RACING SELF-DRIVING CARS WILL MAKE ROADS SAFER FOR EVERYONE
(autonomous vehicles – part 2)
#AUTONOMOUS VEHICLES, #MOTORSPORTS
Picture:URL:http://www.wired.com/wp-content/uploads/2015/12/G7C5023.jpg or URL:http://www.wired.com/2015/12/roborace-autonomous-vehicle-racing/
- “Racing Self-Driving Cars Will Make Roads Safer for Everyone”
Author: Alex Davies; Date of Publication: December 2, 2015
- “Formula E & Kinetik Announce Driverless Support Series”
Author: Formula E; Date of Publication: November 27, 2015
In motorsports, Formula One has long been recognized as the Queen, as the sport where the most advanced, sophisticated technology is rapidly as well as viciously developed, but also brutally tested. However, it is necessary to stress that this perception is agreed to shift with a racing series aiming to definitely eliminate the most obsolete, but still the most important component of an F1 car – the driver. Formula E, the all-electric racing series currently in its second season, is launching “Roborace,” an international motorsports series destined specifically for autonomous vehicles. According to Alex Davies, the author of article “Racing Self-Driving Cars Will Make Roads Safer For Everyone”, this unique championship will provide a competitive platform for the autonomous driving solutions that are now being developed by many large industrial automotive and technology players as well as top tech universities. It is possible to conclude that the Roborace Series, initiated in partnership with automaker Kinetik, encourages as well as indicates to be more than an absolutely magnificent demonstration of what the technology is able do when humans get out of the way. Furthermore, it has to be emphasized that developing autonomous racing vehicles (still “single-seaters”?) that race each another around difficult, sophisticated circuits at nearly 200 mph could provide essential information concerning how such technology could be deployed, implemented in our everyday lifes. What is more, it is necessary to stress that Roborace Series are to form part of the support package of the FIA Formula E Championship, with the first race expected to take place during the 2016-2017 season. Moreover, what has to be emphasized is the fact that Roborace is planned to race prior to each Formula E race, using the same circuits in major cities across the world. Ten teams – including a “crowd-sourced community team,” open for passionate software and technology specialists throughout the world –, and moreover, each with two driverless cars, will face one-hour races over the full championship season. It also crucial to stress that nevertheless the fact that all the teams will have the same cars, they are to contend using real-time computing algorithms and AI technologies. The cars will be electric, however, it has to be emphasized that the event organizers admit they will be nearly as fast as the single-seaters competing in Formula One. Moreover, nevertheless the fact that Denis Sverdlov, CEO of Kinetik Company, promises “really crazy speeds” up to 186 mph, specific limits almost certainly will be imposed for racing. What has to be also stressed is the information that the cars may look completely different from the current, traditional race cars, as there is no need for a human inside. It is possible to conclude that the mission of Roborace is to determine that the future of automotive and information technology is already available and can even work in the most extreme conditions. Denis Sverdlov is of the following opinion: “We passionately believe that, in the future, all of the world’s vehicles will be assisted by AI and powered by electricity, thus improving the environment and road safety.” “It’s a global platform to show that robotic technologies and AI can co-exist with us in real life. Thus, anyone who is at the edge of this transformation now has a platform to show the advantages of their driverless solutions and this shall push the development of the technology.” Furthermore, “Roborace is an open challenge to the most innovative scientific and technology-focused companies in the world. It is very exciting to create a platform for them to showcase what they are capable of and I believe there is great potential for us to unearth the next big idea through the unique crowd-sourced contest,” emphasizes Alejandro Agag – CEO of Formula E.
However, what is even more exciting than the concept of robots racing is the issue of how training, teaching those vehicles to race may develop the systems destined for consumer vehicles. “There are certain problems you have to solve at these high speeds that could improve performance at low speeds,” says John Dolan, who studies autonomous technology at Carnegie Mellon’s Robotics Institute. What is crucial to emphasize here is the problem to reduce latency – the time it takes the computer to process the data coming from a sensor and transmit instructions to various systems. “At 180 mph, you’re gonna have to do that faster,” Dolan stresses. It is possible to conclude that reducing that time, which is mostly a software issue, in racing develops a more efficient as well as effective system in the automobiles we will have the opportunity to use. On the other hand, it is also necessary to stress that creating an “everyday” car that can handle racing dynamics may also have a significant impact on the broadly defined behavior of autonomous cars. It has to be emphasized that – two years ago – Audi’s self-driving RS7 lapped Germany’s Hockenheimring F1 track, hitting all 17 turns with precision and reaching maximum speed of 149 mph. What is more, Audi also decided to send an autonomous TTS racing up the 156-turn Pikes Peak mountain circuit in 2010, then around California’s Thunderhill Race Track in 2012. Furthermore, it is also crucial to present here the information that Stanford University researchers demonstrated an autonomous DeLorean they instructed to drift and do donuts. It is possible to conclude that both of the projects were focused on comprehending how driverless cars behave at the limit of traction and grip, and implementing that learnings to technology destined for consumers. Moreover, Alex Davies is of the opinion that by developing cars that can reach triple-digit speeds while racing on the very difficult street circuits of the Formula E calendar, the Roborace teams will inevitably be developing systems that can be deployed to consumer cars. However, it is crucial to stress that the Roborace vehicles will have to confront a challenge the Audi and Stanford cars did not have to deal with: competition. The Roborace cars will be racing, and the only way to come in first – if you do not start from the pole position and hold the lead – is to pass the car – the robot – ahead of you. It is important to emphasize that for a human, whether on the racetrack or a two-lane country road, passing is considered to be a problematic maneuver – it is necessary to pick the perfect moment, the right direction, the proper steering angle and degree of acceleration; all while balancing the risk of crashing with the reward of moving ahead. Finally, it is possible to conclude that the capability to make that kind of complex decision in near real time is key to safely handling all sorts of everyday driving situations.
I would like to emphasize that even though some of the most crucial details concerning the Roborace Project have already been presented, there is still no information regarding the potential participants. Nevertheless the fact that it is impossible to confirm that the most deeply involved in automotive autonomy concept companies (Ford, Google) will also concentrate on creating self-driving racing cars – developing “racing” algorithms and AI “racing” technologies –, I believe that the implementation of this great, unique racing series will have a significant impact on the autonomous driving solutions, technologies that are now being developed by many large industrial automotive and technology players – on the systems destined for consumer vehicles. I am convinced that developing autonomous racing vehicles that can race each another around difficult Formula E street circuits – at nearly 200 mph – will provide essential information concerning how such technology could be implemented in our daily lifes. What is crucial to emphasize here is the issue of reducing latency – the time it takes the computer to process the data coming from a sensor and transmit instructions to various systems. It is possible to conclude that reducing that time, which is mostly a software issue, in racing develops a more efficient as well as effective system in the automobiles we will have the opportunity to use. However, it is also crucial to stress that the Roborace vehicles will have to confront a challenge concerning overtaking other vehicles. In my opinion, the capability to perform that kind of difficult maneuver in near real time is key to safely handling all sorts of everyday driving situations. It is also important to remember about the idea of creating crowd-sourced community racing team. I would like to stress that this is a great idea since there are many independent talents in the world that might contribute to this initiative. All things considered, the Roborace teams will inevitably be developing systems that can be deployed to consumer cars.
Picture:URL:http://www.wired.com/wpcontent/uploads/2015/12/JAGUAR_FORMULA_E_02-932×524.jpg or URL:http://www.wired.com/2015/12/jaguars-joining-formula-e-electric-racing-but-its-not-just-about-the-races/#slide-3