Uncertainty-Aware Data Aggregation for Deep Imitation Learning

by   Yuchen Cui, et al.

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.


page 5

page 6


End-to-end Driving Deploying through Uncertainty-Aware Imitation Learning and Stochastic Visual Domain Adaptation

End-to-end visual-based imitation learning has been widely applied in au...

Safe end-to-end imitation learning for model predictive control

We propose the use of Bayesian networks, which provide both a mean value...

HG-DAgger: Interactive Imitation Learning with Human Experts

Imitation learning has proven to be useful for many real-world problems,...

Multi-Task Conditional Imitation Learning for Autonomous Navigation at Crowded Intersections

In recent years, great efforts have been devoted to deep imitation learn...

Density-Aware Federated Imitation Learning for Connected and Automated Vehicles with Unsignalized Intersection

Intelligent Transportation System (ITS) has become one of the essential ...

Operation and Imitation under Safety-Aware Shared Control

We describe a shared control methodology that can, without knowledge of ...

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

In this paper, we propose an uncertainty-aware learning from demonstrati...