There’s a lot of talk these days about self-driving cars and their place in our driving future. While we are likely to see autonomous vehicles plying our highways in the years ahead, in the meantime many of the ‘smart’ technologies integral to self-driving cars are available in vehicles you can buy today. Focusing on accident prevention and driver convenience, their appearance is usually in higher-end vehicles first before they filter down to more affordable models, driven by popularity, major cost reductions, and government mandates. Fortunately, many new capabilities can be added easily by writing software that uses sensors, cameras, and other hardware already installed on a vehicle. Automakers can use the Internet of Things (IoT) to add this software over the air without requiring owners to take vehicles back to the dealer, just like Windows and Apple update your computer and smartphone. Yes, it’s a brave new world.
DRIVER DROWSINESS DETECTION helps prevent accidents. Fatigue can be measured by monitoring eye activity, changes in driving style determined by steering input, or a lane departure alert system showing a driver is often drifting from his lane. In more sophisticated systems drowsiness could be identified with sensors monitoring brain activity, heart rate, skin conductance, or muscle activity. A visual or audible warning may be issued or the driver’s seat may vibrate. More sophisticated monitoring techniques may also detect a medical emergency and call 911.
BLIND ZONE ALERT systems typically use radar or ultrasonic sensors on both sides of the vehicle to “look” for cars, trucks, and motorcycles in side blind zones. These systems alert a driver with a flashing light in the side view mirrors and often with an audible sound or vibration of the steering wheel. If the turn signal in not activated to indicate you’re planning to change lanes, the mirror warning light glows to show there’s a vehicle in your blind spot but does not flash.
ADAPTIVE CRUISE CONTROL augments a vehicle’s standard cruise control system to enhance safety. Once selected, it automatically adjusts vehicle speed to maintain a safe distance from vehicles ahead. The system’s radar, laser sensors, and/or cameras detect if you will be overtaking a vehicle in the lane ahead and automatically slows your speed if necessary. Your set cruise control speed resumes when traffic ahead allows.
COLLISION AVOIDANCE SYSTEMS can prevent or reduce the severity of a collision by using cameras, radar, and sometimes LIDAR to detect an imminent crash. Once detected, the system provides a warning if a collision is imminent and can autonomously activate braking or steering, or both. If a driver does not react to a warning, the system pre-charges brakes and increases brake assist sensitivity to maximize braking performance. Most manufacturers plan to include automatic emergency braking as standard equipment on cars in the U.S. by 2022.
LANE DEPARTURE ALERT uses a specialized camera to detect painted lane markings and alert a driver that inadvertently strays out of their lane. An audible warning and indicator light on the instrument panel is typically used to warn wayward drivers, and sometimes a steering wheel vibration. In more sophisticated systems, Steering Assist will initiate corrective steering to help keep the vehicle in its lane if a driver does not take corrective action.
OBSTACLE AVOIDANCE SYSTEMS scan the road ahead with radar, ultrasonic sensors, and/or cameras for pedestrians, motorcycles, large animals, or other objects that are stopped or moving slowly. Initially, visual and audio warnings are given when a potential collision is detected by the sensors. If necessary, automated steering and braking maneuvers the vehicle to avoid a collision.
ANTICIPATING THE ROAD AHEAD is possible with GPS navigation data integrated with on-board systems. For example, navigation data can be used to control a transmission or set up suspension for a winding road ahead, or adjust for sporty driving, fuel economy, or comfort. In plug-in vehicles data can be used to identify sections of a route best suited for electric drive or for charging the battery.
REAL TIME TRAFFIC INFORMATION supplied by a traffic information service identifies accidents and other traffic delays by presenting this information on a navigation screen. The navigation system can calculate and recommend alternate routes to a destination that bypass the location causing a delay.
PARKING ASSIST enables hands-off automated parallel and often also perpendicular parking by controlling throttle, steering, and braking. The system scans to assure there is sufficient space and often locates vacant parking spots. Advanced systems may work with a real-time traffic information system to predict the odds of finding an open parking spot in a particular area, since looking for a parking space is a major contributor to traffic congestion in urban areas.
PRE-SENSE SYSTEMS detect potentially unavoidable crashes with sensors from electronic stability and collision avoidance systems, blind spot detection, adaptive cruise control, and rear cameras. A pre-sense event occurs in phases with a visual and/or audible warning so the driver can take evasive action, then brief automatic braking tells a driver to apply braking with brake assist enhancing deceleration. If a collision can’t be avoided maximum braking is applied, seat belts are pre-tensioned, hazard lights are activated, windows are closed, and airbags deployed to mitigate injuries.
REMOTE PARK ASSIST allows your car to autonomously park in a tight spot or a narrow garage. With this system, driver and passengers exit the vehicle once it is aligned with a parking spot. The vehicle is then slowly and autonomously moved forward using a remote control fob or smartphone. This capability is made possible by surround-view sensors that enable precise movement and positioning of the vehicle amid other cars or objects, using the same sensors and controls as those used by more familiar parallel and perpendicular park assist systems. Once parked, the car can also be turned off and locked remotely. The process is reversed to fetch the car when you want to leave.
VEHICLE-TO-VEHICLE COMMUNICATION allows vehicles to “talk” with one another to exchange information like speed and GPS-derived location. The main benefit is accident avoidance, but once implemented this sophisticated network could also reduce traffic congestion. Vehicles share safety data 10 times per second to identify risks and provide warnings to avoid crashes. This kind of information can inform a driver in advance whether it is safe to pass on a two-lane road, make a left turn across the path of oncoming traffic, or if a vehicle is approaching at a blind intersection. Vehicle-to-infrastructure communication enables the transfer of data between vehicles and elements of the roadway infrastructure including speed limits and traffic lights. With advanced V2V and V2I systems, vehicles could autonomously take necessary actions to avoid a potentially serious incident or collision.
The age-old adage, “Race on Sunday, Sell on Monday,” is being applied to driverless cars in Roborace, a global championship series for autonomous electric race cars. Rather than fender-to-fender duels between race drivers, competitors will be programmers. The ones with the best software and artificial intelligence (AI) techniques will be taking the checkered flag. These advanced technologies could be used in future driverless vehicles that will be sold to consumers in coming years. As expected, the key challenge is collision-avoidance. If a driverless racer can avoid others racing alongside at 200 mph, the technology stands a pretty good chance on the street.
Each of the 10 teams participating in the Roborace series will be competing in identical driverless Robocars, two per team. It’s a new take on spec series racing where teams compete in identical cars, but in this case what sets teams apart is not a driver’s skill and daring, but the algorithms and capabilities of its programmers. In other words, the best computer programming skills will result in a win with less requirement for the enormous budgets or huge R&D required for most race competitions. That means college teams could conceivably compete against a team of Ferrari engineers. Racing is planned for the same tracks used by the FIA Formula E Championship series where electric-powered race cars compete, but still with human drivers.
Designed by Daniel Simon, the 2145 pound, primarily carbon fiber Roborace Robocar is powered by four 402 horsepower (300 kW) motors and a 540 kWh battery, plus the requisite electronic gear. Obviously, there is no need for a cockpit with a steering wheel, instruments, or pedals. Safety equipment like roll cages and air bags are also unneeded. This frees up space and weight in the race car for a huge array of electronics including two radars, five laser-powered LIDAR detectors, six AI-driven cameras, two optical speed sensors, 18 ultrasonic sensors, and GNSS (Global Navigation Satellite System) positioning. The Robocar’s nose is made of special material so radar can ‘see’ through it. LIDARs are built into the wheel arches to eliminate blind spots. Computing is done by an NVIDIA Drive PX2 AI supercomputer capable of up to 24 trillion AI operations per second.
Initial testing began in the summer of 2016 using ‘DevBot’ test vehicles. These had the same internal components including battery, motor, ad electronics used in the Robocar, but were placed in the chassis of an LMP3 Ginetta race car. DevBots drove on their own, but they also had a cockpit so an engineer could sit inside and take control if required. The DevBots were quite different from the Robocar in looks and performance. During testing before the 2017 Buenos Aires ePrix, two DevBot cars raced autonomously against each other for 20 laps. This was the first-ever live demonstration of two driverless cars on the track at the same time. One successfully avoided a dog that ran onto the course while the other car crashed on a corner, showing there were clearly many challenges to be solved before race fans would see a full grid of Robocars racing on a track.
Now another milestone has been achieved. A self-driving Robocar performed a demonstration on the city streets of Formula E’s Paris ePrix on May 20, with the car negotiating its way around 14 turns of the circuit in self-driving autonomous mode. Similar demonstrations will be performed at other Formula E events during the rest of the 2017 racing season.
There remains one important question: Will motorsports fans want to see silent driverless cars racing? One pundit says maybe so…when the NFL uses robot quarterbacks. Still, progress marches on. The Robocar is taking a bold step toward a new type of racing that will provide learnings and technology breakthroughs that should help bring autonomous cars to our highways sooner than later.