LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World

TL;DR

LiDARsim is a realistic LiDAR simulation framework that leverages real-world data and combines physics-based and learning-based methods to generate high-fidelity point clouds for autonomous vehicle testing.

Contribution

The paper introduces a novel LiDAR simulation approach that uses real-world data and a hybrid physics and neural network model for realistic point cloud generation.

Findings

Produced realistic LiDAR point clouds for diverse scenarios.

Enabled testing of perception algorithms on rare, safety-critical events.

Demonstrated effectiveness in end-to-end autonomous vehicle evaluation.

Abstract

We tackle the problem of producing realistic simulations of LiDAR point clouds, the sensor of preference for most self-driving vehicles. We argue that, by leveraging real data, we can simulate the complex world more realistically compared to employing virtual worlds built from CAD/procedural models. Towards this goal, we first build a large catalog of 3D static maps and 3D dynamic objects by driving around several cities with our self-driving fleet. We can then generate scenarios by selecting a scene from our catalog and "virtually" placing the self-driving vehicle (SDV) and a set of dynamic objects from the catalog in plausible locations in the scene. To produce realistic simulations, we develop a novel simulator that captures both the power of physics-based and learning-based simulation. We first utilize ray casting over the 3D scene and then use a deep neural network to produce deviations from the physics-based simulation, producing realistic LiDAR point clouds. We showcase LiDARsim's usefulness for perception algorithms-testing on long-tail events and end-to-end closed-loop evaluation on safety-critical scenarios.