This article summarizes the new technological developmentbrought by Google – ‘Autonomous cars.’ The Google autonomous car project becameWaymo, a self-driving technology company with a mission to make it easy andsafe for people and things to move around. Cars today already include manysemi-autonomous features, like assisted parking and self-braking systems. Andcompletely autonomous vehicles—able to operate without human control—arerapidly becoming more of a reality.
The sensors in the car will be scanningeverything, and they are not affected by the driver’s mood (angry, tired,happy). “Recent NHTSA research shows that approximately 94 percent of accidentsare caused by human error,” adds Alan Amici, a vice president of automotiveengineering at TE. “Cars with advanced safety features and eventually,self-driving cars, can significantly reduce the number of collisions. Theimpact of this innovation can be far-reaching, including reduced demand foremergency response systems and reduced auto insurance and health care costs.” AnalysisIt is estimated that 1.2million people are killed on theworld’s road every year. In America alone, 33,000 people are killed each year.
So, Google claims that it can reduce these deaths by 80% with the newtechnology. The driverless car starts by understanding where it is in the worldby taking a map and sensor data and aligning the two. With the sensors, itwould be differentiating the other vehicles, pedestrians, etc. This car shouldbe able to guess other peoples’ moves and figure out how it should respond in amoment. Something like what trajectory it should follow, how quickly it shouldslow down or speed up. The car needs to understand where it is and roughlywhere the other vehicles are which is a geometric understanding of the world.
These cars can access the data from the new traffic,weather, surface conditions, construction, maps, adjacent vehicles and roadinfrastructure. Information from these sources is used by the car for brakingor avoiding hazardous situations. “Byfar the most complex part of self-driving cars, the decision-making of thealgorithms, must be able to handle a multitude of simple and complex drivingsituations flawlessly,” Amici says. “The software used to implement thesealgorithms must be robust and fault-tolerant.” These algorithms should reliablycatch the data from the sensors to make correct decisions on steering, braking,speed and route guidance.
Google came up with lidar (a radar-like technology that useslight instead of radio waves) sensor technology to bring a car without pedalsand steering wheels. Lidar builds 3D images of the surrounding landscapes.Lidar contains some rotating stacked lasers that shoot at various angles.
Everylayer is termed to be a channel and is made up of laser beams. The signal fromeach circuit generates one contour line, and together these lines create a 3Dimage of the object. Lidar also has a 360-degree vision and accurate depthinformation. Unfortunately, this lidar technology is way too expensive.A single autonomous car with all of its sensors, cameras,and Lidar roughly could generate one gigabyte of data every second.
That wouldadd up to 2 million GB of data per year per car assuming that on an averageAmerican drives 600 hours a year. This data produced by a car can be classifiedinto three categories:• Technical Data: It is the informationthat comes from the car’s sensors and is analyzed by the car’s machine learningalgorithms• Community Data: data about traffic anddriving conditions• Personal Data: riders’ personal preferences regardingdriving locations, indoor temperature, in-car entertainment, etc., all servingto improve the user experience.The autonomous car uses this data in making better decisionswhile driving.
Waymo seems to favor a higher-detail view of the world, withKrafcik saying “The detail we capture is so high that, not only can wedetect pedestrians all around us, but we can tell which direction they’refacing. This is incredibly important, as it helps us more accurately predictwhere someone will walk next”.The real hurdle for Waymo is not just in collecting the dataabout the car’s surroundings, but to implement learning algorithms and improvethe driving capability, the more data it gathers and analyzes. For suppose, acar can differentiate between a tube light and a potato chips and uses thatknowledge in future. It can conclude when a pedestrian is ready to cross thestreet by observing behavior repeatedly. Deep learning algorithms can figureout what is essential so that the car need not apply brakes every time a tinybird crosses its way.
Hence, the car uses both predictive as well asprescriptive models to improve its ability to recognize and react to its surroundings.Apart from safety issues, Google’s self-driving car canpotentially create security and personal data issues. There might be asituation where hackers can take control of the car. Intruders and advertiserscan take advantage of the exposed personal location data which is verysensitive.
Big data creates anopportunity for the self-driving cars in the future is to build a massivelyconnected network of vehicles, which will be able to interact with each other.They could also communicate with roadside wireless sensor networks to sync upinformation about traffic lights or accidents. It is firmly believed thatshortly, autonomous cars have the potential to become safer than human driverseventually.Data is transforming the way we think about transportation.
Ithas the potential to make driving more reliable and safe, by creating new opportunitiesand insights. As data becomes the new paradigm in transportation, people whocan leverage the power of this data and build responsive, intelligent,decision-making vehicles that move people and cargo around will be the winners!
