Keynotes

Bio: Luis combines over two decades of experience in GNSS, ADAS, and autonomous systems with a visionary drive to redefine precision and safety in mobility. Having held senior roles at u-blox, Trimble Navigation, STMicroelectronics, BMW and Apple’s Special Projects Group (SPG), he has contributed to some of the industry’s most advanced positioning and perception programs, including at Apple’s SPG and General Motors’ SuperCruise with Trimble.

​His expertise spans GNSS, robotics, surveying, functional safety, and AI-based localization. At NeuraLoc, Luis leads the mission to make GNSS corrections and predictive integrity services the trusted foundation for autonomous, connected, and accuracy-driven technologies worldwide.

Abstract: High-precision GNSS positioning has become a foundational technology for a wide range of emerging applications, including autonomous vehicles, robotics, machine guidance, and critical infrastructure monitoring. While techniques such as Real-Time Kinematic (RTK) and network correction services have significantly improved positioning accuracy, a key challenge remains: ensuring the integrity and reliability of positioning solutions in complex and safety-critical environments.

As autonomy and precision systems move from controlled environments to real-world deployment, positioning systems must not only be accurate but also capable of detecting faults, monitoring signal quality, and providing confidence metrics in real time. Multipath effects, atmospheric disturbances, signal interference, and hardware inconsistencies can introduce subtle positioning errors that traditional correction services alone are not designed to identify or mitigate.

This keynote presents a new approach to positioning reliability through AI-powered GNSS integrity monitoring integrated with global correction services. The work introduces a cloud-based architecture that combines RTK positioning, real-time signal observables analysis, and machine-learning models trained to detect anomalies and predict degradation in positioning performance.

The system leverages a distributed network of GNSS reference stations and real-time data streams to monitor satellite signals, detect multipath patterns, and identify abnormal positioning behaviour across the network. Machine-learning techniques enable the system to extract patterns from large GNSS datasets and provide predictive indicators of positioning quality, effectively creating a safety layer on top of traditional correction services.

The presentation will discuss the development of a global correction and integrity monitoring service designed to support safety-critical applications. Early deployments demonstrate how combining RTK positioning with AI-driven integrity monitoring can significantly improve the reliability of positioning solutions for autonomous machines, robotics, deformation monitoring, and other precision systems. By closing the loop between global GNSS correction infrastructure, real-time integrity monitoring, and machine-learning-based signal intelligence, this approach represents a step toward the next generation of trusted positioning services for autonomy and precision applications.

Bio: to be added

Abstract: to be added

Bio: to be added

Abstract: to be added