DriveGAN: Towards a Controllable High-Quality Neural Simulation

TL;DR

DriveGAN is a novel neural simulator that learns to generate high-quality, controllable, pixel-space environment simulations from unannotated data, enabling re-simulation and scene manipulation for robotics training.

Contribution

It introduces DriveGAN, a fully differentiable neural simulator that disentangles scene components for controllability without supervision, trained on real-world driving data.

Findings

Outperforms previous data-driven simulators in quality and control.

Enables re-simulation of scenes with different actions.

Supports scene feature sampling like weather and object placement.

Abstract

Realistic simulators are critical for training and verifying robotics systems. While most of the contemporary simulators are hand-crafted, a scaleable way to build simulators is to use machine learning to learn how the environment behaves in response to an action, directly from data. In this work, we aim to learn to simulate a dynamic environment directly in pixel-space, by watching unannotated sequences of frames and their associated action pairs. We introduce a novel high-quality neural simulator referred to as DriveGAN that achieves controllability by disentangling different components without supervision. In addition to steering controls, it also includes controls for sampling features of a scene, such as the weather as well as the location of non-player objects. Since DriveGAN is a fully differentiable simulator, it further allows for re-simulation of a given video sequence, offering an agent to drive through a recorded scene again, possibly taking different actions. We train DriveGAN on multiple datasets, including 160 hours of real-world driving data. We showcase that our approach greatly surpasses the performance of previous data-driven simulators, and allows for new features not explored before.