Sensors Simulation for Autonomous Systems

Name: Sensors Simulation for Autonomous Systems
Rating: 4.1 (22 reviews)

Sensors Simulation for Autonomous Systems using SimX for Radar , Camera Lidar and Ultrasonics sensors using LabVIEW

Created bySimX Academy

Last updated 11/2025

English

English [Auto],

What you'll learn

Learn how to simulate Radar , Camera and Lidar sensors for autonomous systems using SimXai simulator
Learn to detect obstacles in lidar point clouds through clustering and segmentation, apply thresholds and filters to radar data
Process raw lidar data using Velodyne sensors with filtering, segmentation, and clustering to detect other vehicles on the road
Analyze radar signatures to detect and track objects. Calculate velocity and orientation by correcting for radial velocity distortions, noise, and occlusions

Course content

8 sections • 37 lectures • 1h 36m total length

Introduction1:21
Course Content0:57

SimXai Simulation3:05
Explore SimXai, a multi-domain simulator for autonomous vehicles and robots, design environments with an open environment editor, configure vehicle dynamics, and stream sensor data via the LabVIEW SDK.
SimXai Light Version0:28
Explore a physics-based xd simulator for modeling radar, lidar, and camera sensors, featuring the lite version with predefined maps and assets, designed for easy use and interaction via flint.

LabVIEW by NI Emerson1:13
LabVIEW Getting Started1:12
LabVIEW Project1:45
First LabVIEW Code1:05
Error Debugging0:19
Identify wiring issues that prevent code from running, then use the error and warning list accessed via the broken arrow to locate and fix the error.
Data Flow0:17
Data Types1:17
Explore core data types in Levi, including numeric (double and integers), boolean, string, arrays, and clusters, and learn 64-bit floating point representation and signed versus unsigned integers.
While Loop3:27
For Loop1:15
Shift Registers3:11

Radar Principles3:30
Radar Simulation3:00
Radar Cross Section1:56
3D Radar Cube2:41
Targets Range Estimation8:01
Learn how radar estimates target range for four targets using fmcw radar, beat frequency, and time-of-flight calculations with the speed of light.
Fast Fourier Transform (FFT) for Range Calculation3:56
Doppler Estimation2:05
2D FFT for Doppler Velocity Calculation7:17
Apply a two-dimensional fft to radar data to extract target range and velocity, using column and row ffts to calculate doppler velocity and visualize results in a 3d radar cube.

Module Content0:26
Navigating the Editor3:35
Navigate the scenario editor’s 3D viewport to place vehicles, pedestrians, and signs, manage assets in the content browser and world outliner, and adjust position, rotation, and scale.
Placing Vehicles in the Scenario Editor0:53
Refining Vehicle Behaviour8:54
Refine vehicle behaviour in sensors simulation by adjusting set speed, initial speed, and obeying speed limits, then tune search forward backward distance and lane change to evaluate steering accuracy.
Tagging System1:14
Scenario File Generation1:04
Vehicle Trigger Boxes1:26
Use vehicle trigger boxes to define actions when vehicles or intersections interact. Drag and drop triggers from search results and set actions such as changing lanes or staying in lane.

Requirements

Basic knowledge of Sensor Theory

Description

Simulation is a key technology for developing, verifying and validating the behavior of highly automated vehicles in a variety of scenarios, environments, system configurations and driver characteristics. More and more engineers use this powerful technology in their daily work to solve multidimensional and interdisciplinary problems. Simulation is mainly used where classical experiments (under controlled conditions) are not possible due to the size, number and complexity or also because of the impact on the environment. The increasing product complexity of software-defined vehicles (SDV) and their mapping to digital twins (DT) also leads to deep supply chains in the simulation domain. To navigate this data ecosystem, it is not just about understanding the technology itself, but more importantly be able to confidently evaluate simulation models, methods and processes, know their limitations and optimize the relationship between business impact and resources used.

This course is designed to approach simulation-driven development of highly automated and self-driving cars from both a latest and a future technology perspective

Powered by NVIDIA and Unreal Engine ,The course builds on standardization projects such as ASAM OpenX and covers software approaches to simplify participants' entry into the technology area

Modules

A - Sensors Simulation (Radar , Camera , Lidar , Ultrasonic Sensors)

B - Scenarios & Driving Functions ( ASAM OpenDrive , ASAM OpenScenario )

Who this course is for:

Sensor Fusion Engineer , Vehicle Test Engineer , ADAS/AV Function Owner

Sensors Simulation for Autonomous Systems

What you'll learn

Explore related topics

Course content

Introduction2 lectures • 2min

Introduction to SimXai Sensors Simulation2 lectures • 4min

Getting Started2 lectures • 6min

LabVIEW Programming10 lectures • 15min

Radar8 lectures • 32min

LiDAR5 lectures • 19min

Vehicle Behavior and Environment Simulation.7 lectures • 18min

To Be Continued1 lecture • 1min

Requirements

Description

Who this course is for: