Edge Case Research: Self Driving Car Safety Series

Phil Koopman, Co-Founder and CTO, Edge Case Research, addresses safety performance indicators covered in the recently published, UL 4600, the Standard for Safety for the Evaluation of Autonomous Products. A section of the 4600 standard is devoted to safety performance metrics. Phil will take this opportunity to review a few of the 4600 SPIs as well as addressing the important differences between SPI's and KPI or Key Performance Indicators when it comes to developing a self driving car

In this episode, Phil Koopman, Co-Founder & CTO, Edge Case Research, addresses conformance-based metrics. Phil provides questions that can be asked to get more insight into whether a system partially or fully conforms to a standard.

Prof. Philip Koopman, Co-Founder, and CTO, Edge Case Research explains how using metrics to track the unknowns, or surprises can help determine if the self driving car is good at recognizing something weird has happened and if it will respond safely.

Prof. Phil Koopman discusses approaches to ODD (Operational Design Domain) Metrics. Phil addresses the importance of taking into account all the dimensions of the ODD to ensure the self driving car is prepared for all the interesting scenarios that it will encounter in the real world.

Professor Phil Koopman, Co-Founder & CTO, Edge Case Research explains why prediction metrics based on object movement, speed, direction, and acceleration are critical for safe path planning for self driving cars.

Prof. Phil Koopman, Co-Founder & CTO, Edge Case Research addresses approaches to perception metrics for self driving cars. Hear Phil discuss sensor performance, sensor fusion, classification accuracy, and the ability to track how often the system encounters novel things it isn't trained to see.

Phil Koopman, Co-Founder and CTO, Edge Case Research talks about approaches to planning metrics. Planning metrics deal with how effectively a self driving car can plan a path through the environment, obstacles, and other actors. I

Phil Koopman, Co-founder & CTO, Edge Case Research addresses different approaches to motion safety metrics for self driving cars.

Phil Koopman, Co-founder & CTO, Edge Case Research, provides examples of leading and lagging metrics that can help companies determine whether a self driving car will be safe enough for deployment.

Prof. Philip Koopman, Edge Case Research, Co-Founder and CTO, discuss coverage driven metrics. Phil provides an overview of industry approaches and focus metrics that measure the edge cases, or the rare situations that self driving cars will encounter in the real world.

Michael Wagner, Co-founder, and CEO, Edge Case Research, provides an overview of the company and the reasoning for establishing an education series focused on self driving car safety.

Prof. Philip Koopman, Edge Case Research, Co-Founder and CTO, begins the series discussing why lots of miles driven as metric does not necessarily prove the safety of a self-driving car.

Prof. Philip Koopman, Edge Case Research, Co-Founder and CTO, addresses disengagements as a metric for self driving cars. Governments consider disengagements as a metric to show progress, however, the disengagement metric may be doing more harm than good.

Prof. Philip Koopman, Edge Case Research, Co-Founder & CTO, addresses road testing as a safety metric. Listen to Phil explain why road testing is not about the safety of the self driving technology rather its the ability of the human test driver to keep the vehicle safe.

Prof. Philip Koopman, Edge Case Research, Co-Founder and CTO, addresses whether a driver's test can prove a self driving car is safe. Listen to Phil explain how the aspects of a human driving test change when it's a self driving car.