Computer Scientists From Italy

"I’m here to help Five tackle the challenge of verifying autonomous vehicles. I have a clear aim: to help Five find ways of giving guarantees that Five’s cars are safe, so passengers can step inside the vehicle knowing it will do no harm to them or those around them."

"The general public will experience the car as a vehicle that performs journeys on our cities’ roads, getting people from A to B quickly and affordably. But, under the proverbial bonnet, there will be plenty more going on. These are not cars as we’ve known them. They’re autonomous in the sense that the car will be taking a number of decisions independently during the journey."

"With this in mind, we need to think about how we can give guarantees that the actions the vehicle will perform are safe with respect to its integrity and the environment. Let’s remember that we do not only have to consider the passengers but also the environment, which will be diverse and complex, encompassing other vehicles, pedestrians, cyclists, buildings, weather conditions, and more."

"To provide guarantees, we’ll of course perform extensive testing. This will give us some confidence about the way in which the vehicle will behave over a broad range of standard and corner cases. But testing is necessarily incomplete however extensive our testing, it can never be exhaustive. There are only a finite amount of situations one can test."

"A major challenge in deploying ML-based systems, such as ML-based computer vision, is the inherent difficulty in ensuring their performance in the operational design domain. The standard approach consists in extensively testing models against a wide collection of inputs. However, testing is inherently limited in coverage, and it is expensive in several domains."

"let's start with the approach. I'd say first of all that my approach is the historical one, that of early artificial intelligence. Artificial intelligence, born at the 1956 Dartmouth conference, is a technical discipline that brings together philosophers, computer scientists, engineers, neuroscientists, and psychologists of the time."

"In the community of artificial intelligence scholars, this type of approach, which brings together expertise from different fields to study the same phenomenon in both biological and artificial systems, is extremely rare. Today, hyper technicality clearly prevails."

"Those who work in computer vision, those who write facial recognition software, know almost nothing about the technical developments that concern, say, automatic reasoning systems: they know almost nothing about that sub-area of artificial intelligence. Furthermore, still using the example of computer vision, another important aspect is the fact that, in the vast majority of cases, this approach no longer draws on what we know from studies regarding the vision of other biological entities, such as humans or even animals."

"And this applies not only to vision but to all areas perception, action, reasoning, and even natural language, as is evident today with ChatGPT and other generative models of this type. It's important to emphasize that the way these systems respond has nothing to do with the way we humans generate responses using our linguistic competence."