Waymo has years of experience operating a fully autonomous fleet across multiple cities in the United States. The promises of safety, accessibility, and sustainability of Automated Driving Systems go hand in hand with both the technological feasibility and public acceptance. In this talk, Dr. Favaro will present an overview of the criteria that ground deployment decisions for the Waymo Driver. The presentation will also feature a discussion on the careful decision-making governance framework in place at Waymo to responsibly evaluate autonomous driving configurations. An example criterion will anchor a brief deeper dive to showcase the application of the presented concepts.

The Cooperative Driving Automation Phase II project implemented a hierarchical controller integrating a cloud-based Speed Planner with onboard driving automation controllers. Conducted as a field test on I-680N traffic in California, a fleet of Connected and Automated Vehicles applied real-time speed advisories to preempt shockwaves and reduce stop-and-go behavior. Key performance metrics—including hard-braking events, time-to-collision (TTC) occurrences, acceleration variability, and stoppage time—demonstrated significant improvements: up to an 85% reduction in intense braking, elimination of sub-2-second TTC events, 20% smoother driving speed fluctuation, and a 70% drop in near-stop time. Results validate this approach’s feasibility and safety benefits for real-traffic smoothing.

What the audience will learn

• Understanding the hierarchical CCM system combining cloud Speed Planner with local vehicle controllers
• Recognizing measured safety gains: up to 85% reduction in hard-braking events
• Appreciating key performance metrics: Time-to-Collision, acceleration distribution, and stoppage time
• Learning implications for scaling CCM: macroscopic impact and recommendations for broader deployment

The presentation will provide an overview of California's framework for regulating automated driving systems (SAE Level 3-4).

What the audience will learn

• California's regulatory framework for autonomous vehicles
• Permitting – testing with a safety driver/driverless testing/commercial deployment of AVs
• Federal government's role versus state's role in regulating AVs
• Post-permitting controls on traffic safety

The presentation will show how dangerous a poisoning attack can be on a fictitious ADAS system. It will work through a systematic approach to train engineers in detecting and preventing the attack. It will also offer an overview of ISO TR 5469 and discuss other potential functional safety hazards in an AI/ML system.

What the audience will learn

• Introduction of the 3-stage AI/ML development stages
• Introduce the AI classification scheme from ISO TR 5469
• Explain the six desirable AI properties leading to methods & techniques and acceptance criteria
• A brief look at all the six properties including transparency and explainability and resilience to adversarial inputs

The methods to develop and test ADAS and automated driving systems are continuously evolving. Principles like ODD and scenario coverage need languages that describe the respective artifacts. A variety of test environments needs to be blended with the best-fit test methods. And results of virtual testing will only be accepted if the underlying tools and methods provide sufficient quality and credibility. ASAM is addressing these topics with the release of new standards and by upgrading existing standards. This presentation shall give an overview of what has been achieved so far and what the near future will bring under the roof of ASAM.

This presentation introduces the concept of blocked force in NVH testing, a key metric representing the vibratory force a LiDAR sensor exerts on an infinitely rigid mount. It serves as a standardized indicator of structure borne vibration emissions, with higher values signaling greater potential to induce noise and interfere with surrounding components. The talk outlines relevant measurement standards that suppliers may be required to follow prior to sourcing, enabling more informed decisions in sensor integration for automotive applications.

What the audience will learn

• Understand the concept of blocked force and its importance in quantifying structure-borne vibration from LiDAR sensors in NVH analysis.
• Learn how high blocked force values can impact sensor integration, potentially affecting noise levels and surrounding component performance.
• Gain insights into standardized measurement techniques and supplier requirements to evaluate blocked force before sourcing LiDAR systems.

For almost a decade, states and the federal government have struggled to craft a regulatory framework tailored to AVs. But what if instead of crafting an AV-specific framework, we return to true tech neutrality and recognize that regulation works best when broad-based rules apply to many use cases, including emerging technologies? Under this approach, we would unleash the power of existing rules – both vehicle standards and operational standards – instead of crafting AV-specific rules. There are many benefits in this approach. Speed: These rules already exist, and simply need to be generalized for AV contexts. Right at this moment, 16-year-olds around the country are studying the rules of the road to execute safe vehicle operations. AVs can be held to the same basic principles with minimum adoption friction. Futureproofing: We aren’t committing all our regulatory energies to a pathway that can become stale with new tech developments. Corruption-proof: Consumers will only adopt AV tech if they trust the underlying safety standards. Now more than ever, it is critical for regulators to adopt standards that do not appear to tilt toward developers who have privileged governmental access. Tech-neutral standards best accomplish this objective by avoiding the appearance of favoritism.

What the audience will learn

• We do not have to wait for a perfect metric or flawless industry standard to regulate AVs. Existing laws provide a potent foundation for rulemaking, today
• Regulating today based on tech-neutral standards will help promote consumer confidence and adoption, and inherently provide clarity in the comparisons between AVs and other forms of transportation
• We are starting down the same dangerous road with AI regulation: attempting to craft AI bespoke rules, with the risk of differential treatment for the same types of harm, based entirely (and arbitrarily) on the type of tech that is the source of harm

This session explores the evolving legal landscape for connected vehicle data, addressing privacy risks (e.g., biometrics, geolocation), cybersecurity threats, and compliance strategies under state/federal laws. Attendees will gain actionable insights into balancing innovation with regulatory demands, mitigating enforcement risks, and implementing industry privacy principles. Case studies include recent FTC actions and state AG investigations. Designed for engineers, business leaders, and legal teams, this talk bridges technical data practices with legal obligations, offering tools to build consumer trust while navigating complex data flows in connected mobility systems.

What the audience will learn

• Emerging federal/state privacy laws governing vehicle data
• How biometrics/geolocation data trigger heightened compliance obligations
• Enforcement trends: FTC, CPPA, and state AG priorities
• Practical application of auto industry privacy principles in product design
• Cybersecurity best practices for vehicle-to-infrastructure systems

The proliferation of diverse software systems within modern vehicles introduces critical interoperability problems from incompatible protocols, standards and data formats, resulting in costly development delays. System interoperability requires accurate, instant data exchange between software components. Ineffective system communication results in suboptimal performance, or worse, safety-critical failures. Deploying a data-centric communication model via DDS facilitates interoperability within vehicle architectures. The Data Distribution Service (DDS) standard enables data interoperability by decoupling the data from the applications, providing flexibility, portability and scalability. This session will discuss data centricity and a data-oriented communication architecture that enables software components to be developed independently, updated incrementally.

What the audience will learn

• Interoperability challenges in modern vehicle architecture
• Fundamentals of a Data-centric architecture
• Introduction to the DDS standard
• Technical architecture based on DDS that enables data interoperability

The use of AI/ML is rapidly expanding across safety-critical sectors, including automotive. However, its non-deterministic nature challenges traditional functional safety frameworks like ISO 26262 and IEC 61508, which rely on traceability and predictable behavior. Emerging standards—such as ISO/IEC TR 29119-11, ISO/IEC DTS 25058, ISO PAS 8800, and ISO DTS 5083—aim to address these gaps. Until then, ensuring the reliability, safety, and security of AI-driven systems remains a complex task. This talk explores how the industry can balance the need for innovation with the demands of safety assurance in AI/ML-based automotive applications.

What the audience will learn

• Understand the challenges AI/ML introduces to ISO 26262 and functional safety frameworks in automotive systems
• Learn about emerging AI/ML safety standards like ISO/IEC TR 29119-11, ISO PAS 8800, and ISO DTS 5083
• Explore the conflict between AI’s non-determinism and the need for traceability and predictability in safety-critical systems
• Gain insights into strategies for assuring safety, reliability, and security in AI-driven automotive applications
• Discover how AI/ML can enhance safety beyond traditional development methods while maintaining compliance expectations

The presentation will address the test challenges of multi-drop 10BASE-T1S network implementation and securing the network with MACsec(802.1AE) in an SDV. It will include Physical Layer Collision Avoidance (PLCA), Time Synchronization over Half Duplex (802.1ASds), MACsec over 10BASE-T1S and use of TSN to ensure the required Quality of Service.

What the audience will learn

• Test multi-drop 10BASE-T1S network
• Validate networks with MACsec(802.1AE)
• Timing challages in 10BASE-T1S networks
• MACsec(802.1AE) conformance testing

Bridging the gap between research and current development in ADAS involves translating cutting-edge research findings into practical, scalable solutions. This process requires close collaboration between academia, industry and regulatory bodies to ensure that emerging technologies are effectively integrated into real-world applications. By fostering collaboration, sharing knowledge and investing in robust testing and validation processes, we can accelerate the adoption of advanced ADAS features, enhancing safety and efficiency on the road.

What the audience will learn

• The current development status
• Where research and development need to work together more closely
• What the future of development and research could look like

We have a once in a generation opportunity to incorporate GenAI capabilities into ADAS workloads and achieve outsized productivity gains, increased innovation across product development teams, and decrease time-to-release new ADAS capabilities. During this discussion, we will share industry trends and common GenAI use cases we see across OEMs, Tier1s and Start-ups. We will walk through specific ADAS development strategies using GenAI that have yielded success through clearly quantifiable metrics.

What the audience will learn

• Using GenAI with a modern data strategy and removing data silos
• Identifying the right GenAI use cases for ADAS development
• ADAS development approaches and ways to incorporate GenAI tools
• Success metrics

As vehicles and critical systems become increasingly software driven, ensuring uncompromising safety is paramount. This presentation explores the evolving landscape of advanced safety technologies. It highlights the critical role of robust software architectures, rigorous testing methodologies and real-time validation in building trust and reliability for ADAS systems. Discover how OEMs and suppliers are shaping the future of automotive safety through innovative solutions that prioritize human-centric design and resilient systems.

This presentation explores the transformative role of artificial intelligence (AI) in advanced driver assistance systems (ADAS) and automated driving (AD) applications. It delves into the integration of AI models, highlighting the shift from traditional, stack-oriented architectures to end-to-end (E2E) networks. The presentation discusses the benefits of using E2E networks with generative AI, including enhanced system integration, simplified maintenance and scalability. It also examines the potential of AI in sensor fusion, route planning and driver assistance, emphasizing the importance of modern architectures in improving vehicle safety and driver satisfaction.

What the audience will learn

• The transformative impact of artificial intelligence (AI) on advanced driver assistance systems (ADAS) and automated driving (AD) applications
• The transition from traditional, stack-oriented architectures to end-to-end (E2E) networks in AI integration
• The role of AI in sensor fusion, route planning and driver assistance
• The importance of modern architectures in improving vehicle safety and driver satisfaction
• The benefits of using E2E networks with generative AI, such as enhanced system integration, simplified maintenance and scalability

As the automotive industry transitions toward increasingly autonomous capabilities, machine learning (ML) is becoming foundational in enabling perception, decision-making and control functions across ADAS and automated driving (AD) systems. However, the inherent uncertainty and non-determinism of ML models present unique safety challenges, particularly in environments where traditional rule-based validation is insufficient. To address this, the concept of trained supervision is emerging as a critical layer in the development and deployment of safe ML-powered systems.

What the audience will learn

• Safe ML definition
• Embedded systems and SDV
• Trained supervision

From ChatGPT to generative world model for autonomous driving (AD), data for AI model training must be high performance, flexible and scalable. Data helps AI models identify and extract meaningful features from input data. Quality and depth of training data significantly affect the success of AI models. Training data provides examples and relevant information for AI models to learn from. The audience will learn about AI-powered computing for AV development; data-driven development; and how to accelerate AV development.

What the audience will learn

• Data for AI model training must be high performance, flexible and scalable
• Quality and depth of training data significantly affect the success of AI models
• Data helps AI models identify and extract meaningful features from input data

Autonomous Vehicle (AV) ML systems demand infrastructure that can handle real-time perception, high-throughput data, and latency-critical workloads. While model optimization gets much attention, infrastructure bottlenecks often define system performance. This talk shares lessons from scaling AV ML pipelines using Kubernetes-native tools. We’ll cover orchestration with Dagster, distributed execution via Ray, and dynamic GPU scaling with Kueue and KubeRay. From cloud-based fleet learning to edge-deployed perception, we’ll explore how to balance performance, cost, and developer velocity. If you’re building or maintaining AV ML systems, this session offers practical strategies to move fast, without compromising safety or scalability.

What the audience will learn

• Infrastructure-first strategies for scaling ML systems in autonomous vehicles—beyond just model compression.
• How to design resilient, cost-efficient ML pipelines using Kubernetes-native tools like Dagster, Ray, Kueue, and KubeRay
• Techniques to handle bursty inference, real-time perception, and multi-stage workloads in both edge and cloud deployments
• How to optimize GPU utilization without over-provisioning, through dynamic orchestration and auto-scaling
• Lessons from real-world AV systems that balance performance, developer velocity, and system reliability

This technical session offers a deep dive into the deployment and optimization of AI models powering autonomous driving systems. It walks through some industry-standard workflows, from model development to real-time deployment in embedded automotive platforms. The presentation will cover critical topics such as inference acceleration, quantization, pruning, and runtime optimization on Autonomous Driving hardware. Attendees will gain insights through practical examples, toolchains, and performance benchmarks, highlighting best practices and common pitfalls in deploying AI on autonomous vehicles.

What the audience will learn

• Model Deployment
• Model Optimization
• Inference Acceleration

2025 marks a turning point for autonomous trucking, moving from years of R&D into real-world commercial deployment. This talk introduces Plus’s three-layer architecture powering this shift – Vision language models (VLMs), End-to-End models and Safety Guardrails. We’ll share how VLMs help with meta decisions and handle “long tail” problems, End-to-End models enable scalable deployment across diverse regions and vehicle platforms, and Safety Guardrails provide sanity checks to prevent radical maneuvers – together forming a robust, scalable, and interpretable foundation for safe and generalizable autonomous driving.

What the audience will learn

• Incorporating driving-specific VLMs to decode complex human interactions and signals or interpret variable messages on electronic signs
• Using highly optimized end-to-end models that take sensor inputs and provide the planned vehicle trajectory
• Ensuring safe driving through Safety Guardrails which are algorithmic constraints acting as a watchdog over model-based driving

As autonomous systems become increasingly complex, the industry must validate their behaviors with determinism while scaling software development across large teams. This presentation explores two complementary solutions to these challenges: Apex.OS for V&V enables deterministic, high-fidelity recording and fixed-order replay of real-world and simulated data across distributed ECUs. It supports synchronized, reproducible testing integrated with simulators and diagnostics tools—making it ideal for scalable, standards-compliant validation of L2–L5 autonomous systems. Apex.Alan is a scalable software infrastructure solution that unifies fragmented toolchains and automates end-to-end development workflows. It brings structure to variant management, CI/CD, and testing, while embedding traceability, compliance, and quality controls directly into the development process—empowering large teams to move fast without compromising safety or rigor.

What the audience will learn

• How deterministic data replay and fixed-order execution enable reproducible validation of complex autonomous behaviors across simulation and real-world scenarios.
• How integrated, infrastructure-aware development environments improve traceability, variant management, and developer efficiency at scale.
• How combining runtime observability with automated CI/CD pipelines creates a continuous, verifiable workflow from algorithm development to deployment in safety-critical systems.

Advanced driver assistance systems (ADAS) present a uniquely challenging development environment: an open-world infinite problem space, combined with a need to be repeatable to demonstrate safety and security. Current development approaches are inherently limited; handling rare events is critical, yet such events cannot be reproduced on demand in test systems. This presentation introduces the concept of deterministic ADAS development using a middleware that supports full validation and verification using recomputability. We will demonstrate how such middleware supports development through 'forensic recompute' and validation via 'credible recompute'. Additionally, we will illustrate how deterministic application performance can be enhanced using hardware accelerators.

What the audience will learn

• Why an open-world problem domain, such as ADAS, demands a non-traditional development approach
• How a reproducible system underpinned by deterministic middleware is the key to cracking ADAS verification and validation
• How 'forensic recompute' can assist in the debugging of a deterministic ADAS by guaranteeing reproducible behavior in the car and in the lab
• How 'credible recompute' enables validation of today’s ADAS and future systems using the same recorded data
• The performance implications of deterministic systems and some of the challenges when we try to interface with the non-deterministic world

More than an automated vehicle proving ground, GoMentum Station (GMS) is the nexus of an automated vehicle safety ecosystem. Just 60 miles from San Jose, this 2,100-acre site offers multiple dynamic environments for real-world connected and automated vehicle testing in a safe and closed-course setting. The Authority’s license of GMS gives it a unique ability to bridge public transportation needs with private sector innovation. The Innovation Program is a roadmap for investment in advanced technologies to address transportation demand and congestion management. Projects such as Shared Autonomous Vehicles and Smart Signals get funded and vetted before deployment on public roads.

What the audience will learn

• GoMentum Station Testing Capabilities: 2,100 acres available for testing19 miles of roadway10 distinct zones32 intersections
• CV V2X lab features: • Dedicated to research, training, & testing for traffic engineers• ATC traffic signal controllers, video detection, DSRC/5G...
• Test to Deployment of Emerging Technologies: Smart SignalsCloud-based Transit signal priorityTransit on Bus ShoulderAutomated driving systems
• Workforce Development:Innovation Alliance - collab among public, private, academic, state and regional. New mobility training, upskill & reskill.
• CCTA Innovation Program Digital Road managerInnovate 680Shared Autonomous VehiclesCloud-based Transit Signal PriorityTransit Bus on Shoulder

This presentation examines the critical role of traffic rule compliance assessment in the approval and authorization of automated driving. By leveraging roadside infrastructure in real-world testbeds, the approach enables the capture of key data to compare the driving behavior of operators under assessment with other road users in the same location and time. The discussion includes practical examples of compliance assessment and reporting, offering insights into how these evaluations inform regulatory decisions and enhance public trust in AV technology. This assessment aims to validate driving competency and ensure alignment with safety and traffic regulations.

LiDAR remains underutilized in ADAS, but China is changing that—with 150+ production models already equipped. Driven by regulation, consumer trust, and smart integration, LiDAR is scaling faster in China than anywhere else. In this session, Peipei Zhao, President of North America at RoboSense, shares deployment lessons from China and how they can inform global ADAS strategies. Drawing on programs like the first US OEM initial LiDAR deployment, he explores how LiDAR adoption can grow across markets. Rather than focusing on specs, this talk reframes LiDAR’s role through deployment, perception, and system design—offering a strategic blueprint from China for the world.

What the audience will learn

• Why LiDAR is scaling faster in China than anywhere else—and what global OEMs can learn from its regulatory, consumer, and integration models.
• How public visibility and branding influence LiDAR’s perceived value beyond its technical specs.
• What real deployment reveals: pricing myths, feature positioning, and system design lessons that drive adoption or stall it.
• Key insights from U.S. OEMs and other cross-market programs bridging East-West ADAS strategies.
• How China’s LiDAR deployment offers a practical blueprint for the rest of the world navigating autonomy and sensor fusion.

Since launching its first commercial autonomous mobility service in 2021, Sonnet.AI has expanded operations across diverse cities in Korea, gaining practical insights from deployments in tourism, commuting, and everyday transport. These real-world lessons have shaped our vision for a next-generation Roboshuttle—designed from the ground up with a software-defined architecture, operational service integration, and a user-focused design. Crucially, the shuttle is engineered for cost-effective manufacturing, ensuring scalability and commercial viability. This session explores how field-proven experience is driving innovation across software, service strategy, and shuttle design to enable a practical, inclusive, and sustainable future for autonomous mobility.

What the audience will learn

• Key lessons from deploying autonomous mobility services in diverse real-world environments
• How operational insights shaped the Roboshuttle’s software architecture and service design
• Strategies for cost-effective shuttle development from the ground up
• The importance of integrating service operations into autonomous vehicle design
• A scalable, inclusive vision for the future of autonomous urban and regional mobility

As ADAS-equipped vehicles begin to incorporate higher levels of automation, having a robust understanding of the sensors that enable these more advanced features is critical to understanding the way in which features can be expected to perform under diverse environmental and situational conditions. There is still a large gap in the technologies on the roads today between the level 2 systems that have emerged and are becoming more commonplace and the level 4, near level 5, AV vehicles driving around our various cities. Michelle will discuss evolving sensor technologies, and how testing at the edge of edge cases can uncover their functional capabilities and limitations.

OpenX standards, including OpenSCENARIO, OpenDRIVE, and OSI, enhance automated vehicle validation by fostering collaboration and openness. These standards allow efficient test coverage, seamless scenario exchange, and integration of third-party sensor models. Support of OpenX enables real-time HIL-simulation, scalable SIL testing, physics-based sensor simulation, and complex road network simulation. This presentation will discuss the benefits of OpenX and share insights on implementing native support, including addressing challenges encountered.

What the audience will learn

• Benefits of OpenX Standards - how OpenX support enhances test coverage, scenario exchange, and sensor integration.
• Implementation Insights - challenges encountered during the integration of OpenX standards and the strategies employed to overcome them
• Workflow Demonstration – showcase for the exchange of OpenX artifacts between best-in-class scenario simulation tools

2025 has the potential of being a pivotal year for Automated Vehicles (AV) ecosystem, with various large-scale deployments in the Americas and Europe & Asia moving to the later stages of regulation, including the secondary legislation of the UK’s Automated Vehicles Act. However, one of the key challenges associated with understanding safety of AV is in establishing the safety threshold or benchmark. Various approaches have been suggested, such has Careful & Competent Human Driver or comparison to historic accidents; however, a well understood and accepted objective definition of safety for AV still evades of the industry. In this talk, we present an objective leading indicator-based approach to defining safety for AV and stopping criteria for their testing.

Participants will learn how to specify the ODD in a machine readable and human interpretable fashion. Together, we will learn how to analyse the real-world conditions and how to exclude unsuitable ones. We will modularise the specification to enable assembling a single joint specification from components provided by numerous teams and experts. We will understand which use-cases and data are required to support ODD evaluation, including discussion of the various technologies and data sources involved. Finally, we will understand how to utilize these definitions in simulation toolchains to determine the impact of specific capabilities.

Imagine a machine which ingests ADS real-world driving logs and simulation results and emits a safety evaluation with good traceability to the source data. Further imagine that this machine is automated and forms a part of the CI/CD and safety validation flows. Why would we want such a machine? What would it look like? Which enabling technologies would be needed? How would different stakeholders (e.g. AV developers, fleet operators, insurance firms, govt. authorities) extract value from it? I will answer these questions in my talk and present a blueprint for ADS safety evaluation that can be utilized by AV developers as well as various third parties.

What the audience will learn

• What is an automated and data-driven approach to safety and how is it different from existing approaches?
• What does a blueprint of a data-driven safety framework look like? What enabling technologies are needed?
• How can different stakeholders like AV developers, fleet operators, insurance firms, government agencies etc. derive value from a data-driven safety evaluation
• How should a data-driven safety evaluation framework be deployed?

The AV landscape is rapidly evolving, presenting new complexities that demand robust, safe, and secure software systems. We’ll explore the field of autonomous systems with a focus on application safety and security for all levels of autonomous algorithms with various types of sensors. How to extend AV system lifecycle through the creation of interconnected systems of systems. Including the critical aspects of data flow management, cloud data aggregation and the establishment of a comprehensive distributed secure system life cycle. These elements are essential for developing safe and secure AV environments that can adapt to the increasing demands of future AVs.

What the audience will learn

• How unsafe and unsecure vehicles hurt the industry and what to do about it.
• How to secure the software lifecycle both to and from the vehicle including upgrades via the cloud and V2X applications.
• Security is a moving target, with increasing complexities that require systems to adapt to the evolving threat landscape.
• Fault tolerance is necessary in keeping the autonomous systems performing without lengthy downtimes and reboots.

Autonomous driving demands rigorous, evidence-based safety assurance, especially as programs advance from R&D into real-world deployment. An autonomous vehicle safety case is a set of arguments, claims and evidences that proves the AV system is devoid of unreasonable risks across its lifecycle. At Plus, we’ve developed a metrics framework to define, track, and manage key performance indicators at both system and sub-system levels. This framework enables us to generate objective and auditable evidence to support core safety claims, strengthening confidence in our Level 4 system’s safety and readiness for scalable deployment.

What the audience will learn

• A safety case needs to have objective performance metrics that act as the evidence to prove the validity of the claims and arguments
• A well-defined metrics framework is necessary for enabling the organization to define, develop and track performance metrics at various levels
• Learning about Plus’s extensive metrics framework that enables the measurement of performance across the AV ecosystem

As autonomous vehicles move from pilots to real-world deployment, the missing link remains: high-definition, real-time location intelligence that adapts dynamically to complex environments. Drawing on HERE’s global expertise, this talk will showcase how HERE’s dynamic Location Platform integrates sensor fusion, real-time updates, and AI-powered mapping to enable safe, scalable autonomous navigation. We’ll explore how OEMs and AV developers are using HERE’s advanced mapping solutions to bridge critical gaps in perception, planning, and execution. Attendees will gain practical insights into how real-time geospatial data can de-risk AV operations, improve route planning, and accelerate the rollout of Level 4/5 autonomous systems worldwide.

What the audience will learn

• How real-time, high-definition mapping enhances AV perception, planning, and decision-making
• How HERE’s Dynamic Location Platform fuses sensor data, AI, and real-time updates to deliver an always-accurate understanding of complex road environm
• Proven strategies used by global OEMs and AV developers to integrate dynamic location intelligence
• Proven strategies used by global OEMs and AV developers to integrate dynamic location intelligence