New Pact Brings Us, In the automotive sector, new features have typically been introduced using an approach based on the integration of the necessary sensors and corresponding ECUs. This has led to the emergence of numerous independent systems, increasing complexity and raising costs.
Contrasting this vision is the idea of the software-defined car, which aims to implement software that is distributed across a small number of processors and shares sensors and the communication network in order to enable advanced features like autonomous driving, powertrain, body control, and infotainment. A platform that makes middleware—a software layer that enables the communication between the many dispersed components—available must be there for the software-defined automobile transition to be successful. Reliability, real-time behaviour, and low latency are required of middleware.
TTTECH AUTO, ZETTASCALE COLLABORATION
The recent collaboration agreement between TTTech Auto and ZettaScale Technology, which aims to develop the first European implementation of a data distribution service (DDS) that is safety-certified under ISO 26262 (ASIL D) for use in series cars, represents an important step toward the widespread adoption of the software-defined car. The brand-new item, called MotionWise Cyclone DDS, will provide secure and high-quality communication throughout the complete car, supporting software updates after the fact to lengthen the life of the vehicle. The Object Management Group (OMG) has standardised the middleware protocol DDS, which offers low-latency communication and a number of built-in quality-of-service (QoS) guidelines.
Through this partnership, the MotionWise platform from TTTech Auto, the open-source Cyclone DDS network protocol, and time-sensitive networking technologies will all be merged.
The safety software platform MotionWise was created for automated driving. It can manage a variety of applications, each of which operates in a unique setting. This enables you to design a secure environment where apps with various real-time and safety needs can coexist.
Friedhelm Pickhard, chief growth officer of TTTech Auto, stated “We are delivering a software platform that permits the orchestration of applications in an automobile architecture beyond ECUs.” We must make sure that every application complies with the timing, performance, and communication criteria and that this occurs in a predictable way.
The MotionWise software platform is ideal for difficult applications like automated driving because of real-time orchestration, deterministic behaviour, and guaranteed latency (independent of system load). That implies a very rigid schedule because the software cannot handle other time-consuming processes that would otherwise cause the programme to react with unacceptable latency and you must brake in a specific amount of time when the application detects an object for physical reasons.
There are two factors to think about, as Pickhard notes. First and foremost, we must make sure that the entire application chain responds and runs in a predetermined amount of time without being interrupted by another application. Second, we need to guarantee that this behaviour will continue if a new programme is downloaded.
Because it makes software testing easier each time a new application needs to be deployed, this trait is crucial. A suitable communication stack is needed to use a service-oriented architecture (SOA) like MotionWise on a vehicle. DDS is a technology that complies with these specifications, but it needs to be safe.
New Pact Brings Us Closer to Software-Defined Cars for 2022
Pickhard stated, “We are working on this jointly with ZettaScale.” “Putting DDS and our core technology together in a car is definitely a game-changer for the industry, since then we can enjoy all the benefits without having any compromise in terms of safety,” says a representative of the automotive sector.
In order to meet the demand for its two primary technologies—Cyclone DDS and Zenoh—coming from the automotive and robotics businesses, Adlink Technologies spun off ZettaScale. Zenoh is a cutting-edge protocol created to offer unified and location-transparent abstractions for computations, data in motion, and data at rest (such as databases and file systems). With a wire overhead of only 5 bytes and a throughput of over 50 Gbps, Zenoh can operate on a variety of hardware designs, from a multi-core processor to a tiny microcontroller. It also has a latency of a few tens of microseconds.
According to Angelo Corsaro, CEO of ZettaScale Technology, “Actual-time behaviour is not necessarily only about timelines; it’s also about real determinism and making sure that you have a timetable that is always followed because if you miss a deadline in a car, then you know something horrible might happen.”
The automotive sector is adopting DDS, according to Corsaro, because other industries have done so before with success, attaining a high level of modularity, reconfigurability, and seamless integration of the world in real time. These industries include avionics and military vehicles.
Dynamic discovery is one of the features of DDS that our users most value, according to Corsaro. “This is a crucial feature for systems where there is a possibility of partial failure or when you wish to add features quickly and increase capabilities. Although you cannot certify this and it is not necessary for the most important parts of the system, it is a game-changer for the less important parts of the system and throughout development.
Users can benefit from this dynamic component of the system in the non-safety-critical area. If dynamic discovery is not available and you need to test the software of a distributed system, you will need to configure each communication endpoint, which is a time-consuming and error-prone task. However, you could run the same system with one node, ten nodes, fifty nodes, or more if you had dynamic discovery. The configuration doesn’t need to be altered because the nodes are automatically found.
The fact that DDS promotes the quality of service by design is one of the simplifications that we bring in comparison to other systems, according to Corsaro. “DDS collects and expresses important non-functional aspects and gives the system significant flexibility by expressing the quality of service through a set of QoS policies.”
Although a system can be configured flexibly using a SOA design, this goes against safety regulations. Due to resource constraints, you must make sure that safety-relevant applications are prioritised and running in the lead time and order that have been established.
Pickhard explained that on the one hand, by offering the dynamic configuration mechanism, “we attempt to make the life of the designer easier, and on the other hand, we ensure through MotionWise that the applications that are safety-relevant have a deterministic behaviour.”
This is an example of a SOA paradigm, which on the one hand simplifies things for engineers by lowering complexity, while on the other hand ensuring safety and determinism.
The following stage, according to Pickhard, is to establish DDS as a high-performance safety platform for SOA systems in automobiles.
READ MORE: New BMW X7 for 2023: Don’t Focus on Its Face
