Validation of ADAS/AD Platforms (ECUs) with Data Replay Testing

• Test sensor fusion and perception components with recorded real-world data
• Synchronous replay of heterogeneous data streams (sensors and vehicle bus data)
• Real-time data adaptation of the recorded data with security and time information, e.g., SecOC, IPSec
• Modular approach to fit variant bandwidth requirements

Task

Benchmarking different software versions of the ADAS/AD platforms, and validation and release testing of the perception and sensor fusion platforms (ECUs) is a challenging task. Real-world data is crucial for these tests as the platforms must be tested within different real-world environment and traffic scenarios to prove their performance in the complex conditions and not only within simple synthetic simulations.

Challenge

During the data replay tests, the ADAS/AD platforms must be fed with data in the same manner as in the vehicle during real test drives. Heterogeneous data streams including sensor and network/bus data must be synchronized. A single AD platform can be fed with data of more than 25 sensors, which in turn adds up to more than 40 Gbit/s bandwidth in some cases. Another challenging aspect is the growing number of security and safety functions in the new ADAS/AD platforms. Some platforms are equipped with “Replay Attack” counter measures, which makes replaying the data directly as they are recorded invalid, as fault mode is automatically triggered. All of this must be done in a very scalable manner to ensure testing thousands or even millions of kilometers within a short time frame.

Solution

System modularity is at the core of the dSPACE data replay solutions to enable test scalability and to master the data replay tests. Variant bandwidth requirements can be covered by easily upgrading the server PC, while additional sensor and bus interfaces can be simply expanded by adding Environment Sensor Interface Units (ESI Units) and SCALEXIO systems.

All these components are synchronized by gPTP (generalized Precision Timing Protocol), to ensure synchronous data feed. The SCALEXIO real-time system maintains low-jitter real-time replay of all the vehicle bus data, such as Ethernet (Some/IP), CAN, and FlexRay. It also supports real-time adaptation of the recorded data with security and time information to test and overcome the “Replay Attack” measures in the ADAS/AD platforms. The Environment Sensor Interface Unit (ESI Unit) supports a wide range of standard sensor interfaces and is easily adaptable with new ones. Scalability is also granted, as the entire system can be easily automated through open APIs. Another advantage is that the complete system can be used with minimal effort for closed-loop simulation in addition to data replay tests.

RTMaps, the development framework for multisensor applications from Intempora, supports the synchronous replay of recorded data streams within a wide range of file formats, such as MDF4, rosbags, DAT files, etc., in addition to comprehensive 2-D, 3-D visualization capabilities. This is advantageous for debugging and fault analysis. Real-time access on SCALEXIO and RTMaps is granted through XIL API, which can be used for monitoring, analysis, and manipulation of the replayed data in real time by the dSPACE ControlDesk software.