Members Profile

Persival GmbH

Tool Vendor / Service Provider

The development of automated driving systems is increasingly virtualised with the help of simulated vehicle environments. However, perception sensors, as the interface between the vehicle and the open world, pose one of the greatest challenges. Perception sensor simulation software saves our customers' time, money, and test engineers. It transfers most of the testing and safety validation effort from the real world to simulation. Persival supports the use of perception sensor models for each individual use case, from defining requirements, to building custom sensor models, to validating with real-world measurements. Our simulation and validation services are not limited to the automotive industry, as we also provide virtual camera, lidar, radar and ultrasonic sensors for any wheeled and non-wheeled robotic and infrastructure applications.

ASAM related products

Custom Perception Sensor Model Development
Type
Software as a Service
Functionalities
Persival offers tailored perception sensor model development designed to match the specific Operational Design Domain (ODD) of your real-world sensors and functions. Our process begins with clear requirements and acceptance tests, ensuring alignment with your goals. The primary focus is on validating synthetic sensor data for accuracy and reliability. We integrate sensor models seamlessly using the ASAM Open Simulation Interface (OSI) and provide them packaged as Functional Mock-up Units (FMU) for easy deployment in your simulation environments.
Supported ASAM Standards
ASAM OpenCRG® , ASAM OpenDRIVE® , ASAM OpenMATERIAL® , ASAM OpenSCENARIO® , ASAM OpenSCENARIO® XML , ASAM OSI®
Persival Simspector
Type
3D Asset and Sensor Data Analysis
Functionalities
Persival Simspector is designed to streamline perception sensor modeling by offering advanced visualization and debugging capabilities. Whether you’re working with synthetic data or real-world inputs, Simspector provides an intuitive platform to inspect 3D assets in detail. With support for OpenMATERIAL, Simspector enables you to view asset geometry, partitioning, mesh levels of detail, and material assignments—all in one place. Overlay perception sensor data onto static and dynamic 3D objects, enhancing your understanding of how sensors interact with the environment. Seamlessly integrate Simspector into your existing simulation via ASAM OSI over TCP/IP, and enjoy compatibility with both SensorView and SensorData. Elevate your sensor modeling workflow with Persival Simspector.
Supported ASAM Standards
ASAM OpenDRIVE® , ASAM OpenMATERIAL® , ASAM OpenSCENARIO® , ASAM OpenSCENARIO® XML , ASAM OSI®
Persival Avelon
Type
Perception Sensor Model Validation
Functionalities
Persival Avelon is a software tool for automated evaluation of perception sensor data. It enables a structured validation process by comparing real and synthetic sensor data within a model validation campaign. Users can define multiple tests using a flexible combination of filters, metrics, and acceptance criteria - like assembling a construction kit. This approach allows for tailored assessments of specific effects in the data, ensuring a transparent and human-understandable validation process. The final output is a comprehensive report containing the results and conclusions from all tests, and samples within the campaign. This report provides insights into the overall simulation model performance based on the data to be compared.
Supported ASAM Standards
ASAM OpenDRIVE® , ASAM OpenMATERIAL® , ASAM OpenSCENARIO® , ASAM OpenSCENARIO® XML , ASAM OSI®
Perception Sensor Performance Measurements
Type
Specific Measurements and Data Analysis
Functionalities
We provide comprehensive measurement setups and execution, incorporating reference sensors enabling sample-wise validation of synthetic sensor data against real-world data: https://www.persival.de/performance-measurements Special focus is given to environmental factors, with our weather test bench equipped with precision reference sensors measuring parameters like visibility, brightness, precipitation drop size and speed, temperature, wind speed, and direction. Our test bench supports year-round measurements in a variety of real-world conditions, and can accommodate multiple LiDAR and radar sensors. We conduct these measurements according to the DIN SAE Spec 91471 standard and compare them with simulation results to validate sensor models. Currently, we are working on semi-automated test benches to further streamline this process.
Supported ASAM Standards
ASAM OpenCRG® , ASAM OpenDRIVE® , ASAM OpenLABEL® , ASAM OpenMATERIAL® , ASAM OpenODD® , ASAM OpenSCENARIO® , ASAM OpenSCENARIO® XML , ASAM OSI® , ASAM OpenTestSpecification
Specification of Perception Sensor Simulation
Type
Requirements Engineering
Functionalities
Persival's approach to requirements engineering for perception sensors is rooted in cutting-edge methodologies and tools. We utilize the Perception Sensor Collaborative Effect and Cause Tree (PerCollECT), an open-source framework designed to systematically analyze cause-effect relationships in sensor performance (https://github.com/PerCollECT). For safety and validation, we integrate SOTIF Trigger Conditions with Cause, Effect, and Phenomenon Relevance Analysis (CEPRA), providing a comprehensive understanding of sensor behavior in critical scenarios (https://tuprints.ulb.tu-darmstadt.de/18949/). Additionally, we apply robust metrics for model acceptance tests, ensuring that our sensor models meet rigorous standards for accuracy and reliability (https://tuprints.ulb.tu-darmstadt.de/23034/).
Supported ASAM Standards
ASAM OpenCRG® , ASAM OpenDRIVE® , ASAM OpenLABEL® , ASAM OpenMATERIAL® , ASAM OpenODD® , ASAM OpenSCENARIO® , ASAM OpenSCENARIO® XML , ASAM OSI® , ASAM OpenTestSpecification

Keywords

Perception Sensor Simulation and Model Validation

CONTACT INFORMATION
Address
Carlo-Mierendorff-str. 2
64372 Ober-Ramstadt
Germany
Phone
+49 6154 803659-1
Website