Do we really have self driving cars right now?

Mizara Norton
Nov 1 · 9 min read

What are self-driving cars?

Self-driving cars are vehicles that are capable of sensing their environment and moving safely with little or no human input. They are also known as autonomous vehicles, connected and autonomous vehicles, driverless cars, robot cars, or robotic cars. Self-driving cars combine a variety of sensors to perceive their surroundings, such as radar, lidar, sonar, G.P.S., odometry, and inertial measurement units. Long-distance trucks are seen as being at the forefront of adopting and implementing technology.

Artificial Intelligence in autonomous vehicles

Driverless vehicles require some form of machine vision for visual object recognition. Automated cars are being developed with deep neural networks: a type of deep learning architecture with many computational stages, or levels, in which neurons are simulated from the environment that activates the network. The neural network depends on an extensive amount of data extracted from real-life driving scenarios. Researchers at their Computer Science and Artificial Intelligence Laboratory have developed a new system called MapLite. MapLite allows self-driving cars to drive on roads that they have never been on before, without using 3D maps. The system combines the G.P.S. position of the vehicle, a “sparse topological map” such as OpenStreetMap, and a series of sensors that observe the road conditions. Heavy rainfall, hail, or snow could impede the car sensors.

Classification

A classification system based on six different levels was published in 2014 by S.A.E. International, an automotive standardization body, as J3016, Taxonomy and Definitions for Terms Related to On-Road Motor Vehicle Automated Driving Systems. This classification system is based on the amount of driver intervention and attentiveness required, rather than the vehicle capabilities, although these are very loosely related. In the United States in 2013, the National Highway Traffic Safety Administration released a formal classification system but abandoned this system in favor of the S.A.E. standard in 2016. Also, in 2016, S.A.E. updated its classification, called J3016_201609.

Self-driving cars

According to SAE J3016, Self-driving car P.C. Mag defines a self-driving car as “A computer-controlled car that drives itself.” U.C.S.U.S.A. states that self-driving cars are “cars or trucks in which human drivers are never required to take control to operate the vehicle safely. Also known as autonomous or ‘driverless’ cars, they combine sensors and software to control, navigate, and drive the vehicle.”

Semi-automated Vehicles

It is considered that semi-automated vehicles are between manually driven vehicles and fully autonomous vehicles. There are a variety of vehicle types that can be described to have some degree of automation. These are collectively known as semi-automated vehicles. As it could be a while before the technology and infrastructure are developed for full automation, vehicles have increasing levels of automation. These semi-automated vehicles could potentially harness many of the advantages of fully automated vehicles, while still keeping the driver in charge of the vehicle.

Autonomous vs. automated

The definition of autonomous is self-governing. Many past projects related to vehicle automation have been automated subject to a heavy reliance on artificial aids in their environment, such as magnetic strips. Autonomous control implies satisfactory performance under significant uncertainties in the environment and the ability to compensate for system failures without external intervention. As of 2017, most commercial projects focused on automated vehicles that did not communicate with other vehicles or with an enveloping management regime. EuroNCAP defines autonomous in “Autonomous Emergency Braking” as: “the system acts independently of the driver to avoid or mitigate the accident.” which implies the autonomous system is not the driver.

Safety considerations

Most modern vehicles provide partly automated features such as keeping the car within its lane, speed controls, or emergency braking. Nonetheless, there are still some differences that remain between a fully autonomous self-driving car and driver assistance technologies. According to the B.B.C., confusion between those concepts leads to deaths. Association of British Insurers considers the usage of the word autonomous in marketing for modern cars to be dangerous. Car ads make motorists think ‘autonomous’ and ‘autopilot’ mean a vehicle can drive itself when they still rely on the driver to ensure safety. Technology, by itself, is still not able to drive the car. When some car makers claim vehicles are self-driving, when they are only partly automated, drivers risk becoming excessively confident, leading to crashes.

Levels of driving automation

In S.A.E.’s automation level definitions, “driving mode” means “a type of driving scenario with unique dynamic driving task requirements.”

Level 0: Automated system issues warnings and may momentarily intervene but has no sustained vehicle control.

Level 1: The driver and the automated system share control of the vehicle; examples are systems where the driver controls steering, and the automated system controls engine power. It maintains a set speed or engine and brake power to maintain and vary speed. Parking Assistance is another example where steering is automated while speed is under manual control. The driver must be ready to retake full control at any time. Lane Keeping Assistance Type II is a further example of level 1 self-driving. The Automatic Emergency Braking alerts the driver to a crash and permits full braking capacity is also a level 1 feature.

Level 2: The automated system takes full control of the vehicle. The driver must monitor the driving and be prepared to intervene immediately at any time if the automated system fails to respond correctly. The shorthand “hands-off” is not necessarily meant to be taken literally. Contact between a hand and the wheel is mostly mandatory during S.A.E. 2 driving, to confirm that the driver is ready to intervene.

Level 3: The driver can safely turn their attention away from the driving tasks, e.x., the driver can text or watch a movie. The vehicle handles situations that call for an immediate response, like emergency braking. The driver must still be prepared to intervene within some limited time, specified by the manufacturer when called upon by the vehicle to do so.

Level 4: As level 3, but no driver attention is ever required for safety, e.x., the driver may safely go to sleep or leave the driver’s seat. Self-driving is supported only in limited spatial areas or under exceptional circumstances. Outside of these areas or circumstances, the vehicle must be able to safely abort the trip, e.x., park the car if the driver does not retake control.

Level 5: No human intervention is required at all. An example would be a robotic taxi. In the formal S.A.E. definition below, note in particular what happens in the shift from S.A.E. 2 to S.A.E. 3: the human driver no longer has to monitor the environment. This is the final aspect of the “dynamic driving task” that is now passed over from the human to the automated system. At S.A.E. 3, the human driver still has the responsibility to intervene when asked to do so by the automated system. At S.A.E. 4, the human driver is relieved of that responsibility. At S.A.E. 5, the automated system does not need to ask for an intervention.

Technical challenges

Different systems help the self-driving car control the car. Systems that currently need improvement include the car navigation system, the location system, the electronic map, the map matching, the global path planning, the vehicle control method, and the vehicle control. Other areas that need improvement are the environment perception, laser perception, radar perception, visual perception, and the perception of vehicle speed and direction. The challenge for driverless car designers is to produce control systems capable of analyzing sensory data to provide accurate detection of other vehicles and the road ahead. Modern self-driving cars generally use Bayesian simultaneous localization and mapping algorithms. They fuse data from multiple sensors and an off-line map into current location estimates and map updates. Waymo has developed a variant of SLAM with detection and tracking of other moving objects, which also handles obstacles such as cars and pedestrians. Simpler systems may use roadside real-time locating system technologies to aid localization. Typical sensors include lidar, stereo vision, G.P.S., and IMU. Control systems on automated cars may use Sensor Fusion. Sensor fusion is an approach that integrates information from a variety of sensors on the car to produce a more consistent, accurate, and useful view of the environment.

Digital technology, homogenization and decoupling.

Autonomous vehicles, like digital technology, have specific characteristics that distinguish them from other types of technologies and vehicles. Due to these characteristics, autonomous vehicles can be more transformative and agile to possible changes. Homogenization comes from the fact that all digital information assumes the same form; during the evolution of the digital era, specific industry standards have been developed on how to store digital information and in what type of format. This concept of Homogenization also applies to autonomous vehicles. For autonomous vehicles to perceive their surroundings, they have to use different techniques, each with their accompanying digital information. Due to Homogenization, digital information from these different techniques is stored similarly. The previous statement implies that all digital information comes in the same form. That means their differences are decoupled; digital information can be transmitted, stored, and computed in a way that the vehicles and its operating system can better understand and act upon it. Homogenization also helps to exponentially increase the computing power of hard- and software, which also supports autonomous vehicles. The goal of the hardware and software is to understand and act upon the digital information more cost-effectively, therefore lowering the marginal costs.

Companies and their innovations

In 2017, Audi stated that its latest A8 is automated at speeds of up to 250kmph using its “Audi AI.” The driver would not have to do safety checks, such as frequently gripping the steering wheel. The Audi A8 was claimed to be the first production car to reach level 3 automated driving. Audi is the first manufacturer to use laser scanners in addition to cameras and ultrasonic sensors for their system. In November 2017, Waymo announced that it had begun testing driverless cars without a safety driver in the driver position; however, there was still an employee in the car. In October 2018, Waymo announced that its test vehicles had traveled in automated mode for over, increasing by about per month. In December 2018, Waymo was the first to commercialize an entirely free taxi service in the U.S.

A STAR’s Institute for Infocomm Research has developed a self-driving vehicle, which was the first to be approved in Singapore for public road testing at one-north in July 2015. It has ferried several dignitaries such as Prime Minister Lee Hsien Loong, Minister S. Iswaran, Minister Vivian Balakrishnan, and several Ministers from other countries.

References:

Also, from presentations and discussions at the Automated Vehicles Symposium organized annually by TRB and AUVSI.

Kraneshares.Com, 2019, https://kraneshares.com/resources/presentation/2019_03_31_kars_presentation.pdf

“BAE Systems To Develop Automated Cyber Defense Tools For DARPA | BAE Systems | International.” BAE Systems | International, 2019, https://www.baesystems.com/en/error-page?pagefor=article/bae-systems-to-develop-automated-cyber-defense-tools-for-darpa.

Crowe, Steve. “Maple Enables Autonomous Vehicles To Navigate Unmapped Roads.” The Robot Report, 2019, https://www.therobotreport.com/maplite-autonomous-cars-unmapped-roads/

“Tesla: How To Lose $700 Million And Maintain A $60 Billion Valuation”. Medium, 2019,https://thinkgrowth.org/tesla-how-to-lose-700-million-and-maintain-a-60-billion-valuation-107e777b530

“Who Leads The Self-Driving Cars Race? State-Of-Affairs In Autonomous Driving”. Neurohive.Io, 2019, https://neurohive.io/en/state-of-the-art/self-driving-cars/

Welcome to a place where words matter. On Medium, smart voices and original ideas take center stage - with no ads in sight. Watch
Follow all the topics you care about, and we’ll deliver the best stories for you to your homepage and inbox. Explore
Get unlimited access to the best stories on Medium — and support writers while you’re at it. Just $5/month. Upgrade