-Efficient Imitation Learning for End-to-End Autonomous Driving
• Safe end-to-end imitation learning for model predictive control
• Learning Robust Bed Making using Deep Imitation Learning with DART