UniSim: A Neural Closed-Loop Sensor Simulator

TL;DR

UniSim is a neural sensor simulator that transforms a single recorded driving log into realistic closed-loop multi-sensor data, enabling safe and accurate testing of autonomous vehicles in safety-critical scenarios.

Contribution

UniSim introduces a neural feature grid-based approach to convert recorded logs into realistic, configurable closed-loop sensor simulations for autonomous vehicle testing.

Findings

Simulates LiDAR and camera data with small domain gap

Enables closed-loop evaluation of SDV in safety-critical scenarios

Handles scene modifications like actor addition/removal effectively

Abstract

Rigorously testing autonomy systems is essential for making safe self-driving vehicles (SDV) a reality. It requires one to generate safety critical scenarios beyond what can be collected safely in the world, as many scenarios happen rarely on public roads. To accurately evaluate performance, we need to test the SDV on these scenarios in closed-loop, where the SDV and other actors interact with each other at each timestep. Previously recorded driving logs provide a rich resource to build these new scenarios from, but for closed loop evaluation, we need to modify the sensor data based on the new scene configuration and the SDV's decisions, as actors might be added or removed and the trajectories of existing actors and the SDV will differ from the original log. In this paper, we present UniSim, a neural sensor simulator that takes a single recorded log captured by a sensor-equipped vehicle and converts it into a realistic closed-loop multi-sensor simulation. UniSim builds neural feature grids to reconstruct both the static background and dynamic actors in the scene, and composites them together to simulate LiDAR and camera data at new viewpoints, with actors added or removed and at new placements. To better handle extrapolated views, we incorporate learnable priors for dynamic objects, and leverage a convolutional network to complete unseen regions. Our experiments show UniSim can simulate realistic sensor data with small domain gap on downstream tasks. With UniSim, we demonstrate closed-loop evaluation of an autonomy system on safety-critical scenarios as if it were in the real world.