Learning End-to-end Autonomous Driving using Guided Auxiliary Supervision

TL;DR

This paper introduces a multi-task learning framework for end-to-end autonomous driving that uses auxiliary supervised tasks to improve learning efficiency, performance, and transparency in stochastic urban environments.

Contribution

The paper presents a novel multi-task learning from demonstration approach with auxiliary supervision for hierarchical task decomposition in autonomous driving.

Findings

Faster learning and improved driving performance in CARLA simulator.

Enhanced transparency of the end-to-end driving model.

Robustness to stochastic urban driving scenarios.

Abstract

Learning to drive faithfully in highly stochastic urban settings remains an open problem. To that end, we propose a Multi-task Learning from Demonstration (MT-LfD) framework which uses supervised auxiliary task prediction to guide the main task of predicting the driving commands. Our framework involves an end-to-end trainable network for imitating the expert demonstrator's driving commands. The network intermediately predicts visual affordances and action primitives through direct supervision which provide the aforementioned auxiliary supervised guidance. We demonstrate that such joint learning and supervised guidance facilitates hierarchical task decomposition, assisting the agent to learn faster, achieve better driving performance and increases transparency of the otherwise black-box end-to-end network. We run our experiments to validate the MT-LfD framework in CARLA, an open-source urban driving simulator. We introduce multiple non-player agents in CARLA and induce temporal noise in them for realistic stochasticity.