Browse Topic: Level 0 (No driving automation)
As the autonomy of ADAS features are moving from SAE level 0 autonomy to SAE level 5 autonomy of operation, reliance on AI/ML based algorithms in ADAS critical functions like perception, fusion and path planning are increasing predominantly. AI/ML based algorithms offer exceptional performance of the ADAS features, at the same time these advanced algorithms also bring in safety challenges as well. This paper explores the functional safety aspects of AI/ML based systems in ADAS functions like perception, object fusion and path planning, by discussing the safety requirements development for AI/ML systems, dataset safety life cycle, verification and validation of AI systems, and safety analysis used for AI systems. Among all the safety aspects listed above, emphasis is put on dataset safety lifecycle as that is not only the most important element for training ML based algorithms for ADAS usage, but also the most cumbersome and expensive. The safety characteristics associated with dataset lifecycle are dataset safety analysis, dataset requirements development, dataset design and implementation, dataset verification and validation and then finally dataset maintenance. All these dataset life cycle characteristics are discussed in detail. Holistically, this paper outlines the process flow on what is needed from safety point of view to evaluate AI/ML based systems to claim the vehicles with advanced AI/ML systems are free from unreasonable risk. Also, considering perception system as an example, Key Performance Indicators (KPI) from safety perspective are defined to explain the acceptance and rejection criteria of the AI/ML based perception system.
Automated vehicle technology is rapidly increasing in capability and the adoption of these technologies will become more widespread in the future. In the intermediate stages of automation where the driver is required to supplement the automated technology, it may be necessary to evaluate the driver’s readiness to take-over a part or of all the dynamic driving task (SAE, 2016). Specifically, while driving with a level 2 or 3 automated driving feature, a challenge may be that drivers with low readiness fail to take over in an appropriate manner. One important implication of assessing driver readiness is to assess driver state. In this study, we investigated candidate for a driver readiness index which was compared between manual driving (Level 0) and ACC driving (Level 1). Additionally, one more method to evaluate the readiness of the driver is to measure whether the driver anticipates potential hazards (i.e., does their foot hover over the brake or throttle). To encourage this type of behavior, vehicles could include a human-machine interface (HMI) that supports the driver to understand where potential hazards exist; however, this would need to be designed to prevent annoyance. The hypothesis for the series of studies was that showing overall traffic status allows the driver to more rapidly prepare for potential hazards when compared with no additional information (i.e., next lane vehicle turn signal). This part of the current study measured driver behavior and traffic data along a designated route in a naturalistic setting. Several traffic scenarios were identified that include overt anticipatory behavior. In this paper, we had two research questions. One is how to measure driver readiness level. Two is what type of information would be useful for maintaining readiness.
Items per page:
50
1 – 3 of 3