Autonomous Vehicle Simulation Simulation will be an essential part of the development and testing of Autonomous Vehicles as physical testing alone will not be enough to prove that they are safe. Our simulation solutions use rFpro with physics based sensor models and scenario based testing designed to test your system against diverse edge cases as well as routine driving operation

Virtual testing

rFpro provides driving simulation software and Digital-Twins for Autonomous Driving, ADAS and Vehicle Dynamics development, testing and validation. You can immerse the complete autonomous vehicle control system into the virtual world using sensor models, your vehicle dynamics model, your controllers and real world locations.

Sensor realistic simulation

Claytex develops camera, radar and LiDAR sensor models based on physics for use with rFpro. These models are representative of the real sensors and include weather and other noise effects.

Scenario based testing

Our Simulation Manager enables scenario based testing with support for OpenSCENARIO and OpenDRIVE. Define the intended trajectory for the ego vehicle, traffic and pedestrians and measure the system performance.  Reuse a single scenario in multiple virtual worlds and vary weather and time of day to challenge your system.

Measuring your performance

Simulation Manager for rFpro includes metrics that can be calculated to measure your system performance during a test and quantify the risk. It provides an extendible plugin mechanism to allow you to add your own metrics to measure performance.

Ground truth

In simulation we can generate pixel perfect, labelled, ground truth data to train and test your perception layer. It can also be used to bypass the perception layer and focus on the planning and actuation part of the control system

Use your vehicle model

rFpro has interfaces to a wide range of vehicle dynamics software including Dymola, IPG CarMaker, SimPack, VI-Grade, Carsim, Simulink and also offers an open API enabling support for others

Real time capable

rFpro supports both real-time and “as fast as possible” simulation modes.  This enables both HiL testing of your control system as well as non real-time SiL testing of your control logic.  It’s also possible to generate high quality training data by running simulations slower than real-time to capture motion blur and shutter effects into each camera frame.

Control system integration

Our sensor models replicate the output messages from the real devices they represent easing the integration of your controller into the simulator.  Generic sensor models also output UDP messages and receivers can accept UDP to bring the “driver” demands back into the simulator.  A ROS interface is also available.

Related Articles

  • Introduction to Supervised Learning
    Introduction to Supervised Learning

    Though there are many definitions of machine learning (“ML”), the principal idea is to give an algorithm the ability to improve without programming it explicitly. It gets around the fact that the set of all possible behaviours given all possible inputs quickly becomes too complex to describe and programme in a classical way. In this blog we will give a […]

    Read More »
  • AVS #5: Providing the Safety Case: is it Deterministic or Stochastic?
    AVS #5: Providing the Safety Case: is it Deterministic or Stochastic?

    Providing the structure in which Self-driving Vehicle Safety Case can take place is the next challenge for the Government. It is the make-or-break of the entire industry. In doing so, there are questions on the nature of safety to be answered. Are there? Introduction There are two ways to understand the risks that AVs face. A deterministic system is one […]

    Read More »
  • AVS #4: Measuring Safety – the ‘99% reliable’ fallacy
    AVS #4: Measuring Safety – the ‘99% reliable’ fallacy

    “99% reliable” sounds good. An autonomous vehicle advertised as being ‘99%’ reliable conveys a message of trustworthiness, but naturally cannot be perfect. But this is not enough. It has to be 99.9999% reliable, or more! Why? “An autonomous car must be as safe as a human driver” – this statement is a key AV performance criterion. Every government publishes the […]

    Read More »

How do we prove that autonomous vehicles are safe?

rFpro rFpro logo Driving simulation for ADAS, vehicle dynamics and autonomous system development and testing
Dymola Dymola logo Build multi-domain physics based vehicle models for use in rFpro and desktop Modelica Modelica Libraries Logo Claytex develops and distributes a wide range of Modelica model libraries. FMI FMI logo Using FMI we can help you maximise the value in your models by making them more accessible in other tools. Reqtify Reqtify Requirements traceability across multiple tools to support quality and certification process with impact analysis


Got a question? Just fill in this form and send it to us and we'll get back to you shortly.


© Copyright 2010-2022 Claytex Services Ltd All Rights Reserved

Log in with your credentials

Forgot your details?