U-blox has expanded its automotive GNSS portfolio with the launch of two highly specialized modules: the ZED-X20K and the ZED-A20K. This dual release addresses engineering needs of both mass-market advanced driver assistance systems (ADAS) and safety-critical autonomous architectures.
Both modules feature pin-to-pin compatibility, enabling platform flexibility and simplifying product development across vehicle generations as well as jamming and spoofing detection to mitigate the impact of security risks.
The ZED-X20K is designed for mass-market ADAS L3 and TCU/IVI applications, delivering lane-level accuracy worldwide using all-band GNSS and native Galileo High Accuracy Service (HAS). By eliminating the need for paid correction services, backend infrastructure, or service management, it reduces total cost and accelerates time-to-market while maintaining consistent global performance.
For applications that require a functional-safety concept for GNSS sensors, the ZED-A20K introduces a new architectural approach. It provides ISO 26262 ASIL-B(D)-compliant GNSS RAW data simultaneously to high-performance QM positioning outputs within a single module. This enables OEMs to transition from traditional dual hardware based-GNSS systems to a single module approach, reducing system complexity and cost.
With flexible support of externally hosted positioning engines, especially for ADAS of Levels 3 and up, the A20 concept enables enhanced flexibility for SDV–based architectures. The form-factor compatibility between ZED-X20K and ZED-A20K allows the flexibility to equip different trim levels with or without functional safety requirements out of a single socket.
The ZED-X20K has reached the engineering sample stage, and its evaluation kit is available. Samples for the ZED-A20K will be available starting in August.
Deepen AI has released its latest targetless calibration platform, built to simplify and accelerate calibration for complex autonomous vehicles, automotive ADAS and robotics sensor suites.
The platform supports a wide range of configurations including GNSS receives, multiple lidars, radars, cameras and inertial measurement units (IMUs). It processes all inputs in one pass using a single continuous dataset such as a ROS bag.
As sensor stacks become more sophisticated, traditional calibration methods are increasingly becoming a bottleneck in deploying autonomous systems at scale. These approaches are often manual, iterative and dependent on physical targets. Deepen AI’s solution introduces a fully automated and unified approach that calibrates all sensors simultaneously.
The platform estimates intrinsic, extrinsic and temporal parameters across the entire sensor suite in a single streamlined workflow, removing the need for sensor-by-sensor calibration. This approach streamlines operations while delivering high performance, achieving up to 0.05° angular accuracy and 0.7 cm positional accuracy, exceeding traditional target-based calibration techniques.
Capabilities include:
Simultaneous calibration across all sensors using a single dataset
Support for multi LiDAR, camera, radar, IMU, and GNSS configurations
Accuracy of up to 0.05° and 0.7 cm
No strict requirement for loop closure or fixed driving patterns
“Calibration has traditionally been one of the most time-consuming, complex and fragmented steps in deploying autonomous systems,” said Mohammad Musa, founder and CEO of Deepen AI. “With this release, teams can move to a system level approach that delivers both speed and precision using real-world data.”
The system is designed to work without controlled environments or rigid data collection protocols, allowing teams to seamlessly integrate calibration into existing workflows for both research and large-scale production deployments. It requires only simple and practical conditions, with calibration possible in locations such as parking lots, garages or quiet streets, provided the environment is mostly static with minimal moving objects. A minimum of 30 seconds of continuous driving data is required.
The platform is already being deployed with customers working on highly complex sensor configurations, where multiple lidars and cameras need to be calibrated together as a single system. In one such deployment, the full sensor stack was calibrated during a normal drive in a parking garage, parking lot, or a small residential street, without any special driving patterns or looped trajectories.
Using only a short duration of driving data, Deepen AI simultaneously performed intrinsic, extrinsic and temporal calibration across all sensors in a single workflow. This unified approach not only simplifies operations and improves consistency, but also delivers accuracy that surpasses traditional target-based calibration methods, making it well suited for both research and production environments.
Innoviz Technologies, a Tier-1 direct supplier of automotive-grade lidar sensor platforms and software stacks, is demonstrating its fully colored long-range lidar with camera at CES 2026 this week in Las Vegas.
The InnovizThree creates a compact sensor-fusion module designed to significantly reduce OEM integration complexity. The solution combines lidar and RGB sensing in a single compact perception module, purpose-built for behind-the-windshield installations, drones, micro-robotics and humanoids.
The consolidation of an RGB camera inside InnovizThree reinforces Innoviz’s commitment to scalable, OEM-friendly sensor-fusion perception solutions designed for series production and long-term deployment with the potential to enable faster deployment and cost saving.
The RGB sensing capabilities are factory-aligned with the lidar, with an ability to ensure precise and consistent visual-to-lidar geometry across production units. This alignment, combined with hardware-synchronized capture, will enable reliable multi-modal sensor-fusion data correlation while reducing calibration effort during vehicle integration., the company said.
Delivered through a single integration interface, the solution will minimize wiring, interfaces, and system complexity. This approach will reduce the overall integration burden for OEMs, which is expected to enable simpler validation processes, optimized engineering effort, lower cost and faster time-to-production.
Genesys has developed India’s first large-scale high-definition maps engineered specifically for vehicles enabled with advanced driver assistance systems (ADAS).
Covering more than 1 lakh km of India’s national highways, expressways and strategic corridors, this initiative marks one of India’s most ambitious road intelligence programs and establishes a new benchmark for automotive-grade precision.
India’s highways account for a disproportionately high share of road fatalities, driven by fast-moving traffic, inconsistent lane discipline, and limited real-time awareness for drivers and vehicles. HD maps narrow this gap by adding the centimeter-level context that traditional maps cannot provide — lane geometry, curves, slopes, signage, barriers and localization cues that help ADAS systems anticipate danger instead of merely reacting to it. This is a big leap forward from current sensor-based ADAS systems, Genesys said.
The HD maps include ADAS-critical features such as lane geometry, road markings, barriers, signage, medians, elevation and curvature profiles, and localization objects like poles and gantries — all processed to achieve centimeter-grade precision.
CORS network plays a key role
To achieve the centimeter-level accuracy required for ADAS Level 2 functionality, Genesys relies on the Survey of India’s Continuously Operating Reference Stations (CORS) network. Real-time GNSS correction signals along major corridors dramatically strengthen field operations, allowing survey teams to capture lane-level and asset-level detail that meets global automotive standards.
This work builds on the existing memorandum of understanding between Genesys and Survey of India, enabling collaboration on digital twin projects, national mapping programs, and high-accuracy geospatial missions.
These datasets are owned by Genesys and can be licensed across industries, creating opportunities in commercial fleet navigation, logistics optimization, mobility platforms, safety analytics and automotive R&D.
GNSS technology has had a reputation for unreliability in safety-critical applications, such as advanced driver assistance systems (ADAS). This perception has shaped automotive design and manufacturing: some ADAS developers have avoided GNSS altogether, instead relying on cameras, lidar and other sensors. Here, Manuel Del Castillo, VP of business development at Focal Point Positioning, explains how, with the right reliability, GNSS can offer a powerful layer of redundancy and support these other sensor types.
The hesitation to include GNSS in ADAS stacks is historical. Traditionally, this technology was unreliable, especially in dense, urban environments where satellite signals were obstructed. Consequently, many automakers turned to alternative sensors. For example, cameras can identify lane markings, traffic signs and objects, while lidar can build highly detailed 3D maps of the vehicle’s surroundings.
Each of these sensors provides important navigational data. However, they all describe a car’s location relative to its immediate environment. With no reliable source of absolute positioning, these relative measurements can’t confirm the vehicle’s exact place in the world — information that is critical for safe navigation.
Why ADAS Needs GNSS
Cameras, lidar and other sensors provide rich environmental data. However, they are limited by what they can directly observe. A camera can identify lane markings but can’t confirm which road the vehicle is on when multiple lanes or junctions overlap. Similarly, lidar can map obstacles in 3D, but without a wider frame of reference, it will struggle to anchor that map to the road network. HD maps provide another valuable layer, but without an accurate global position, they too can be misaligned with the real world, limiting their value.
GNSS can help plug this gap. By supplying absolute latitude and longitude, it ensures that the relative information from the other sensors is grounded in the correct location. GNSS helps calibrate and initialise other sensors, while also providing a cross-check against their measurements to detect potential errors or drift in sensor performance over time. Therefore, reliable GNSS is not an alternative to cameras, lidar or radar. It complements these sensors and boosts accuracy and the reliability of the overall system.
The Importance of Redundancy
Increasingly, the importance of GNSS in ADAS stacks is being recognised. As automotive production moves toward L3 automation and beyond, the demand for absolute positioning increases, along with the need for safe, layered sensing. GNSS, alongside cameras, lidar and radar, can help automakers improve navigational resilience without reinventing vehicular architectures.
Reliable GNSS isn’t about replacing other technologies. It is about reinforcing them. Having a global frame of reference helps ensure that the relative data from other sensors is grounded in the correct place. For automakers, the next step is recognising that GNSS can improve safety and trust in ADAS stacks, supporting the transition toward autonomous driving.
Advancing GNSS Reliability
Even with GNSS integrated into the vehicle’s sensors, challenges remain. Urban canyons and dense foliage can attenuate or even block satellite signals and create reflections, reducing accuracy. Since ADAS systems need reliably accurate absolute positioning, these challenges need to be addressed if we want GNSS to play a role in ADAS.
Newer, more sophisticated GNSS solutions are needed. The progression to Level 3 does not require an entirely new technology stack but rather extracting the very best from each of the existing components. For GNSS, this evolution involves implementing software-based solutions to achieve the necessary reliability improvements without overhauling hardware components. Pursuing cost-effective upgrades enhances performance without necessitating complete system redesigns, thereby keeping costs under control.
FocalPoint’s S-GNSS Auto software enhances GNSS accuracy in autonomous vehicles, providing reliable, absolute location to improve overall ADAS safety and efficiency. By boosting line-of-sight signals and rejecting non-line-of-sight signals, this simple firmware upgrade can help vehicles maintain accuracy in challenging environments.
By reducing positional uncertainty, these enhanced GNSS solutions strengthen the overall sensor stack. Together, these layers improve resilience, safety, and confidence in higher levels of vehicle automation.
As the automotive industry moves further towards L3 automation and beyond, reliable data on absolute position will be essential and will only reinforce the insights captured by cameras, lidar and other sensors.
Hi-Target, a Chinese high-precision positioning enterprise and manufacturer of high-end GNSS equipment, and GMV, a global technology group specializing in advanced navigation solutions, have established a strategic alliance to jointly develop integrated differential service solutions.
Through this partnership, Hi-Target and GMV support a wide range of automation-driven positioning applications — ADAS, robotics, UAVs, precision agriculture, smart infrastructure and intelligent mobility systems.
As industries progressively adopt automated technologies, precise and reliable positioning has become a foundational requirement across application domains. From today’s L2 and L2+ driver assistance systems (ADAS) in vehicles to autonomous UAV operations, robotic platforms, and the emerging needs of Level 3+ mobility solutions, the demand for scalable and high-accuracy positioning continues to grow.
The strategic alliance between the two companies leverages Hi-Target’s strengths in high-precision satellite navigation and user-grade GNSS systems, along with GMV’s extensive global expertise in precise navigation algorithms and satellite-based augmentation services. The result will be a high-availability, low-latency positioning service with global reach.
By combining their complementary technologies, including user-grade GNSS hardware, correction services, and augmentation infrastructure, Hi-Target and GMV will facilitate the adoption of high-precision positioning across various industries and geographic regions.
Their collaboration will support system integrators, OEMs, and solution providers in accelerating the development and deployment of automation in sectors with increasing levels of autonomy.
STMicroelectronics has unveiled the Teseo VI family of GNSS receivers. The new receivers integrate multi-constellation and quad-band signal processing on a single chip, achieving centimeter-level accuracy for various applications.
The Teseo VI family includes the STA8600A and STA8610A models, featuring dual independent Arm Cortex-M7 processing cores. These receivers are designed for automotive applications such as advanced driver assistance systems (ADAS) and autonomous driving, as well as industrial uses including asset tracking, mobile robots and precision agriculture.
The receivers integrate all necessary system elements for centimeter accuracy into one die, supporting simultaneous multi-constellation and quad-band operations. This seeks to simplify product development and enhance reliability in challenging conditions, such as urban canyons.
The Teseo VI+ variant can host enhanced positioning engines developed by third-party companies, providing real-time kinematics for centimeter position accuracy. The Teseo APP2 STA9200MA operates dual cores in lockstep, offering hardware redundancy for applications requiring ISO 26262 ASIL-B functional safety compliance12.
STMicroelectronics’ RF architecture and GNSS baseband design provide quad-band GNSS support (L1, L2, L5 and E6) with the ability to acquire and track only L5, improving performance in difficult conditions.
\All variants include hardware cybersecurity features such as secure boot, over-the-air firmware updates, and output-data protection. The devices comply with UNECE R155 and ISO 21434 specifications for cybersecurity by design. Two new GNSS automotive modules, the Teseo-VIC6A and Teseo-ELE6A, have been introduced to simplify integration of Teseo VI/VI+ ICs on customer platforms and ensure optimal performance.
It has been a wild decade, with so many players in the autonomous vehicle (AV) market, all striving for a leg up. Until the dominant design of present AV stacks emerged, there was no small amount of experimentation and less-than-successful alternate approaches. For instance, there was one big-name player that initially sought to create an AV solution without GNSS. Reality set in, and they soon embraced GNSS as an essential component.
Gordon Heidinger, segment manager, automotive and safety critical systems at Hexagon’s Autonomy and Positioning division, has had a front-row seat from which to observe, and contribute to the evolution of AV.
“I’ve been in the automotive industry for 20 years, all the way from OEMs like Chrysler to tier ones like Harman,” Heidinger said. “I’ve worked on the engineering side, on the project management side, and have now joined Hexagon | NovAtel to help further their involvement in the automotive industry. NovAtel was there for aviation 20 years ago, helping develop systems for planes to take off and land autonomously — we have a deep bench when it comes to applying such expertise for vehicular autonomy.”
NovAtel has long provided GNSS and IMU products and solutions, as well as real-time positioning services. Each are key elements of AV sensor stacks and overall autonomy solutions. Parent company Hexagon has multiple divisions contributing to intelligent transportation — on both the front end and back end.
The Front End
AV systems require highly reliable and smart sensor stacks that typically include cameras, radar, lidar and sonic sensors; these provide the relative positioning for advanced driver assistance systems (ADAS), which are becoming commonplace for newer vehicles. There are also implementations that include GNSS/IMU for navigation and lane keeping.
“Lane keeping is possible to a limited degree with combinations of the other sensors; however, you need GNSS to let you know where you truly are for autonomous driving,” Heidinger said. “Are you on the right freeway lane in Ottawa, or is this an exit ramp? This was a big problem with today’s simple single frequency solution; a car can assume highway speeds on an exit ramp, not realizing it was an exit ramp.”
Only with the absolute precise positioning that GNSS provides, and a high-definition map, level 4 autonomy — and potentially level 5 someday — could be achieved. With current sensor stacks, when the car is moving, it can reliably detect the other cars moving in its vicinity. Furthermore, vehicle-to-vehicle (V2V) solutions are being developed and tested, which enable a vehicle to share data about where it is going, its speed and acceleration, and its current location. We may remain far from full autonomy until such solutions are broadly deployed, however we will see some of the vehicle-to-everything (V2X) solutions sooner than later.
Various developers and departments of transportation around the world are testing short range V2X communication systems.
“We would need real-time construction zone updates,” Heidinger said. “It would be tough to do lane keeping if a construction site closes or diverts lanes during the course of a day. Or if cameras detect crashes, or blocked lanes, this will need to be broadcast immediately and continuously in real-time.”
A representative example of a production high precision positioning system was demonstrated at the recent Consumer Electronics Show 2023 (CES 2023). ZF Friedrichshafen AG (ZF) has developed ProConnect — a dedicated short-range communication (DSRC) solution that enables positioning and communication for use in applications with roadside infrastructure, such as traffic lights. It can be scaled to include other over-the-air alerts that could include first responder vehicle proximity and construction site status. At CES, the GNSS positioning was demonstrated with an autonomous vehicle platform from Hexagon.
“The precise map and the real-time updates from V2V and V2X systems all need precise absolute positions to relate objects to each other,” Heidinger stated. The question then becomes “…how reliable and trustworthy is that solution”?
There are international automotive-grade requirements such as the ISO 26262 standard for electrical/electronic systems, and automotive safety integrity levels. For instance, ASIL-B(D), and cybersecurity standard ISO/SAE 21434. The latter provides protection against external access without authorization.
“The level of reliability required is extremely high,” Heidinger said. “After all, these are human lives, in metal boxes hurtling along at highways speeds. There are ASIL standards that call for a probability of 10-8, or 1 in 100 million, in an hour that the system is wrong. These levels of reliability need to apply to electronic components, communications, and the availability of the GNSS positioning solution to really automate any type of vehicles. You’ll encounter similar AV standard references to five-nines, or 99.999%.”
Positioning Services
Heidinger explained that for most aspects of autonomy, GNSS can be “good enough”, even just to a foot. However, uncorrected, GNSS can never meet even those needs — achieving an accuracy of a few meters at best. Then there is the matter of reliability. Augmentations like real-time kinematics (RTK) and precise point positioning (PPP) apply broadcast “correctors” that can yield centimeter positions. RTK is not practical for broad areas or highway and road networks as it requires dense infrastructure and two-way communication with the vehicle, which can introduce security challenges.
Solutions for autonomy are typically PPP. While there are many applications of PPP that use clock, orbit and ionospheric model data broadcast from geostationary L-band satellites, for applications such as surveying, mapping, maritime and agriculture, this would not meet the reliability requirements for AV. The Achilles heel of broadcast PPP is that the satellites are usually limited in number and positioned over the equator; the vehicle can often lose sight of these. Instead, PPP services, such as that provided by NovAtel and others, are tapped by vehicles via mobile internet connections; this means cellular networks. While cellular services can often meet reliability goals, there are still vast areas of highways where availability is sparse.
The other challenge for PPP is the convergence time needed to get reliable sub-foot precision.
“No one wants to wait five minutes or more for it to converge,” Heidinger said. “By processing data from semi-dense networks of reference receivers, our PPP can converge rapidly enough to be ready to roll as soon as you start driving.”
The Back End
A free-for-all of autonomy is not going to happen on highways and roads that are not precisely mapped and kept up to date.
“There are visions of crowd sourcing map updates from the sensors in cars,” Heidinger said.
Crowd-sourced data is not systematic enough, though, and could be inconsistent. After all, there are privacy considerations, and how many vehicle owners would be willing enough to participate?
There are numerous mapping and imaging “buggies” plying road and highway networks on an ongoing basis; this could provide a base layer. But how precise? The specific applications these mapping buggies support may not need high precision. And operators may not be willing to invest in high precision/accuracy. The precision of the 3D maps would need to be higher than the target range of the AV systems. The technology exists and is broadly used for various applications in the form of centimeter precision 3D mobile mapping — at highway speeds. Such systems with lidar scanners, cameras, and positioning solutions can include GNSS, IMU, wheel speed encoders, and SLAM lidar for enhanced position stabilization. An example is the Pegasus TRK from Hexagon | Leica Geosystems.
GNSS is the key component — the provider of precise absolute positioning. When people drive, they are the sensor stack, and they are (mostly) aware of the context of where they are and can see and hear what is going on around them. Before we can hand over the driving duties to machines, and fully accept any autonomous driving technology, it will not only need to be as smart and aware as humans, but much better and more aware than humans. Autonomy sensor stacks can tell a car what it is doing, and what other things are doing in its immediate vicinity, but without a precise map, and knowing precisely where it is in real-time, a car would be still tip-toeing around in a fog of uncertainty.
U-blox has signed an agreement with GMV to combine GNSS receiver hardware from u-blox with GMV’s safe correction service and sensor fusion and positioning engine. This solution is suitable for automotive applications because it provides a holistic safety approach that maximizes performance and minimizes timetomarket costs.
Starting in April 2023, u-blox will directly commercialize the solution. This includes integration services and certification support provided jointly by u-blox and GMV for applications such as ADAS Level 2+ and vehicle autonomy.
The collaboration was forged at the recent Mobile World Congress (MWC), Barcelona 2023. The two companies will work hand in hand to integrate their technologies and provide a solution for the needs of future automotive application
The third Innovative, Connectivity, Autonomous (ICA) Summit will take place May 15-16, 2023, in Frankfurt, Germany.
The ICA Summit 2023 will focus on the various levels of automated vehicles and how the industry is being redefined by fast-changing technology. Industry professionals will discuss how manufacturers and suppliers will integrate key connectivity requirements to achieve advanced levels of autonomous driving.
The closed-door ICA Summit will dive into innovative solutions and regulatory framework of development and validation. Attendees will have a chance to explore the latest developments in the industry and share their insights on the following topics:
• “Autonomous vehicles: Future is today”
• “Connectivity should not be an option for today’s vehicle”
• “ADAS: From ABS to level 5”
• “Software and hardware: The key to superior AI”
For more information and to register, visit the ICA Summit 2023 website.
On Jan. 3, Hexagon and Dayou announced the availability of TerraStar-X Enterprise test beds in Beijing, Shanghai, Anqing and Shenzhen for OEMs in the automotive and micro-mobility industries. Terra-Star-X Enterprise precise-point positioning corrections provide lane-level accuracy with fast convergence for autonomous vehicles and mass-market use.
The availability of the test beds follows the initial announcement by Hexagon’s Autonomy & Positioning division and Dayou of their partnership aiming to deliver GNSS correction services to the Chinese market. Users of autonomous platforms will now have a single correction service that works in China, North America and Europe.
OEMs in China can now leverage the test beds with consumer and automotive-grade GNSS receivers to design advanced driver assistance systems (ADAS), and other products, such as mobile applications, safety-critical solutions and more.
An interview with Markus Uster, head of product center positioning at u-blox about recent GNSS receiver innovations.
Uster
What was the most significant technical innovation in your GNSS receivers in the past five years?
The u-blox F9, launched in 2018, is our robust and versatile high-precision positioning technology platform. It was the first receiver to enable multi-band high-precision positioning solutions for mass-market industrial and automotive applications — and remains the benchmark for the industry today.
The platform combines multi-constellation (continuous reception of four satellite constellations) GNSS technology with dead reckoning and high-precision algorithms. It is also compatible with a variety of GNSS correction data services to achieve positioning accuracy down to the centimeter level.
The u-blox F9 platform is leading the next generation of high-precision navigation with its augmented reality, unmanned vehicles and various machine automation applications. It has since been integrated into a selection of modules catering to a wide range of applications.
What has it enabled users to do that they could not do before?
The u-blox F9 is a widely adopted multi-band GNSS platform for automotive and industrial applications. (Photo: u-blox)
In a nutshell, the u-blox F9 brought high-precision positioning to the mass market. The demand for scalable high-precision technology is growing rapidly, as evident in the automotive world with next-generation advanced driver-assistance systems (ADAS) and in robotics with applications such as UAVs and robotic lawnmowers. However, due to the complexity, size, power and cost restrictions of existing high-precision solutions, until now it has been difficult to meet the demands of these markets.
u-blox developed the u-blox F9 platform by building on the success of our NEO-M8P high-precision GNSS module series and drawing on our extensive experience in GNSS positioning technologies, including dead reckoning, multi-band, real-time kinematic (RTK) and GNSS correction services. The platform delivers the next level of scalable GNSS high-precision technology and shows how u-blox is consistently addressing challenges and driving the GNSS technology evolution.
What is a good example of this?
Integration of the u-blox F9 platform into various applications has proven quite successful in a diverse range of use cases. In the industrial realm, u-blox F9 technology enables mass adoption of commercial unmanned vehicle applications. One example is precision agriculture, where high-precision positioning cost-effectively enables vehicle guidance solutions to improve pass-to-pass accuracy resulting in improved crop yield and reduced consumption of pesticides, fertilizer and seeds. The u-blox F9 modules also paved the way for autonomous driving, including lane-level navigation for heads-up displays and vehicular infotainment systems, a prerequisite for highly automated and fully autonomous vehicles.
