By Indraneel Ghosh
Earlier this week Ubers autonomous vehicles were banned in Arizona, USA. This followed a road accident which led to the death of a pedestrian. At around 10 PM on March 18, one of Ubers autonomous vehicles struck a woman as she crossed a road in Tempe, Arizona. She later died from her injuries at a local hospital.
A video released by Tempe police showed the horrifying scenes before the accident occurred. In the video, the automated Uber car was moving at a constant speed with no attempt to slow down or swerve in the moments before the collision. Immediately following the crash, Uber suspended all autonomous vehicle testing activities across the US.
Self-driving technology challenged
Uber is one of the many companies which is working to design self-driven cars. In fact, there are companies all around the world working on designing such cars. After the event, all these companies came out to say that their vehicles do not have such issues. However, after witnessing the events that unfolded in Arizona, more questions are being asked about such assurances. This is the first major event that has raised questions about the viability of using current Computer Vision and automation in real-life scenarios.
Autonomous or self-driving cars work on the principles of object detection, which falls under the field of computer vision. These cars have mechanisms to detect objects in the surrounding area and then manoeuvre around them. To further enable these vehicles to drive themselves, several real-life drivers were followed and their behaviour was noted. This was then used to create a standardised model which can be used by the cars to navigate. In short, the technology uses human behaviour combined with the ability to detect objects.
What went wrong?
In the case of the accident with the Uber car, one of the things that may be to blame was the training set used for the car which was not exhaustive enough. The car could not detect the presence of an objectin this case a pedestrianand respond appropriately. Theoretically speaking, a well-designed self-driving car would have detected the pedestrian and slowed down or adjusted its speed. However, there is quite a bit of difference between theory and practical application.
Computer Vision is one of the hottest fields of research in Computer Science with several research papers coming out in the field every year. Nearly all these research papers are trying to find newer and more efficient methods for handling the problems with automated object detection. Companies around the world are attempting to use this technology to get rid of the errors that are caused by humans.
The Uber incident seems to suggest that the industry is still quite far from achieving that goal. Nevertheless, it does offer an opportunity for the industry to develop more efficient object detection techniques. It is an example of what can go wrong. Future accidents could be avoided by using a larger data-set for the algorithms. It is only a matter of time before a solution is found to such issues. Until then, one might question the safety of the automation technology that is currently being used by various firms.