An Integrated Simulation Platform to Validate Autonomous Vehicle Safety

The ANSYS autonomous vehicle opens simulation platform addresses several challenges by integrating physics, electronics, and embedded systems and software to accurately simulate complete autonomous driving systems in a fraction of the time and cost required for road testing.

Automotive

Whitepaper ADAS

Challenge

Autonomous driving systems rely upon sensors and embedded software for localization, perception, motion planning and execution. Autonomous driving systems can only be released to the public after developers have demonstrated their ability to achieve extremely high levels of safety. Today’s hands-off autonomous driving systems are largely built with deep learning algorithms that can be trained to make the right decision for nearly every driving situation. These systems, however, lack the detailed requirements and architecture that have been used up to now to validate safety-critical software, such as that which controls commercial airliners. Road testing is clearly an essential part of the development process, but billions of miles of road testing would be required to validate the safety of autonomous driving systems and software. 

 

Solution

The ANSYS autonomous vehicle open simulation platform addresses this challenge by integrating physics, electronics, and embedded systems and software to accurately simulate complete autonomous driving systems in a fraction of the time and cost required for road testing. ANSYS capabilities span the simulation of all sensors, including lidars, cameras, radars, and ultrasonic sensors; the multiphysics simulation of physical and electronic components; the analysis of system functional safety; as well as the design and automatic code generation of safety-certified embedded software. Sensor simulation can be integrated into a closed-loop simulation environment that interacts with traffic simulators, enabling thousands of driving scenarios to be executed virtually. ANSYS medini analyze helps to manage the safety validation process by implementing key safety analysis methods such as failure modes and effects analysis (FMEA) while supporting safety analysis and design according to ISO 26262 for electrical/electronic systems and software-controlled safety-related functions. This integrated solution can achieve end-to-end safety in deep-learning-based and other autonomous driving systems.  

Benefits 

ANSYS has leveraged its vast experience in multiphysics simulation and  safety-critical embedded software to deliver a complete closed loop simulation platform for virtual testing of autonomous driving systems that includes physically accurate sensor models, virtual environment and scenarios and virtual SIL and HIL testing. These unique capabilities enable you to drive your future autonomous vehicle on virtual test tracks with realistic traffic conditions, including weather, oncoming vehicles and pedestrian scenarios, to train your machine learning software and validate its response to any driving scenario. By providing realistic physics-based simulation in real time, ANSYS enables automotive systems engineers to create the safest autonomous driving systems.

  

TO GO FURTHER

Learn more about VRX 2018

 

See other white papers

See other customer testimonials

See other success stories