An  autonomous car  (also known as a  driverless car ,  self-driving car ,  robotic car ,  autos) and unmanned ground vehicle is a vehicle that is capable of sensing its environment and navigating without human input.

Autonomous cars use a variety of techniques to detect their surroundings, such as radar, laser light, GPS, odometry and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage. Autonomous cars must have control systems that are capable of analyzing sensory data to distinguish between different cars on the road.

The potential benefits of autonomous cars includ e reduced mobility and infrastructure costs, increased safety, increased mobility, increased customer satisfaction and reduced costs cars are predicted to increase traffic flow; provide enhanced mobility for children, the elderly, disabled and the poor; relieve travelers from driving and navigation chores; lower fuel consumption; significantly reduce needs for parking space; reduce crime and facilitate business models for transportation as a service, especially via the sharing economy. This shows the vast disruptive potential of the emerging technology. On the downside, a designed paper by Michael Osborne and Carl Benedikt Frey found that autonomous cars would make many jobs redundant.

Among the main obstacles to widespread adoption are technological challenges, claims concerning liability; the time period needed to replace the existing stock of vehicles; resistance by individuals to forfeit control; consumer safety concerns; implementation of a workable legal framework and establishment of government regulations; risk of loss of privacy and security concerns, such as hackers or terrorism; concerns about the resulting loss of driving-related jobs in the road transport industry; and risk of increased suburbanization as travel becomes less costly and time-consuming. Many of these issues are due to the fact that autonomous objects, for the first time, allow computers to roam freely, with many related safety and security concerns.

Autonomous vs. automated

Autonomous  means self-governance. Many historical projects related to vehicle autonomy have been  automated  (made to be  automatic ) due to a heavy reliance on artificial hints 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.

One approach is to implement communication networks both in the immediate vicinity (for collision avoidance) and further away (for congestion management). Such outside influences in the decision process reduce an individual vehicle’s autonomy, while still not requiring only human intervention.

Wood et al. (2012) write “This Article generally uses the term ‘autonomous,’ instead of the term ‘automated.'” The term “autonomous” was chosen “because it is the term that is currently in more widespread use (and ‘自信’ connotes control or operation by a machine, while ‘autonomous’ connotes acting alone or independently. Most of the vehicle concepts (that we are currently aware of) have a person in the driver’s seat, utilize a communication connection to the Cloud or other vehicles, and do not choose either destinations or routes for reaching them. Thus, the term ‘automated’ would more than describe these vehicle concepts “. As of 2017, most commercial projects focused on autonomous vehicles that did not communicate with other vehicles or an enveloping management regime.

Safety record

Mercedes autonomous cruise control system

In 1999, Mercedes introduced  Distronic , the first radar-assisted ACC, on the Mercedes-Benz S-Class (W220) and the CL-Class. The Distronic system was able to adjust the vehicle speed automatically to the car in front in order to always maintain a safe distance to other cars on the road.

In 2005, Mercedes refined the system (from this point called ” Distronic Plus “) with the Mercedes-Benz S-Class (W221) being the first car to receive the upgraded Distronic Plus system. Distronic Plus could now completely halt the car if necessary on E-Class and most Mercedes sedans. In an episode of  Top Gear , Jeremy Clarkson rendered the effectiveness of the cruise control system in the S-class by coming to a complete halt from motorway speeds to a round-about and getting out, without touching the pedals

By 2017, Mercedes has vastly expanded its autonomous driving features on production cars: In addition to the standard Distronic Plus features such as an active brake assist, Mercedes now includ es a steering pilot, a parking pilot, a cross-traffic assist system, night -vision cameras with automated danger warnings and braking assist (in case animals or pedestrians are on the road for example), and various other autonomous-driving features. In 2016, Mercedes also introduced its Active Brake Assist 4, which was the first emergency braking assistant with pedestrian recognition on the market.

Due to Mercedes’ history of gradually implementing advancements of their autonomous driving features that have been extensively tested, not many crashes that have been caused by it are known. One of the known crashes dates back to 2005, when German news magazine ” Stern ” was testing the Mercedes’ old Distronic system. During the test, the system did not always manage to brake in time. Ulrich Mellinghoff, then Head of Safety, NVH, and Testing at the Mercedes-Benz Technology Center, stated that some of the tests failed due to the vehicle being tested in a metallic hall, which caused problems with the system’s radar. Later iterations of the Distronic system have an upgraded radar and numerous other sensors, which are not susceptible to a metallic environment anymore. In 2008, Mercedes conducted a study comparing the crash rates of their vehicles equipped with Distronic Plus and the vehicles without it, and concluded that those equipped with Distronic Plus have an around 20% lower crash rate. In 2013, German Formula One driver Michael Schumacher was invited by Mercedes to try to crash a Mercedes C-Class vehicle, which was equipped with all safety features that Mercedes offered for its production vehicles at the time,which includ ed the Active Blind Spot Assist, Active Lane Keeping Assist, Brake Assist Plus, Collision Prevention Assist, Distronic Plus with Steering Assist, Pre-Safe Brake, and Stop & Go Pilot. Due to the safety features, Schumacher was unable to crash the vehicle in realistic scenarios.

Tesla Autopilot

In mid‑October 2015 Tesla Motors rolled out version 7 of their software in the U.S. that includ ed Tesla Autopilot capability. On 9 January 2016, Tesla rolled out version 7.1 as an over-the-air update, adding a new “summon” feature that allows cars to self-park at parking locations without the driver in the car. Tesla’s autonomous driving features can be classified as somewhere between level 2 and level 3 under the U.S. Department of Transportation’s National Highway Traffic Safety Administration (NHTSA) five levels of vehicle automation. At this level the car can act autonomously but requires the full attention of the driver, who must be prepared to take control at a moment’s notice. Autopilot should be used only on limited-access highways, and sometimes it will fail to detect lane markings and disengage itself. In urban driving the system will not read traffic signals or obey stop signs. The system also does not detect pedestrians or cyclists.

The first fatal accident involving a vehicle being driven by itself took place in Williston, Florida on 7 May 2016 while a Tesla Model S electric car was engaged in Autopilot mode. The occupant was killed in a crash with an 18-wheel tractor-trailer. On 28 June 2016 the National Highway Traffic Safety Administration (NHTSA) opened a formal investigation into the accident working with the Florida Highway Patrol. According to the NHTSA, preliminary reports indicate the crash occurred when the tractor-trailer made a left turn in front of the Tesla at an intersection on a non-controlled access highway, and the car failed to apply the brakes. The car continued to travel after passing under the truck’s trailer. The NHTSA’s preliminary e v a luation was opened to examine the design and performance of any automated driving systems in use at the time of the crash, which involved a population of an estimated 25,000 Model S cars. On 8 July 2016, the NHTSA requested Tesla Motors provide the agency detailed information about the design, operation and testing of its Autopilot technology. The agency also requested details of all design changes and updates to Autopilot since its introduction, and Tesla’s planned updates schedule for the next four months.

According to Tesla, “neither autopilot nor the driver noticed the white side of the tractor-trailer against a brightly lit sky, so the brake was not applied.” The car attempted to drive full speed under the trailer, “with the bottom of the trailer impacting the windshield of the Model S.” Tesla also stated that this was Tesla’s first known autopilot death in over 130 million miles (208 million km) driven by its customers with Autopilot engaged. According to Tesla there is a fatality every 94 million miles (150 million km) among all type of vehicles in the U.S. However, this number also includ es fatalities of the crashes, for instance, of motorcycle drivers with pedestrians.

In July 2016 the U.S. National Transportation Safety Board (NTSB) opened a formal investigation into the fatal accident while the Autopilot was engaged. The NTSB is an investigative body that has the power to make only policy recommendations. An agency spokesman said “It’s worth taking a look and seeing what we can learn from that event, so that as that automation is more widely introduced we can do it in the safest way possible.”. In January 2017, the NTSB released the report that concluded Tesla was not at fault; the investigation revealed that the Tesla car crash rate dropped by 40 percent after Autopilot was installed.

According to Tesla, starting 19 October 2016, all Tesla cars are built with hardware to allow full self-driving capability at the highest safety level (SAE Level 5). The hardware includ es eight surround cameras and twelve ultrasonic sensors, in addition to the forward-facing radar with enhanced processing capabilities. The system will operate in “shadow mode” (processing without taking action) and send data back to Tesla to improve its abilities until the software is ready for deployment via over-the-air upgrades. After the required testing, Tesla hopes to enable full self-driving by the end of 2017 under certain conditions.

Google self-driving car

In August 2012, Alphabet (then Google) announced that their vehicles had been completed over 300,000 autonomous-driving miles (500,000 km) accident-free, typically involving a dozen cars on the road at any given time, and that they were starting to test In late-May 2014, Alphabet revealed a new prototype that had no steering wheel, gas pedal, or brake pedal, and was fully autonomous. As of March 2016, Alphabet had test-driven their fleet in autonomous mode a total of 1,500,000 mi (2,400,000 km). In December 2016, Alphabet Corporation announced that its technology would be spun-off to a new subsidiary called Waymo.

Based on Alphabet’s accident reports, their test cars have been involved in 14 collisions, of which other other drivers were at fault 13 times, although in 2016 the car’s software caused a crash.

In June 2015, Brin confirmed that 12 vehicles had been collisions as of that date. Eight involved rear-end collisions at a stop sign or traffic light, two in which the vehicle was side-swiped by another driver, one in which another driver through a stop sign, and one where a Google employee was controlling the car manually. In July 2015, three Google employee suffered minor injuries when their vehicle was rear-ended by a car said driver failed to brake at a traffic light. This was the first time that that collision forced in injuries. On the 14 February 2016 a Waymo vehicle attempted to avoid sandbags blocking its path. During the maneuver it struck a bus. Alphabet stated, “In this case, we clearly bear some responsibility, because if our car had not moved there would not have been a collision. “Google characterized the crash as a misunderstanding and a learning experience.

Uber

In March 2017, an Uber test vehicle was involved in an accident in Arizona when another car failed to yield, flipping the Uber vehicle.