Editorial Feature

Robotic Cars That Will Drive Us into the Future

Image Credit: Mopic/Shutterstock.com

The concept of a robot car has always been a question of how and when. Back in the early ’80s, the closest car to being classed as artificially intelligent was Kitt; an electronically-aided 1982 Pontiac Firebird Trans Am, as seen on the famous television series ‘Knight Rider’, starring Michael Knight. However, the vision of developing robotic cars has not been left behind as a fad of this decade and continues to be at the forefront of modern-day research with the expectation that it will pave the way towards a radically new concept of transportation.

In 2010, Researchers at Stanford University demonstrated the product of their design and engineering efforts by presenting the autonomously-driven car, “Shelley”. The research was led by mechanical engineering Associate Professor Chris Gerdes, with the primary aspiration being to enter the car in the infamous Pike’s Peak race of Colorado. The video below captures the autonomous car ‘Shelley’ performing a practice lap of the Santa Clara County Fairgrounds in San Jose, demonstrating the speed and agility with which she is able to navigate the track.

Stanford's Autonomous Car Gets A Workout

Although fully driverless vehicles have not yet made the transition from the race track to suburban streets, automated control has increasingly seeped into vehicle design with the introduction of parking assistance and cruise control now being common features. It is therefore not surprising that automotive companies and authorities so keenly declare that we are on the brink to self-driving cars becoming an everyday part of our transport network.

Structure to an Autonomous Car

A vehicle designed for complete autonomy will be able to perform all tasks to move, tasks that would normally require human input. Not only should an autonomous vehicle be able to take full control of the vehicle, but the great emphasis should also be placed on the autonomous car’s ability to sense its environment and manipulate the function and speed of the car accordingly in order to adapt to varying driving conditions. This fundamental yet excruciatingly complex requirement was truly tested by Stanford’s Robotic Audi as it took on the hairpin bends and extensive incline of Pike’s Peak in 2010. Although Stanford’s race entry did not speed to victory and claim the Colorado crown, the sheer fact that the car completed the track, let alone in a respectable time of 27 minutes, was a victory in itself for the world of engineering.

To understand what’s involved in the design and engineering behind such a feat, it’s important to be aware of the components in the car that will enable it to react independently of manual control by a driver. Let’s sit back and take a look at an overview of some of the main actuation and sensory components that are fundamental in allowing an autonomous vehicle to sense its environment.


Actuation to a vehicle is possible through the application of direct current (DC) motors and servomotors. DC motors are important in the control of the rear wheels and are key to converting electrical current to a mechanical torque (a product of force that results in the rotation of an object). The general concept here is that the more force applied to the DC motor, the more torque produced to power movement of the shaft. In the context of robotic cars, a digital signal would conventionally be required to power the DC motor via Pulse Width Modulation, but motor control cannot work via simple digital signal input due to the significant difficulty in delivering circuitry to the motor. However, this challenge is overcome with the introduction of an interface circuit called an H-bridge which helps to convert a digital signal that is of low power into a signal with sufficient strength to isolate the DC motor and consequently activate it.

In contrast, a servomotor works to monitor both the position and speed of a moving vehicle via a feedback loop to control the speed generated. The general principle of a feedback loop is that the output is measured in comparison to the desired output and used to alter the input accordingly n a continuous process. The result of this is a device that provides precise control of the motor output.


In a manner akin to that of living organisms, in order for the vehicle to adapt to its environment, there need to be internal sensing systems in the vehicle, and there are. Hundreds of years back, you’d have seen carts and wagons with the main sensor to control the movement and speed being you, the human. Luckily, modern-day technology has freed us all from this exhaustive role. Automated vehicles are built with infrared sensors that can locate a white line on a black road surface. However, the location accuracy for this type of sensor is unavoidably dependent on that white line being directly underneath the car. Considering the convention in today's road infrastructure for the white line to run alongside the car, this would clearly not bode well with any driving test instructor.

Magnetic sensors, such as Hall Effect Sensors isolate a magnetic link that activates a field-effect device to then initiate an internal circuitry.

Vision sensors in the form of a digital camera positioned at the front end of a vehicle visually feedback the current state of the road in front. Using digital cameras in a vehicle brings the idea of autonomous cars one step closer to becoming more intuitive as visual feedback of the road ahead will resemble how the human brain perceives their environment. Image processing whereby the vehicle offers information concerning the road ahead is only part of the image sensor system. It is also important to know the proximity to another object on the road, a capability achieved via the use of headway sensors. The functional principle to headway sensing is based on the positioning of an object on the road - a moving object closer to the headway sensor will result in a more intense light emitted by the detector in this device that generates a voltage proportional to the distance between the vehicle and the nearby object.

Robotic Cars Controlled by a Smartphone

The idea of robotic cars capable of functioning independently of human control is clearly a revolutionary step in automation design and engineering. However, researchers are now taking this concept of autonomous vehicles to another gear by studying the application of smartphone technology to drive a car.

Griffith University robotic researcher Dr Jun Jo, with the help of local high school students, designed and engineered an electrically powered vehicle-controlled via an android phone. Control was achieved by connecting the smartphone to the onboard PC through a USB which then connected to the car’s actuation systems via serial interfaces. Through the integration of a lane detection system, a laser detection system, and ranging sensor the model was able to identify and locate moving objects surrounding the car.

This significant achievement by Griffith University was further trumped by the Chinese telecommunications company Huawei in February 2018 as it showcased to the Word it’s artificially intelligent smartphone with the power to remotely control a Porsche Panorama. By capitalising on the AI capabilities already integrated into Huawei’s Mate pro 10 smartphone, the technology demonstrated the enhanced ability to not only detect obstacles but to also recognise and distinguish between them. The installed system comprised of a camera, installed on the Porsche's roof, which continuously scanned the road ahead whilst wirelessly feeding a live stream of data back to the dash mounted phone. The kirin 970 chip built into the Mate Pro smartphone subsequently analysed this data by running through its preprogramed library of objects in order to identify the upcoming obstacle and direct the car to manoeuvre accordingly.

You may justifiably question what happens if the object is not in the chip's programmed directory. This is where Huawei’s prowess in machine learning takes to the stage. The phone responds by storing this newly accounted object which the user can then instruct, via an app, how they wish the car to react to such a situation. The result of which is an autonomous vehicle system with the aptitude to learn to take the most appropriate course of action in a continuous process of enhanced intelligence.

System Safety and Regulations

Although the technology is clearly outstanding and worthy of the publicity received, the idea of a car quite literally taking control out of your own hands leads to significant reservations regarding the level of safety that such a car will provide. Many have expressed apprehension over the possibility of technical breakdown issues whilst driving, particularly along a busy road at high speed. Considering the frequency with which my phone freezes, I am compelled to agree that this is a well-founded doubt. Dr Jun Jo partly addressed this issue of system malfunction by suggesting that an external PC could also operate car control to provide safety backup in the event of a malfunction to the smartphone.

Furthermore, in an effort to keep up with the rate at which autonomous vehicles are being developed, the UK government has initiated a 3-year review of the current driving laws in 2016. The purpose of which will be to adjust the current highway code by combating such questions as: how to define who holds accountability in the event of an accident?, and how can the impact on other road users be mitigated? This review primarily acts to ensure the continued safety of road users, but will also be a crucial update to establish the governments support towards future development and public integration of self-driving cars.

This response has been echoed by many other authorities across the globe. The EU has commissioned a complete revision of the General Safety Regulation for motor vehicles which will ensure consistency between national traffic laws with regards to the operation of autonomous vehicles. The assessment has also highlighted the necessity to improve road infrastructure if these cars are to become commonplace. For example, the ability of a car to react to its surroundings is inherently dependent on the quality of road markings and signs. It will therefore be a matter of paving the way for these robotic cars to drive us into the future.

Sources and Further Reading

This article was updated on 7th February, 2019.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this article?

Leave your feedback
Your comment type

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.