LiDARsim: Realistic LiDAR Simulation by Leveraging the Real World

06/16/2020
by   Sivabalan Manivasagam, et al.
12

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.

READ FULL TEXT

page 1

page 2

page 5

page 6

page 8

page 9

research
08/03/2023

UniSim: A Neural Closed-Loop Sensor Simulator

Rigorously testing autonomy systems is essential for making safe self-dr...
research
09/22/2022

Learning to Simulate Realistic LiDARs

Simulating realistic sensors is a challenging part in data generation fo...
research
01/16/2021

GeoSim: Realistic Video Simulation via Geometry-Aware Composition for Self-Driving

Scalable sensor simulation is an important yet challenging open problem ...
research
05/08/2020

SurfelGAN: Synthesizing Realistic Sensor Data for Autonomous Driving

Autonomous driving system development is critically dependent on the abi...
research
11/24/2019

Unsupervised Neural Sensor Models for Synthetic LiDAR Data Augmentation

Data scarcity is a bottleneck to machine learning-based perception modul...
research
04/30/2021

DriveGAN: Towards a Controllable High-Quality Neural Simulation

Realistic simulators are critical for training and verifying robotics sy...
research
08/02/2023

LiDAR View Synthesis for Robust Vehicle Navigation Without Expert Labels

Deep learning models for self-driving cars require a diverse training da...

Please sign up or login with your details

Forgot password? Click here to reset