Innoviz Advances Embedded Perception with Next-Generation LiDAR Platforms for Level 4 Autonomy

Innoviz Technologies is taking a major step forward in the evolution of automotive sensing by moving perception closer to the sensor itself. In a recent interview with Automotive Industries, Anna Michlin, VP of Product Management at Innoviz Technologies, explained how the company’s new Advanced Development Program is designed to give OEMs a standardized, safety-critical output directly from the LiDAR sensor, reducing latency and easing the burden on central compute systems. That shift is especially important for Level 4 autonomous driving, where milliseconds matter and reliability must be built into every layer of the vehicle architecture.

Michlin also outlined how InnovizThree represents a compact, cost-efficient, behind-the-glass LiDAR platform that maintains automotive-grade performance while making integration easier for OEMs. Alongside InnovizTwo, which is already being deployed in major production programs such as the autonomous shuttle developed by Volkswagen Group, the company is expanding its reach into trucking, commercial delivery, defense, and security applications. From embedded perception and sensor fusion to ultra-long-range sensing and automotive-grade production readiness, Innoviz is pursuing a strategy centered on safety, scalability, and practical deployment. As autonomous mobility moves from pilot programs to large-scale commercialization, Innoviz believes the future belongs to sensor systems that combine high performance with production-proven reliability.

Bringing Perception Directly to the Sensor

One of Innoviz’s most significant recent developments is its Advanced Development Program, which integrates native LiDAR perception software directly onto the InnovizTwo platform.

According to Michlin, some automotive OEMs require a LiDAR sensor that delivers a standardized, safety-critical output that other vehicle systems can rely upon directly.

“For them, the case is about latency, reliability, and functional safety. Piping raw data to a central processor costs latency in critical decisions and adds load on vehicle networks. Extending perception closer to the sensor gives them an independent processing node that keeps functioning regardless of what’s happening in the central compute stack.”

This architecture reduces dependence on centralized computing resources while creating an additional layer of operational resilience. In highly automated vehicles, perception becomes available directly at the sensor level, ensuring that critical information remains available even if other computing systems become overloaded or degraded.

Why On-Sensor Perception Matters for Level 4 Autonomy

Moving perception processing from a vehicle’s central computer directly onto the sensor offers major technical and safety benefits.

Michlin explained that the most immediate advantage is reduced latency.

“From a latency perspective, when perception runs on-sensor, you eliminate the round-trip time to a central processor. In a Level 4 system, every millisecond of response time in safety-critical decisions matters.”

The second benefit is reliability. By generating a standardized perception output directly from the sensor, the vehicle receives information from an independent perception channel.

“This means you have a perception channel that keeps functioning correctly even if other system components are under heavy load or degraded.”

Functional safety is another critical consideration.

“The fundamental difference between Level 3 and Level 4 is the availability of human fallback. At Level 4, there’s no expectation of a driver being on alert. On-sensor perception, operating independently from central compute and on top of it, is a core architectural building block for achieving that availability.”

For autonomous vehicle developers, this creates an additional layer of redundancy that supports higher levels of automation.

InnovizThree: Smaller, Smarter, and Easier to Integrate

InnovizThree represents a major redesign of automotive-grade LiDAR, focused not only on performance but also on real-world vehicle integration.

Michlin described the new platform as a rethinking of how LiDAR should fit within modern vehicle architectures.

“InnovizThree is a rethink of what an automotive-grade LiDAR needs to look like, not just what it needs to do.”

At just 600 grams, InnovizThree is approximately 60% smaller than InnovizTwo.

This compact form factor enables installation behind the windshield, on rooftops, or within front grilles while preserving vehicle styling and aerodynamics.

“That compact form is what enables the deployment position that the automotive industry has been waiting for: behind the windshield, on the rooftop, or in the front grille, without compromising vehicle aerodynamics or exterior design.”

The platform combines a tighter optical architecture with 905nm Time-of-Flight technology and lower-power operating modes that reduce thermal loads and allow smaller housing designs.

Despite its reduced size, performance has improved.

“InnovizThree detects beyond 250 metres and delivers over 35% cost reduction compared to InnovizTwo. Size went down, performance went up, and cost went down. That is not a compromise, it is a generation shift.”

The result is a platform designed to support broader adoption across future vehicle programs.

Colored 3D Sensor Fusion Simplifies Integration

Another key innovation is InnovizThree’s sensor-fusion colored 3D LiDAR and camera system.

This approach combines camera imagery and LiDAR point cloud information into a single, perfectly calibrated perception dataset.

According to Michlin, the technology delivers several benefits.

“Firstly with a perfectly calibrated point cloud and camera data. Second, it simplifies sensor fusion, third, it enriches environmental perception with RGB on top of the point cloud, and lastly we simplified the mechanical integration in the area of the windshield where it matters the most.”

For OEMs, reducing sensor calibration complexity can help lower integration costs while improving perception quality and environmental understanding.

Volkswagen ID. Buzz AD: From Pilot Projects to Series Production

One of Innoviz’s most significant achievements is its participation in the ID. Buzz AD autonomous shuttle program from Volkswagen Group.

Each vehicle incorporates nine InnovizTwo LiDAR sensors to provide complete 360-degree environmental coverage.

Michlin views the project as a turning point for the autonomous vehicle industry.

“The ID. Buzz AD program is a landmark for the entire industry as it is the world’s first Level 4 robotaxi to enter series production, and Innoviz is proud to be at the centre of it.”

Unlike many autonomous vehicle programs that remain limited to testing environments, this initiative represents genuine production deployment.

“This isn’t a pilot fleet or a proof-of-concept, it is full series production.”

The project also highlighted the complexity of delivering automotive-grade autonomy at scale.

“Every aspect from the mechanical integration across nine mounting positions, the sensor-to-sensor calibration, the all-weather blockage resilience, and the functional safety certification, have to hold to the same standard on vehicle number ten thousand as it does on vehicle number one.”

That level of consistency demands production expertise beyond pure sensor performance.

“What we have built with Volkswagen is a validated, production-ready suite.”

As the ID. Buzz AD expands into European and U.S. cities, Innoviz expects the experience gained from the program to strengthen confidence among future OEM customers.

Extending LiDAR Vision to One Kilometer

Innoviz has also introduced InnovizTwo Ultra Long-Range (ULR) LiDAR, extending detection capabilities to as far as one kilometer.

According to Michlin, this dramatically expands the operating envelope of autonomous systems.

“One-kilometer sensing range fundamentally changes the operating envelope for autonomous systems.”

For autonomous trucking, the ability to detect hazards at such distances provides critical additional reaction time.

“At that distance, a heavy truck travelling at highway speed has more than 30 seconds of decision time before it reaches the detected object.”

This enables smoother braking, safer operations, and reduced wear on vehicle systems.

“For autonomous highway trucking, the ULR allows vehicles to anticipate lane merges, slow-moving traffic, and road debris at distances no prior LiDAR could resolve.”

The technology is particularly relevant for autonomous trucking programs such as those being developed by Daimler Truck and Torc Robotics.

Beyond transportation, Michlin sees significant opportunities in defense and homeland security.

“Border surveillance, airport runway monitoring, and port perimeter security all require sustained, reliable 3D detection at long ranges across harsh outdoor conditions.”

The system is designed to maintain performance even in dust, rain, and extreme temperatures.

Expanding Beyond Passenger Vehicles with LOXO

Innoviz is also broadening its reach beyond traditional passenger vehicle applications through its partnership with LOXO.

The collaboration focuses on autonomous last-mile delivery vehicles operating in real-world logistics environments.

According to Michlin, the partnership reflects Innoviz’s broader strategy of leveraging automotive-grade technology across commercial and industrial sectors.

“The LOXO partnership is a strong example of how Innoviz is applying its automotive-grade technology platform to commercial and industrial use cases beyond passenger vehicles.”

LOXO selected InnovizTwo following an extensive evaluation process, citing both technical performance and manufacturing reliability.

“LOXO selected InnovizTwo after a thorough market evaluation, specifically citing point cloud quality at long distances and the supply and manufacturing reliability that comes from Innoviz’s existing validation by major automotive manufacturers.”

The partnership demonstrates how technologies originally developed for passenger vehicles can be successfully adapted to logistics, transportation, and industrial automation.

Conclusion

Innoviz’s latest innovations demonstrate how LiDAR technology is evolving from a sensing component into an intelligent perception platform. By integrating perception directly onto sensors, reducing hardware size and cost, introducing advanced sensor fusion, and extending detection ranges to unprecedented distances, the company is addressing some of the industry’s most pressing challenges.

Equally important, Innoviz is proving that its technology can operate at true automotive production scale through programs such as the Volkswagen ID. Buzz AD while simultaneously expanding into trucking, logistics, defense, and security applications. As the autonomous mobility market continues to mature, Innoviz’s combination of embedded perception, production readiness, and scalable deployment positions the company as a significant contributor to the future of autonomous transportation.