Ahead of AutoSens USA 2025, we spoke with Sneha Shetiya, Staff Software Engineer at Torc, to gain insights into the limitations of current Onboard Diagnostics (OBD) systems in meeting the evolving needs of autonomous vehicles, and discover why a proactive approach to vehicle maintenance is essential for ensuring the safety and reliability of these complex systems.
Plus, don’t miss out on attending Sneha’s session this June. Find out more, and read the article below ⬇
The Next Generation of Vehicle Diagnostics: Predictive Maintenance for Autonomous Vehicles
Wednesday 11th June | 3:20pm EDT | Room 140A-B
This presentation will explore the shortcomings of current On-Board Diagnostics (OBD) systems in meeting the evolving needs of autonomous vehicles. It will advocate for a proactive vehicle maintenance strategy as crucial for ensuring the safety and reliability of these complex systems. Furthermore, the presentation will emphasize the necessity of collaboration among vehicle manufacturers, suppliers, and regulators to develop and implement effective predictive maintenance strategies for sustainable solutions.
The current OBD approach is focused on reporting existing symptoms or faults, rather than predicting potential failures of components. This highlights the growing importance of predictive maintenance—an area that faces several challenges, particularly in obtaining high-quality data through Onboard Monitoring (OBM). Key challenges include developing standards to define anomalies, developing the algorithms, data privacy, as well as the risks of tampering and cybersecurity, for which several potential solutions will be discussed. It will also examine the vital role including advanced sensing technology, AI, and ML for predictive analytics and attack detection. It will also explore the vital role of collaboration between vehicle manufacturers, suppliers, and regulators to develop and implement effective predictive maintenance strategies that will also be necessary for sustainable solutions.
OBD Systems
OBD systems are currently designed to monitor and report faults in vehicles by identifying issues in various subsystems, such as the engine, transmission, or emissions control. These systems rely on predefined fault codes (Diagnostic Trouble Codes, or DTCs) that are triggered when a sensor detects an abnormality or deviation from expected operational parameters. The primary focus of OBD systems is reactive maintenance: alerting the driver or technician about existing problems that need repair.
For example, if an engine misfire occurs, the OBD system will detect it via sensors and generate a fault code that can be read using diagnostic tools. However, these systems are limited to reporting faults after they occur rather than predicting potential issues.
Modifications Necessary for Autonomous Systems
Autonomous vehicles introduce new challenges that traditional OBD systems are not equipped to handle. These vehicles rely on complex networks of sensors, actuators, and control algorithms that require more advanced diagnostic capabilities. Key modifications needed include:
- Predictive Maintenance Capabilities: OBD systems must evolve to predict potential failures before they occur by analyzing data trends. This requires integrating predictive analytics powered by AI/ML to identify early signs of wear or malfunction.
- Real-Time Monitoring: Autonomous vehicles operate in dynamic environments where real-time data collection and analysis are crucial. Modified OBD systems should continuously monitor the performance of critical components like LiDAR, radar, cameras, and neural network processors.
- Sensor Health Diagnostics: Autonomous systems depend heavily on sensor accuracy. The modified OBD system must detect sensor degradation (e.g., dirt on a camera lens or misaligned radar) and alert the system before it impacts vehicle performance.
- Cybersecurity Monitoring: With increased connectivity in AVs, OBD systems must also monitor for cybersecurity threats, such as unauthorized access or tampering with vehicle controls.
- Integration with Vehicle Networks: Autonomous vehicles utilize advanced communication protocols (e.g., CAN bus, Ethernet) for data exchange between components. The modified OBD system must integrate seamlessly into these networks to access and analyze data effectively.
Challenges
Several challenges must be addressed to enable effective predictive maintenance for autonomous vehicles, such as developing algorithms, data privacy, and risks of tampering and cybersecurity. Further challenges around the monitoring of vehicle sensors include:
Enhanced Sensor Networks
Autonomous vehicles require a more comprehensive sensor array, including LiDAR, radar, cameras, and high-precision GPS, in addition to traditional vehicle sensors.
A network of IoT sensors throughout the vehicle continuously monitors critical performance parameters, providing real-time data on various components.
Data Processing and Analysis
Onboard computers with enhanced processing power to handle real-time diagnostics and decision-making without constant internet connectivity.
AI-Powered Predictive systems
Advanced ML models analyze sensor data to identify patterns and anomalies indicating potential failures.
Communication and Updates
Cloud computing platforms to store and process vast amounts of diagnostic data from multiple vehicles.
Safety and Reliability Enhancements
- Digital Twin technology: Virtual representations of vehicle components for real-time simulations and optimization.
- Continuous monitoring: AI systems that constantly analyze vehicle health data, comparing it to predictive models for immediate anomaly detection.
- Failure prediction models: AI algorithms that forecast when specific components might fail based on current conditions and historical data.
- Over-the-Air (OTA) update capability: Systems that allow for remote software updates and delivery of new features or security patches.
- Real-time alert systems: Mechanisms to notify drivers or fleet managers about potential issues and necessary maintenance actions.
- Redundant systems: Critical components with backup systems to ensure safety in case of failures.
- Self-diagnostic capabilities: AI-powered systems that can perform regular self-checks and identify potential issues before they become critical.
Solutions
AI/ML for Predictive Analysis
Artificial intelligence and machine learning are integral to predictive maintenance solutions for autonomous vehicles. These technologies analyze vast amounts of sensor and operational data to identify patterns and predict potential failures before they occur. By leveraging advanced algorithms, AI/ML models can:
Detect Anomalies:
Identify deviations from normal operational behavior that may indicate impending component failures.
Forecast Failures:
Use historical data to predict when specific vehicle components are likely to fail, enabling proactive maintenance.
Optimize Maintenance Schedules:
Reduce unnecessary repairs by accurately predicting when maintenance is actually needed, minimizing downtime and costs.
Adapt to New Data:
Continuously learn and improve predictions as new data from vehicles becomes available, ensuring relevance in dynamic environments.
For example, AI/ML models can analyze real-time telemetry data from autonomous vehicles to predict failures in critical systems like braking or steering, ensuring safety and reliability.
Attack Detection
In the context of autonomous vehicles, attack detection focuses on identifying cybersecurity threats that could compromise vehicle safety or operations. Autonomous systems rely heavily on interconnected sensors, communication networks, and software, making them vulnerable to cyberattacks. Key aspects of attack detection include:
Intrusion Detection Systems (IDS):
Monitor network traffic within the vehicle to identify unauthorized access or suspicious activity
Behavioral Analysis:
Use AI/ML models to detect deviations from expected system behavior that could indicate a cyberattack.
Real-Time Threat Identification:
Quickly identify and respond to threats such as spoofing (false sensor data), tampering with control signals, or denial-of-service (DoS) attacks targeting vehicle systems. Implement attack detection systems that not only identify threats but also isolate compromised components to maintain safe operation. For instance, AI-driven attack detection systems can monitor vehicle communication channels to detect anomalies in messages exchanged between sensors and control units, preventing malicious interference.
Advanced Sensing Technology
Advanced sensing technologies play a crucial role in both predictive analysis and attack detection by providing high-quality data for analysis. These include:
Enhanced Sensors:
Improved LiDAR, radar, cameras, and other sensors capable of capturing detailed environmental and operational data.
Sensor Fusion:
Combining data from multiple sensors to create a comprehensive view of the vehicle’s environment and internal state.
Edge Computing:
Processing sensor data locally within the vehicle for real-time analysis and decision-making without relying on external servers.
Self-Monitoring Sensors:
Sensors equipped with self-diagnostic capabilities detect their own degradation or malfunction. By integrating advanced sensing technologies with AI/ML models, autonomous vehicles can achieve higher levels of safety, reliability, and resilience against failures or attacks.
Collaboration for Sustainable Solutions
To implement these solutions effectively, collaboration between vehicle manufacturers, suppliers, and regulators is essential. This includes developing industry standards for anomaly detection and predictive maintenance, sharing best practices and data across organizations while addressing privacy concerns, establishing regulatory frameworks to ensure compliance with safety and cybersecurity requirements and combining advanced technologies with collaborative efforts, predictive maintenance strategies can enhance the safety and reliability of autonomous vehicles while addressing challenges like cybersecurity risks and data privacy concerns.
Some notable industry examples:
BMW's AI-supported Predictive Maintenance
BMW has implemented an AI-supported system at its Regensburg plant to monitor assembly line conveyor equipment. The system uses data from load carriers to detect irregularities in power consumption, conveyor movements, and barcode readability, allowing for early intervention and prevention of malfunctions.
Ford's Data-Sharing Initiative
Ford has partnered with CARUSO and HIGH MOBILITY to provide third-party businesses access to vehicle-generated data, with drivers’ consent. This collaboration enables the development of innovative products and services, including predictive maintenance solutions and usage-based insurance.
Intuceo's Predictive Maintenance for OEMs and Dealers
Intuceo has developed a solution that leverages in-vehicle sensor data and machine learning algorithms to provide predictive maintenance insights for OEMs and dealers. This collaboration helps reduce downtime and costs in the automotive manufacturing industry.
Conclusion
As autonomous vehicles become more prevalent, the need to move beyond traditional, reactive OBD systems is critical. The current OBD frameworks, while effective for conventional vehicles, are not equipped to support the complex sensor networks, AI-driven systems, and cybersecurity demands of autonomous technologies. To ensure safety, reliability, and efficiency, a shift toward predictive maintenance is essential—one that incorporates advanced sensing technologies, AI/ML-powered analytics, and robust attack detection mechanisms.
However, this evolution presents substantial challenges, including standardization of diagnostic protocols, secure and private data handling, algorithm development, and the integration of real-time monitoring systems. These cannot be solved in isolation. Successful implementation will depend on coordinated efforts across the automotive ecosystem—from manufacturers and suppliers to regulatory bodies.
By embracing predictive diagnostics and fostering collaborative innovation, industry can build smarter, safer, and more resilient autonomous vehicles. Ultimately, this transformation is not just about maintaining machines—it’s about building trust in the systems that will define the future of transportation.
Interested in in-cabin monitoring technology?
With a pass to AutoSens USA, you’ll also get full access to our co-located sister event, InCabin. Explore InCabin here >>
