Interview with Mobileye on Next Generation AEB

Mobileye Subject Matter Expert: Shimon Solodkin, Director of Product for AEB & Lighting Applications 

1. DVN: Can current RCCB cameras meet the specs for the NHTSA FMVSS 127 AEB regulation? Is SWIR an option – and will quantum dot allow them to reach a reasonable cost? Can a single (Forward) camera be used for level 2 and meet nighttime AEB specs or do we need a separate solution for this.  
   
   Mobileye’s current generation of camera-based systems demonstrate strong performance in nighttime AEB scenarios, including with only a single front-facing camera. For FMVSS 127, achieving compliance largely depends on the overall system design, including headlamp optimization on the OEM side. Our current assumption is that a single camera shows very good performance against FMVSS performance metrics. Mobileye’s camera-based solution leverages advanced image processing and AI algorithms to achieve high accuracy for pedestrian and vehicle detection, even in challenging low-light conditions, without requiring additional sensors. Additional sensors beyond cameras would add cost and complexity barriers that could limit widespread adoption.  
    
2. DVN: Are LWIR Thermal cameras a better solution and why/why not ?  Can they achieve the costs required ?  
   
   Mobileye believes that optimizing the capabilities of forward-facing cameras combined with robust AI processing offers a more cost-effective and scalable solution for meeting regulatory requirements. 

3. DVN: Is HD Radar an alternative option for this application, and what are the pros and cons versus LWIR ?
   
   Radar’s resolution for detecting smaller objects or differentiating pedestrians from other obstacles is less precise than camera-based systems on their own. Mobileye integrates radar with cameras in some configurations to enhance redundancy and performance, especially for higher levels of autonomy. 
    
4. DVN: LiDAR is still expensive – US/EU vendors might approach $500 in this timeframe and China vendors might be half of that – how does HD Radar compare to LiDAR in this timeframe ? 
   
   The imaging radar solution Mobileye is preparing to bring to market demonstrates the potential to reduce the need for surround Lidar in advanced systems, offering cost advantages to OEMs without sacrificing performance. However, we believe Mobileye’s camera-based solutions will be capable of meeting regulatory requirements without the need for the added cost and complexity of imaging radar or lidar. Imaging radar and lidar become more relevant as automakers deploy more advanced automated systems, such as eyes-off highway driving.   

5. DVN: The AEB solution requires more than just the sensor of course – is the AI Component of the solution best in the camera/radar module ?  What sort of processing is needed to achieve this (TOPS ? ). Is a specialized ISP required ?  
   
   AI models for driver assistance applications are most efficiently deployed on purpose-built hardware optimized for AI-specific workloads. Mobileye’s EyeQ family of SoCs are designed from the ground up to deliver high-performance, low-power processing tailored for ADAS and autonomous capabilities. Our processors can handle the demands of multi-sensor fusion, including both cameras and radar, with enough computational power to enable real-time object detection and classification.  
   
   As an example for AI integration, the EyeQ6L harnesses a deep learning dynamic neural network (DNN). When combining the additional computational resources EyeQ6L offers with new AI integrations, this unlocks powerful capabilities, like Neural Network Semantic Segmentation (NSS), our pixel segmentation DNN, and pairs it with advanced classifiers, which enables “pathways.”  Pathways are in reference to a novel algorithm that introduces center paths for all lanes in the image simultaneously. There are also multiple new sensing products, such as advanced, any-object detection and enriched semantic information of VRUs (vulnerable road users) and vehicles alike.  

6. DVN: Will most vehicles have other L2+ functions in this timeframe. Assuming that is the case, what is the optimal sensor set for L2+ including AEB? Is there much cost savings to only meet the NHSTA requirement and will base models just have this?  Is the Mobileye system in this timeframe scalable, i.e. you can have low-cost base configuration, but same platform (with additional sensors for example) allows an upgraded L2+/L3 solution also? 
   
   By 2027, we anticipate L2+ capabilities, such as eyes-on, hands-off highway autopilot, will be offered as a premium option by most global automakers. Mobileye’s scalable architecture supports both cost-effective base configurations and enhanced systems with additional sensors for L2+/L3 functionality. For these requirements, our Surround ADAS solution, using front, rear and parking cameras linked through a single EyeQ6H, provides robust safety and driver-assist features with a simpler sensor configuration and lighter compute, making it a cost-effective option for mass market vehicles. At the premium end, Mobileye SuperVision™ delivers robust, hands-free L2+ functionality in defined domains through 11 cameras for 360-degree coverage, as well as an HD Map and Mobileye’s RSS driving policy model, using two EyeQ6H – building on the economies of scale enabled through Surround ADAS. 

7. DVN: Is there a relation given how camera detection of objects differs from human perception ? 
   
   “Perception” is the key term – humans perceive objects, the environment and key driving tasks in many ways that surpass even the most advanced camera systems. However, cameras have the advantage of never being distracted or fatigued from sensing what’s around the vehicle. Our long history with camera-based safety systems proves that technology working together with humans saves lives and reduces crashes.  

8. DVN: Are there requirements on low beam performance for good AEB performance ? 
   
   Yes, there are minimum requirements already defined in headlamp regulations. Mobileye works with OEMs to align headlamp design and sensor performance to meet these standards effectively. 

9. DVN: What would be the optimum low beam performance be for such situations ? 
   
   FMVSS No. 108 defines the maximum allowable illumination for low beam performance, which serves as a key benchmark for AEB nighttime performance. Mobileye is actively collaborating with OEMs to strike the right balance between optimizing illumination for sensor performance and ensuring compliance with FMVSS 108 regulation.   

10. DVN: Even the best camera system needs some time to arrive in its process by then detecting an object. What is the time span for object detection (worst case – average – best case) ? (Because the delta between elapsed time until detection/reaction and the remaining distance means remaining braking distance) 
    
    Our front-camera system is capable of detecting objects at ranges of hundreds of meters during daytime conditions. In low-illumination scenarios, such as those specified under FMVSS 127, detection range is more constrained due to the more limited visibility provided by low beams. However, the nighttime breaking scenarios outlined do not require extremely long detection distances for AEB to be effective. Detecting an object as close as 40 meters is sufficient to ensure safe braking under such conditions.  

11. DVN: How strong do you think is the impact of the low beam for the far- distance pedestrian object detection under streetlights in NCAP testing? 
    
    Detection with low beams under street lighting has been a standard part of NCAP testing for several years. We don’t see this as a significant challenge, as current systems on the market have consistently demonstrated strong performance at speeds up to 60 kph as required by NCAP. We work frequently with automakers to ensure low-beam headlights provide enough light for robust camera sensing in these situations at a variety of speeds.