Automation and robotics are completely changing the way we live and lead our lives. One of the good examples of this has to be the home vacuum robots that have revamped the way we clean our homes. Now, imagine this same level of automation being implemented to driving then we would be looking at autonomous driving.
Everyone is talking about autonomous driving but it is still a few years away from becoming a reality. For now, though, there is already progress made on this idea and automakers are not leaving any stone unturned to make autonomous driving a reality on our roads.
What is autonomous driving?
Autonomous driving essentially refers to the idea of self-driving vehicles or transport systems capable of moving without the intervention of a human driver. This is made possible with the help of vehicular automation, a ground vehicle capable of sensing its environment and moving safely with little or no human input.
Similar to how a human driver manages external conditions, an autonomous driving system is also fitted with the necessary software, sensors, and even computer vision technology, to allow the vehicle to respond to external conditions. An autonomous vehicle with support technologies such as adaptive cruise control, active steering (steer by wire), anti-lock braking systems (brake by wire), GPS navigation technology, lasers, and radar.
What are the six levels of autonomous driving?
In 2014, SAE International (Society of Automotive Engineers) published the J3016 standard to define the various parameters translating to define the state of autonomous driving. The levels for autonomous driving range from Level 0 (no automation) up to Level 5 (full vehicle autonomy).
- Level 0: This is normal driving where the car has no control over its operation and the human driver does all of the driving.
- Level 1: This is the simplest form of autonomous driving wherein the vehicle’s ADAS (advanced driver assistance system) has the ability to support the driver with either steering or accelerating and breaking.
- Level 2: In this stage, the ADAS is able to oversee steering and accelerating and breaking in some conditions. While ADAS is able to take over some of the actions, the human driver is required to pay complete attention to the driving environment. This is one of the most commonly available assisted driving systems or autonomous driving systems from brands like Tesla, BMW, Audi, Mercedes-Benz, et cetera.
- Level 3: The advanced driving system (ADS) in this case can perform all parts of the driving task in some conditions by which the human driver is required to regain control when requested to do so by the ADS. Here, the human driver remains in control even though ADS is capable of executing a large set of tasks.
- Level 4: In this case, the ADS is able to perform all driving tasks independently in certain conditions. It means the ADS does not require human attention while performing these tasks.
- Level 5: This is the pinnacle of autonomous driving which can also be referred to as full automation or fully autonomous driving. At level 5, the advanced driving system (ADS) will be able to perform all tasks in all conditions and won’t require any driving assistance from the human driver. This is made possible by the use of technologies like computer vision, advanced artificial intelligence, 5G, and more. There is even a possibility that level 5 autonomous driving vehicles might not even have a steering wheel.
Autonomous driving: How it works
An autonomous driving system, also known as an autonomous vehicle, driverless vehicle, or a robo-car, is a ground vehicle incorporating vehicular automation. These vehicles are capable of sensing their environment and moving safely within their environment with little or no human input. Autonomy in vehicles is categorised into six levels where level 0 means no automation and level 5 means the steering wheel is optional.
The most common technology available right now is called level 2, where drivers can take their hands off the steering wheel. Level 3 and level 4 autonomy allow drivers to take their eyes and mind off driving, respectively.
A self-driving car can drive itself using a variety of sensors to study its environment. These sensors include thermographic cameras, radar, lidar, sonar, GPS, odometry, and inertial measurement units. The data collected by these sensors are interpreted by onboard computers that help the vehicle identify appropriate navigation paths, as well as obstacles and relevant signage.
What are the challenges with autonomous driving?
The fully autonomous or level 5 driving system is currently being tested in major cities around the world. However, none of these systems are available to the general public yet. Out of caution, companies like Waymo are essentially using their autonomous vehicles to offer rides to their employees. Autonomous driving is a technical challenge that involves these factors.
- Lidar and Radar: The biggest challenge is the use of Lidar technology, which is expensive and has been found difficult to strike a balance. The challenge for automotive brands is to find the right balance between range and resolution so that the tech is able to distinguish between a human being and signage.
- Weather: Another challenge faced by autonomous systems is identifying the markers on the road or a layer of snow or lane dividers during difficult weather conditions. It is still not clear whether all the cameras and sensors on the autonomous driving system will be able to make the right call.
- Traffic conditions and laws: All humans drive differently. Some might prefer to park very close to the car ahead while another person might choose to maintain a car length. With autonomous driving, there will be this question of whether it will abide by traffic rules at all times and how it will react to different traffic rules in different cities. It is also not clear whether autonomous vehicles will have their own lane initially like a carpool lane for safety.
- AI vs Emotional intelligence: One of the abilities of human drivers that an assisted driving system may not be able to replicate is reading the facial expressions of other human beings and making split-second decisions. Will autonomous systems be able to replicate that or will they be able to save lives with an instinct that human drivers exhibit?
What are the advantages of autonomous driving?
One of the major advantages of autonomous driving touted by automotive companies is that they will be able to provide increased safety on the road. Tech companies like Apple and Google as well as automotive brands like Mercedes-Benz and BMW believe that autonomous vehicles could reduce the number of vehicle crashes each year.
Another advantage of autonomous driving could be people who are unable to drive, due to factors like age and disabilities, can finally get behind the wheel. Some of the other advantages of autonomous driving include the elimination of driver fatigue and the option for long-haul drivers to sleep during overnight journeys.