JEREMY SALINGER Innovation Program Manager Electrical & Control Systems Research Lab GM Global Research & Development

JEREMY SALINGER Innovation Program Manager Electrical & Control Systems Research Lab GM Global Research & Development

ROADMAP TO AUTOMATED DRIVING Autonomous Driving (Chauffeured Driving) Increasing Capability Today s Driver Assist Package Driver Info & Alerts (No Control) SuperCruise Concept Emergency Intervention (Limited Control) Limited On-Demand Automation (Monitored Control) Complex On-Demand Automation (Transferred Control) TECHNOLOGY ENABLERS: Perception and Algorithms Integrated Sensing with Maps, GPS, V2X Driver State Knowledge Today Future

TODAY S TECHNOLOGIES Forward Collision Alert Lane Departure Warning Side Blind-Zone Alert Rear Cross-Traffic Alert Adaptive Cruise Control Auto Collision Mitigation Braking

CADILLAC TO INTRODUCE SUPER CRUISE ON ALL-NEW CT6 ACTIVE SAFETY AUTOMATED STEERING & LANE FOLLOWING CADILLAC SUPER CRUISE 1 Long-Range Radar 2 Short-Range Radars 8-10 Ultrasonic Sensors Sensor Fusion System 1 Front Camera 3 Short-Range Radars + HOW IT WORKS = 1 Rear Camera LANE FOLLOWING: Using a combination of GPS and optical cameras, Super Cruise watches the road ahead and adjusts steering to keep the car in the middle of its lane. COLLISION AVOIDANCE: A long-distance radar system detects vehicles more than 300 ft. ahead. The vehicle will automatically accelerate or apply the brakes to maintain a preset following distance.

ADAPTIVE HUMAN-MACHINE INTERFACE

OPEL INSIGNIA RESEARCH VEHICLE Outfitted with cameras, 6 Lidar sensors, long-range radar, GPS, maps, and V2X communications Vehicle sensors or V2X enable 360-degree awareness Automated urban AND highway driving First demonstration at ITS World Congress (September 2014)

ELECTRIC NETWORKED VEHICLE 2.0 Outfitted with cameras, GPS, Lidar, V2X communications, smartphone, maps, and RFID technologies Autonomous chauffeur Automated valet parking and retrieval Urban automated platooning/ traffic jam assist Intersection collision assist Pedestrian crash avoidance Demonstrated at ITS World Congress (September 2014)

VERIFICATION & VALIDATION OF AUTOMATED DRIVING SYSTEMS Many are asking how to achieve confidence automated driving systems will provide the desired value in both safety and travel convenience/utility There are many flavors of automated driving systems. Each requires extensive testing, including many aspects that are unique. Simulation, test track, and on-road testing are all used. Historically two types of guidelines have been created to help build confidence in Active Safety Products Focus on the processes used for development and testing Focus on objective tests at all levels for each feature

GOVERNMENT AND INDUSTRY COLLABORATION ISO 26262 OVERVIEW NCAP 2-5 Overall safety management 3. Concept phase 3-5 Item definition 3-6 Initiation of the safety lifecycle 3-7 Hazard analysis and risk assessment 3-8 Functional safety concept 1. Vocabulary 2. Management of functional safety 2-6 Safety management during item development 4. 4-5Product Initiation of product development: system level development at the system level 4-6 Specification of the technical safety requirements 4-7 System design 5. Product development: 5-5 Initiation of product development hardware 5-6 at the level hardware Specification level of hardware safety 5-7 requirements Hardware design 5-8 Hardware architectural metrics 5-9 Evaluation of violation of the safety goal due to 5-10 random Hardware HW failures integration and testing 4-11 Release for production 4-10 Functional safety assessment 4-9 Safety validation 4-8 Item integration and testing 6. Product development: software level 6-5 Initiation of product development at the software 6-6 level Specification of software 6-7 safety Software requirements architectural design 6-8 Software unit design and implementation 6-9 Software unit testing 6-10 Software integration and testing 6-11 Software verification 2-7 Safety management after release for production 7. Production & Operation 7-5 Production 7-6 Operation, service and decommissioning Core processes 8-5 Interfaces within distributed developments 8-6 Overall management of safety requirements 8-7 Configuration management 8-8 Change management 8-9 Verification 8. Supporting processes 9. ASIL-oriented and safety-oriented analyses 9-5 Requirements decomposition with respect to ASIL tailoring 9-6 Criteria for coexistence of 8-10 Documentation 8-11 Qualification of software tools 8-12 Qualification of software components 8-13 Qualification of hardware components 8-14 Proven in use argument 9-7 Analysis of dependent failures 9-8 Safety analyses 10. (Informative) Guidelines on ISO 26262 Source ISO/FDIS 26262

V&V CHALLENGES THAT ARE PRE- COMPETITIVE Creating or understanding social norms for automated vehicles Common expectations for behavior of automated vehicles Consistent terminology for performance metrics and test conditions Roadway and environmental conditions Ego-vehicle maneuvers Characteristics and behaviors of others Performance testing facilities for Behavior Sensor Interference Security Shared-data quality assurance

IWPC WORKGROUP ON PERFORMANCE METRICS FOR AUTOMOTIVE RADARS Goals Define a common set of performance metrics for automotive radar performance Agree on terminology and common language for automotive radar scenarios and performance criteria Define a common base line set of performance metrics Create guidelines for measuring metrics Success Criteria: Required test equipment readily available Required test facilities commonly available or accessible Test procedures repeatable enough to meet the intent Terminology applicable to radar, lidar, and vision systems Usable to predict the performance of the sensors in complex road and traffic environments.