Self-Driving Automobiles: Raw and semi-processed data


Blind Driver Challenge (Image: The National Federation of the Blind)



In the beginning, there is Wikipedia.

Autonomous car

An autonomous car (driverless car,[1] self-driving car,[2] robotic car[3]) is a vehicle that is capable of sensing its environment and navigating without human input.[4]

Autonomous cars can detect surroundings using a variety of techniques such as radar, lidar, GPS, odometry, and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage.[5][6] Autonomous cars have control systems that are capable of analyzing sensory data to distinguish between different cars on the road, which is very useful in planning a path to the desired destination.[7]

Some demonstrative systems, precursory to autonomous cars, date back to the 1920s and 30s. The first self-sufficient (and therefore, truly autonomous) cars appeared in the 1980s, with Carnegie Mellon University‘s Navlab and ALV projects in 1984 and Mercedes-Benz and Bundeswehr University Munich‘s Eureka Prometheus Project in 1987. Since then, numerous major companies and research organizations have developed working prototype autonomous vehicles.

Among the potential benefits of automated cars is a significant reduction of traffic accidents, and the resulting deaths and injuries, and related costs, including lower insurance costs; major increases in roadway capacity, with the potential to more than quadruple capacity, resulting in significantly less traffic congestion; enhance mobility for the elderly, people with disabilities, and low-income citizens; relieve travelers from driving and navigation chores, freeing commuting hours with more time for leisure or work; less fuel consumption, producing less air pollution and a lower carbon footprint from road travel; significantly reduced parking space needs in cities, freeing space for other public and private uses; and facilitating or improving existing and new business models of mobility as a service, including carsharing, e-hailing, ride hailing services, real-time ridesharing, and other services of the sharing economy, all contributing to reduce car ownership.

Among the main obstacles and disadvantages due to a widespread adoption of autonomous vehicles, in addition to the technological challenges, are disputes concerning liability; the time period needed to turn an existing stock of vehicles from non-autonomous to autonomous; resistance by individuals to forfeit control of their cars; customer concern about the safety of driverless cars; implementation of legal framework and establishment of government regulations for self-driving cars; 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 driving becomes faster and less onerous without proper public policies in place to avoid more urban sprawl.



Tuesday, July 23, 2013

Making sense out of Driverless Cars

Sitting in the passenger seat as your driver lifts his arms away from the wheel and gleefully says “look, no hands” should be an unsettling experience. But this feeling will soon get superfluous after the advent of the driverless-car technology.

An autonomous car, also known as a robotic car, or informally as driverless or self-driving, is an autonomous vehicle capable of fulfilling the human transportation capabilities of a traditional car. As an autonomous vehicle, it is capable of sensing its environment and navigating without human input. Robotic cars exist mainly as prototypes and demonstration systems, but are likely to become more widespread in the near future.

Driverless vehicles sense their surroundings with such techniques as radar, GPS, and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage. Some driverless vehicles update their maps based on sensory input, allowing the vehicles to keep track of their position even when conditions change or when they enter uncharted environments.

Analysts say these cars are coming no matter what, with the earliest estimates placing commercially-available robot cars within the next five to ten years pending regulatory approval. The technology is there, it’s just a matter of getting the legislation, driver and insurance companies onboard.

Self-driving cars are one of today’s hottest technology trends. Google revealed that it was developing self-driving cars in 2010, and since then, these vehicles have logged hundreds of thousands of miles with few accidents and received approval from Nevada to test is cars on the state’s roads. Car makers such as Tesla, Audi, and Toyota have since started developing driverless solutions of their own, and GPS-maker Garmin revealed its new heads-up display (HUD) gadget today that projects key navigation information on your car’s windshield — a safer alternative to looking down at your Smartphone while driving.

While human error is responsible for 80% of auto accidents, with humans getting into at least one fender bender every 100,000 miles, according to IEEE estimates, Google claims its car logged 300,000 miles without incident.

The cars are expected to become far more widely adopted than the fuel-efficient hybrids and electric vehicles made by the likes of Tesla (TSLA) on the road today. Their focus on safety is expected to be a major selling point for consumers, insurers and the government.

As automakers focus on developing and testing driverless cars, the technologies will slowly start to be adapted into modern-day vehicles, representing a gradual yet inevitable shift.

Toyota, for example, partnered with Tesla and is expected to unveil vehicle-to-vehicle communication in its 2014 Lexus models when cruise control is activated, an early version of a technology expected to become a cornerstone of autonomous cars.

That kind of communication and instantaneous reaction time could feasibly allow a freeway of autonomous cars driving at 70 miles per hour just five feet from each other. It’s a scary thought, and one that will likely take drivers a long time to get used to, but it could serve to significantly reduce traffic and make transportation all the more safer.

Current Driverless Car Technologies

 1.)    Anti-lock brakes – One of the driverless systems that you may not have realized was driverless is anti-lock brakes. Sounds surprising, doesn’t it? After all, anti-lock brakes need the driver in order to work. Still, they represent one end of the driverless continuum because anti-lock brakes perform a function that drivers used to have to do themselves. When a car is braking hard and doesn’t have anti-lock brakes, the wheels can lock up, sending the car into an out-of-control skid. In a car without anti-lock brakes, the driver has to pump the brake pedal to keep the wheels from locking up. With anti-lock brakes, the system does the pumping for the driver — and does it better than the driver. The system can read the wheels and knows when they are about to lock and react faster and with a more appropriate response than a driver could.

2.)    Traction – Another type of driverless system is traction or stability control. These systems are so transparent that usually only professional drivers recognize when they’ve taken control. Like anti-lock brakes, traction and stability control react better than a driver ever could. Unlike anti-lock brakes, these systems are very complicated and use multiple systems within the car to keep the driver from losing control.

3.)    Cruise control – Cruise control is another common driverless system that’s available in most cars. Cruise control keeps the car at a constant speed, set by the driver, without the driver constantly having to press the gas pedal. Cruise control isn’t completely driverless, however, because the driver must watch constantly for slower moving cars in his or her path.

Illustrative Example of Cruise Control

Adaptive cruise control takes care of that. Though it’s currently available on only a few cars, it’s very simple. Using radar sensors on the front of the car, adaptive cruise control can tell when an object is in front of it and, if the object is moving, how fast it’s moving. When cruise control is set, adaptive cruise control will maintain a constant speed, but will also maintain a set distance between it and the car in front of it.

Biggest Barriers to the Driverless Car Technologies

è  The biggest hurdle is garnering widespread regulatory support, not to mention getting insurers on board and collecting support from the masses. It

could take many years.

è  Perhaps the second largest setback is the prohibitively expensive cost of these cars. It is estimated to cost about $250,000 to build each of them due to the expensive nature of the advanced technologies used.

è  The concept of self-driving cars may be all the rage in technology circles, but the organization that represents big U.S. auto makers says a new poll due out later this week indicates many U.S. consumers are wary about sharing the road with robot vehicless that could be hacked by mischief car makers.

è  Other miscellaneous technical problems to overcome.

What people think about Driverless Cars

Cisco’s survey found that 57% of the respondents, who came from 10 countries, said they’d ride in a car controlled entirely by robotic systems. Brazilians gave the most enthusiastic endorsement, with 96% of those surveyed saying they’d trust self-driving cars. Indian consumers were next at 86%. Among Chinese respondents, 70% said they would trust a driverless car. Sixty percent of the Americans surveyed said they would be comfortable in a self-piloting vehicle. The nations with the most scepticism toward autonomous cars: Auto powers Germany (37%) and Japan (28%).

According to designers and manufacturers, an increase in the use of autonomous cars would make possible such benefits as:

  • Fewer traffic collisions, due to an autonomous system’s increased reliability and faster reaction time compared to human drivers.
  • Increased roadway capacity and reduced traffic congestion (due to reduced need for safety gaps), and the ability to better manage traffic flow.
  • Relief of vehicle occupants from driving and navigation chores.
  • Higher speed limit for autonomous cars.
  • Removal of constraints on occupants’ state – in an autonomous car, it would not matter if the occupants were under age, over age, blind, distracted, intoxicated, or otherwise impaired.
  • Alleviation of parking scarcity, as cars could drop off passengers, park far away where space is not scarce, and return as needed to pick up passengers.
  • Elimination of redundant passengers – humans are not required to take the car anywhere, as the robotic car can drive independently to wherever it is required. This would be especially relevant to trucks, taxis and car-sharing services.
  • Reduction of space required for vehicle parking.
  • Reduction in the need for traffic police and vehicle insurance.
  • Reduction of physical road signage – autonomous cars could receive necessary communication electronically (although physical signs may still be required for any human drivers).
  • Improved fuel efficiency.
  • Reduced air pollution as a result of less emissions and traffic congestion.

The Google driverless car is a project by Google that involves developing technology for autonomous cars. The project is currently being led by Google engineer Sebastian Thrun, director of the Stanford Artificial Intelligence Laboratory and co-inventor of Google Street View. Thrun’s team at Stanford created the robotic vehicle Stanley which won the 2005 DARPA Grand Challenge and its US$2 million prize from the United States Department of Defense.The team developing the system consisted of 15 engineers working for Google, including Chris Urmson, Mike Montemerlo, and Anthony Levandowski who had worked on the DARPA Grand and Urban Challenges.

The U.S. state of Nevada passed a law on June 29, 2011 permitting the operation of autonomous cars in Nevada. Google had been lobbying for robotic car laws. The Nevada law went into effect on March 1, 2012, and the Nevada Department of Motor Vehicles issued the first license for an autonomous car in May 2012. The license was issued to a Toyota Prius modified with Google’s experimental driverless technology. As of April 2012, Florida became the second state to allow the testing of autonomous cars on public roads. California became the third state to legalize the use of self-driven cars for testing purposes as of September 2012[update] when Governor Jerry Brown signed the bill into law at Google HQ in Mountain View.

Google first revealed in 2010 that it had been working on self-driving cars. This fits in with its work on mapping and software and might give users extra time to surf the web, boosting Google’s profits. Last year the company released a video of a blind man sitting in the driver’s seat of one of these (albeit with a passenger as backup), being taken to buy takeaway tacos and collect his dry cleaning. Sergey Brin, one of the internet company’s founders, expects its autonomous driving system to be ready for the market in five years. That may be optimistic, but by the 2020s some cars that drive themselves most or all of the time could well be in volume production. This will have big consequences.

The idea of self-driving cars as a means of reducing accidents and congestion has been around for a long time. One of the most popular exhibits at the 1939 New York World’s Fair was “Futurama”, a depiction of a city with cars remotely controlled by radio. In the 1980s and 1990s the European Commission sponsored a programme of research on automated driving, Prometheus. In the mid-2000s the Pentagon’s research agency, DARPA, launched its Grand Challenges, offering prizes to driverless cars that did best at navigating a tricky course. In the first of these, in 2004, none of the robot cars completed the course. In the third, held in 2007, six cars made it. The winning team’s technical director was Mr Urmson. Its main advantage over its rivals was that it had mapped the course in fine detail, something that his current employers are busy doing for the rest of the planet.

But even before such prototypes have proved themselves, the technology is already arriving in instalments as carmakers introduce sophisticated “assisted driving” features as options, even on mass-market models. European buyers of the Ford Focus, a mid-sized car, can now leave it to drive itself and maintain a safe distance in steady traffic. The car can measure a parking space and steer itself into it. It reads road signs and admonishes the driver if he breaks the speed limit. Such gadgetry also increasingly makes decisions on the driver’s behalf and overrules him in an emergency, for instance, braking to avoid a crash.

Other technologies are beginning to make this easier. First, the mechanical links between the controls and the working parts are progressively being replaced by electronic ones. Second, cars now have a rudimentary version of “black box” data recorders to collect information on the moments just before an accident. Insurers have already begun to offer discounts to motorists who agree to have more sophisticated ones that monitor their driving all the time.

Basil Enan, the boss of CoverHound, an online insurance broker, says that as well as giving discounts to drivers who install black boxes, insurers are offering lower premiums on cars with assisted-driving features because they reduce accidents. He thinks that in future “manual driving” will increasingly be penalised: “The more miles you’re logging on autopilot, the less you’re going to pay.” This will give motorists an incentive to use the assisted-driving features on their cars. Carmakers, for their part, will have an incentive to keep adding more to maintain high scores in the widely publicised safety tests that help them sell their models.

Safety-enhancing gadgets on cars tend to start out as optional extras, then get incorporated into “best practice” standards promoted by independent bodies like Euro NCAP, and eventually are made compulsory. Ubiquitous black boxes in road vehicles will provide a mass of data likely to demonstrate the effectiveness of automated-driving features, which will prompt calls to make them obligatory.

Conclusion: Autonomous driver systems are still in the early stages of development and too expensive for the mainstream market, and the race to be the first for mass consumption is heating up.

Posted by Jatin Jain at 8:14 PM















Linear notes



Leave a Reply

Your email address will not be published.

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