Green Car Journal logo

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.

adaptive-cruise-controlBLIND 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-systemCOLLISION 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.

lane-departure-warningOBSTACLE 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-informationREAL 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.

parking-assistPRE-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-vehicleVEHICLE-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.

Volvo Car Group initiates world unique Swedish pilot project witWe are heading toward self-driving cars quicker than anyone could have imagined just a few years ago. While it will clearly be some time before our highways are packed with driverless cars making their way to work, home, and parts beyond, there are glimpses of the future driving alongside us now.

It may be the Honda Civic self-aligned in the fast lane beside you, or the Ford Fusion Energi in your rear view mirror that stopped without driver assistance as traffic ground to a halt, then automatically paced your car as your lane began moving again. Or maybe the driver of the nearby Subaru Crosstrek Hybrid who misjudged how quickly traffic would stop, but escaped incident because of on-board systems that sensed a collision and automatically initiated emergency braking. And what about that Tesla Model S ahead that signaled and changed lanes seemingly on its own as its driver focused on something else?

autopilotThese are real capabilities of vehicles on the road today. Not all models with autonomous technologies are ‘green’ cars, but assuredly many of them will be since there’s a natural convergence of autonomous driving technology and more efficient cars unfolding before us. This is only gathering momentum as a growing number of vehicles begin to feature systems like these.

Already, cars are increasingly equipped with an array of sensors, radar, and cameras to facilitate driver assistance systems that help deal with mundane chores like backing up safely and parallel parking. These same sensors and systems provide a foundation for even more sophisticated autonomous driving capabilities.

360° Surround viewSeveral automakers are striving mightily to lead the field. Tesla is one of these, not only with the ability for its Model S to autonomously stay in its lane and with traffic flow, but automatically and safely change lanes with the flick of a turn signal when Autosteer is engaged. Cadillac is another with its upcoming Super Cruise.

Volvo is also at the forefront of this race to an autonomous driving future, in part because autonomous cars are considered much safer ‘drivers’ than humans and this aligns well with Volvo’s ambitious goal to eliminate traffic fatalities in its vehicles by 2020. Its XC90 plug-in hybrid already features some of the most advanced autonomous systems out there including Sensus Connect, Intersection Auto Brake, and Pilot Assist. Volvo has also created its Concept 26 autonomous driving interior for the XC90, the first such autonomous-focused concept interior built on a vehicle platform sold today. Volvo is taking a lead role in the world’s first large-scale autonomous driving pilot project that will find 100 self-driving Volvos negotiating everyday driving tasks on 30 miles of public roads around Gothenburg, Sweden.

VOLVO CAR GROUP LANCE UN PROJET UNIQUE AU MONDE DE VOITURES A COThe specter of life with self-driving cars presents its challenges, not the least of which is consumer distrust of such systems and the concern we will lose the driving enjoyment and sense of freedom that automobiles have brought us since their invention. While we may be in a new era that finds technology impacting most facets of daily life – with this technology increasingly making its way to our cars – the love of driving remains a priority for many.

This is supported by a recent Volvo survey in which a vast majority of those asked said autonomous car technology should respect the love of driving and, in fact, autonomous cars should include a steering wheel even if they are capable of driving themselves. At the same time, most felt that technology in autonomous cars would make their travel time more productive. In other words, we want these worlds to coexist. There’s a lot to read into that …perhaps from the driver’s seat at 65 mph, no?

Concept 26

nvidia-drive-px-artificial-intelligenceAs the auto industry rushes headlong into autonomous vehicles and technologies there are some important learning curves ahead. Google admitted as much when one of its self-driving cars was involved in a mild fender-bender with a bus…not necessarily the fault of the self-driving Google car, but no doubt caused by reacting to an unfolding situation in ways different than a human driver would react. Humans understand that mass-heavy buses do not always yield right-of-way. On-board computers wouldn’t necessarily know this unless taught.

Teaching autonomous cars how to anticipate the actions of human drivers in varying real-world scenarios is critical, and this kind of deep learning is data-intensive. This is being addressed by many companies including video game-notable NVIDIA, which works with automakers on advanced electronics systems.

nvidia-drive-px-2The company’s new DRIVE PX-2 graphics processing unit (GPU), the world’s first in-car artificial intelligence supercomputer, aims to provide 360-degree situational awareness and facilitate the deep learning required for cars to sense their surroundings and navigate autonomously, using processing power equivalent to that of 150 MacBook Pros. DRIVE PX-2 delivers up to 24 trillion deep learning operations per second, over 10 times more computational horsepower than the previous-generation product.

It’s a dangerous world out there with road debris, varying weather conditions, and unpredictable drivers. These are just some of the challenges as autonomous cars use artificial intelligence to drive better than humans. Unlike video games, there are real consequences on the road and supercomputer power like this will help keep autonomous drivers…um,