Deep Learning: Achilles Heel in Robo-Car Tests

PARIS — Advancements in machine learning have made autonomous driving a near reality. But when the issue comes down to “safety testing,” machine learning is self-driving’s Achilles heel, according to safety experts.

Philip Koopman, professor of Carnegie Mellon Univ., believes the biggest hole in a Federal Automated Policy published late Sept. is in the regulators’ failure to tangle head-on with fundamental difficulties in testing Machine Learning — a problem already known to the scientific/engineering community.

“Mapping Machine Learning‐based systems to traditional safety standards is challenging,” Koopman said, “because the training data set does not conform to traditional expectations of software requirements and design.”

In Koopman’s opinion, the Fed’s policy “should say that Machine Learning is an unusual, emerging technology.” This acknowledgement would prompt regulators to ask more pointed questions on Machine Learning in their safety assessment.

“I’m not saying how to test the Machine Learning (ML)’s training data set,” said Koopman. Rather, “I’m proposing that the DoT should demand from a carmaker or autonomous car platform vendor a written document that justifies why their ML-based autonomous vehicle is safe,” he said.

Philip Koopman

Philip Koopman

Koopman teaches embedded systems to undergraduates, and safety-critical embedded systems to grad students at CMU.

He has been involved in autonomous vehicle safety for 20 years. His experience ranges from participating in the Automated Highway System (AHS) program early in his career to working at the National Robotics Engineering Center with funded projects on autonomous vehicle safety and robotic system dependability.

Challenges in Machine Learning
Asked by EE Times how to test Machine Learning systems, Luca De Ambroggi, principal analyst, Automotive Semiconductor, Technology at IHS Markit, told us, “This is the biggest challenge. There is no answer there yet.” 

R&D veterans of Machine Learning field are familiar with its brittleness. The DoT should probe “the completeness and correctness of the ML data set, training process, and validation process,” explained Koopman.

The DoT rolled out what it calls a “15 Point Safety Assessment” for manufacturers, developers and other organizations to follow in the design, development, testing and deployment of automated vehicles. Under the proposed guideline, regulators are asking automakers to provide the National Highway Traffic Safety Administration (NHTSA) with a safety assessment. While praising the  DoT  for “a good job at proposing a baseline for discussing how an appropriate level of safety can be achieved,” Koopman noted several gaps in the guidelines especially when it comes to Machine Learning.

(Source: Department of Transportation)
Click here to download Federal Automated Vehicle Policy

(Source: Department of Transportation)

Click here to download Federal Automated Vehicle Policy

Followings are a few topics Koopman believes that regulators should cover in assessing safety in ML-based autonomous cars.

To read the rest of this article, visit EBN sister site EE Times.

0 comments on “Deep Learning: Achilles Heel in Robo-Car Tests

Leave a Reply

This site uses Akismet to reduce spam. Learn how your comment data is processed.