Uncertainty-Aware Data Aggregation for Deep Imitation Learning
This work addresses safety concerns in autonomous driving by enabling agents to anticipate mistakes and avoid sub-optimal states, though it is incremental as it builds on prior data aggregation methods.
The paper tackles the problem of improving end-to-end control systems in safety-critical domains like autonomous driving by introducing an uncertainty-aware imitation learning algorithm that uses Monte Carlo Dropout to estimate uncertainty and selectively acquire training data, outperforming existing data aggregation algorithms on benchmark tasks.
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.