Following a joint demonstration at Embedded World (10–12 March), RemotiveLabs and Vayavya Labs announced a system-level ADAS validation setup.
-- Following a joint demonstration at Embedded World (10–12 March), RemotiveLabs and Vayavya Labs announced a system-level ADAS validation setup that brings the full vehicle electronic architecture into software-in-the-loop (SIL). By combining Autoware, CARLA, and a virtual E/E architecture represented by RemotiveTopology, the companies demonstrated how OEMs and Tier 1s can validate autonomous driving behavior together with the vehicle’s electronic architecture - already at the SIL stage, before physical ECUs, HIL benches, or vehicle prototypes are available.
The challenge: ADAS in isolation vs. vehicle reality
In most ADAS/ADS verification workflows today, simulation tools validate algorithms using scenario generators, sensor models, and vehicle dynamics. What is typically missing is the surrounding vehicle network - signal timing, cross-ECU dependencies, combining CAN/Ethernet/LIN communication, and system-level interactions.
To reproduce that full complexity, teams must move to HIL benches or physical vehicles - both expensive, capacity-constrained, and dependent on specialized integration teams. This often creates early project waiting time and long feedback loops. Instead of validating the ADAS stack in isolation, the demo first shown at Embedded world runs the AD stack operating as part of a realistic vehicle network in a closed-loop simulation.
From months to weeks: bringing the vehicle network into SIL
Vayavya Labs specializes in building production-grade SIL and system validation environments. With the reference integration demonstrated at Embedded World they leverage RemotiveTopology to showcase how teams can establish a realistic system-level setup in a fraction of the traditional time. They presented a closed-loop reference integration where full vehicle behavior becomes visible already in SIL - not reconstructed later on hardware. A closed-loop reference setup:
- Autoware (Level 4 autonomous driving stack) runs as a node inside RemotiveTopology
- CARLA provides vehicle dynamics, scenarios, and visualization
- Network signals carry throttle, brake, and steering commands through the virtual E/E architecture
- Vehicle state feeds back into the network, enabling system-level behavior to be observed, logged, and debugged in SIL
"Testing an ADS ECU within a vehicle EE network is typically effort-intensive, requiring complex HIL or bench setups, physical harnesses, and ADAS environment simulation - often consuming tens of person-months and still resulting in only semi-automated testing. " Nitin Swamy, Director, Automotive Systems, Vayavya Labs
By combining Vayavya Labs’ validation expertise with RemotiveLabs’ virtual vehicle platform, teams can start integration testing in week one and scale depth as projects evolve.
No toolchain lock-in
Unlike traditional hardware-centric validation environments, the architecture is simulator-agnostic and supports integration of tools from multiple vendors. OEMs and Tier 1s are not forced into a single proprietary ecosystem. Existing simulation tools can be integrated into the topology, networks can be reconfigured as architectures evolve, and system-level test cases can be reused across SIL, HIL, and future vehicle platforms.
"For too long, system-level validation has been gated behind hardware availability. With this integration, we're showing that the full vehicle network can be part of the loop from week one. That's not an incremental improvement - it's a different way of working." Per Sigurdson, CEO and co-founder, RemotiveLabs
Because the network structure remains available throughout the lifecycle, the same system-level environment continues to deliver value beyond early development which supports regression testing, platform updates, and reuse across future programs.
Earlier confidence, lasting value
For ADAS and ADS development, simulation is the only scalable way to explore edge cases and rare scenarios safely. Bringing the full vehicle network into SIL enables:
- Earlier issue discovery
- Reduced dependency on physical test infrastructure
- Faster system integration
- Reusable validation environments across platforms
The result is less waiting at program start and validation environments that continue to deliver value throughout the vehicle lifecycle.
The integration built by Vayavya Labs using RemotiveLabs’ tooling is designed to scale across compute environments - from local GPU workstations to cloud infrastructure. It can also expand to include additional vehicle domains within the same virtual topology. The next planned step is to include Android running in Cuttlefish, bringing the infotainment node into the same environment as the ADAS stack and vehicle E/E architecture.
About
Vayavya Labs is a Silicon-to-System engineering services partner specializing in vECU development, SIL, and system-level verification and validation for ADAS and autonomous systems: https://vayavyalabs.com/
RemotiveLabs provides a simpler way to prototype, build, and test vehicle software with RemotiveTopology, enabling modular vehicle development across SIL and HIL:https://remotivelabs.com/
Contact Info:
Name: Sheharyar Khan
Email: Send Email
Organization: HackerNoon
Website: https://hackernoon.com/
Video URL: https://youtu.be/cE76Qkp2uoU?si=OrxTsEZl0HN6f3fQ
Release ID: 89186234
In the event of detecting errors, concerns, or irregularities in the content shared in this press release that require attention or if there is a need for a press release takedown, we kindly request that you inform us promptly by contacting error@releasecontact.com (it is important to note that this email is the authorized channel for such matters, sending multiple emails to multiple addresses does not necessarily help expedite your request). Our dedicated team will promptly address your feedback within 8 hours and take necessary actions to resolve any identified issues diligently or guide you through the removal process. Providing accurate and dependable information is our utmost priority.
