What are the main 5 tech pillars to winning the driverless future? How do connected cars work? When will autonomous driving rule the world? – Read to learn the answers.

Look at your car. This might be the last one you drive on your own. The leading car manufacturers promise that driverless cars will conquer the world between 2018 and 2030. One small step aside the wheel for a human becomes a giant leap for the automotive industry.

Roadmap to autonomous driving evolution

  • Rate of automation
  • 100%
  • 50%
  • 0%
Fully autonomous driving systems

Fully autonomous driving systems

Semi-autonomous driving system

More sophisticated systems, requiring driver Intervention only in emergencies

Safe driving assistance systems

Partial automation, with driver still constantly involved

  • 2015
  • 2020
  • 2030
  • Years

Self-driving car technology liberates your time on the road. Intelligent mechanics save fuel, reduce emissions, facilitate the traffic flow, improve transportation and supply services. Moreover, autonomous cars promise to save millions of lives by minimizing human factor on the road.

Autonomous cars functional architecture

Obstacle Sensing
  • Proximity sensor
  • Camera
    • stereo vision
    • edge detection
    • thresholding
    • etc
  • LIDAR, RADAR
On road rules
  • RFID tag
  • Camera
    • feature Extraction
    • Template matching
Navigation
  • Encoder
  • GPS
Path determination
  • SLAM
  • Various algorithms

Process

Monitor Control Vehicle Streeting Control

IC Engines
  • Electronic control Unit
  • Hydraulic and Pneumatic Actuators
Battery powered
  • PMW - Power MOSFETS
  • Realy drives
  • Differential Drive
  • Servo mounted

Roadblocks to the driverless future

The biggest challenges for autonomous vehicles in reaching the global market fall into three major categories: legal, ethical, and technical. Legal and ethical challenges are hard because their solutions stand outside the direct influence of the automotive industry. At the same time, technology is improving faster and faster as more companies join the race to create autonomous cars.

Roadblocks to the driverless future
  • Ethical
  • Technical
  • Legal
  • What stops the driverless future?

Tech pillars to autonomous driving

Tech pillars to autonomous driving

Today, we will take a closer look at the five tech pillars that stand tall for self-driving cars to come in the immediate future.

1. Autonomous Car Sensors and Software

Self-driving car navigation is based on the three key elements:

Car sensors
Car sensors
Connectivity
Connectivity
High-accuracy positioning system
High-accuracy positioning system
Machine learning algorithms
Machine learning algorithms

A few years ago, sensor quality and cost were at the hot spot of every discussion related to the driverless future. For example, Google used LIDAR system with a price of around $75,000 per unit that was half of their driverless car price of around $150,000 a vehicle. These prices made self-driving cars a dead weight for the global market.

Since then, Velodyne, the company specializing in the LIDAR production, offered a small but capable unit for just $500. In such a way, the high cost issue as the main roadblock to autonomous vehicles has gradually started to fade away.

At this stage, a much greater responsibility for a successful self-driving future rests with software providers. They have the entire niche to develop automotive expertise that would meet the autonomous cars requirements listed as follows:

2. Navigation and Mapping

Relying on sensors, software, and GPS, the autonomous vehicle processes nearly 4,000 GB of data daily. Advanced machine learning algorithms need timely updates to react to the ever-changing environment. Continuous exchange of data between a vehicle and the cloud overloads the connectivity channel and data storage. These create additional challenges for software vendors.

  • One autonomous vehicle 4 000 GB per DAY each day
  • Cameras 20-40 MP per second
  • Radar 10-100 KB per second
  • Sonar 10-100 KB per second
  • GPS -50 KB per second
  • Lidar 10-70 MB per second

Currently, map providers put every effort to reduce the data volume transferred between a vehicle and the cloud, trying to maximize data processing within the vehicle itself. One of the solutions is a self-healing map that would use on-board AI algorithms to navigate the autonomous vehicle without stepping too far to the cloud.

Built-in Computer Vision algorithms recognize landmarks and road signs acquired from cameras. This way, the vehicle distinguishes static objects in the changing environment and gains a detailed 3D picture within the embedded navigation system. Reducing data exchange with the cloud, keeps communication channel focused primarily on the exchange of missing map pieces among drivers. This perspective encourages map makers and OEMs to prepare for the new era of crowd-sourced maps.

3. Machine Learning and Open Location Platform

Most innovative tech companies introduce their own Open Location Platforms (OLP) literally to teach a car navigate itself. An OLP can help car manufacturers equip their current models with advanced driver assistance technologies right away instead of designing new prototypes. This step in the direction of cross-industry cooperation might dramatically speed up the appearance of driverless cars.

The collaboration between OLP providers and car makers gives an opportunity to collect as much traffic data as possible. With a growing number of cars equipped with OLP features, sensors, and powerful AI solutions, the data volume on the environment will increase exponentially. Instead of driving endless kilometers worldwide by hundreds of mapping cars to collect traffic data for HD map production, millions of regular cars connected to OLP will bring together a detailed picture of the surrounding world in record time.

  • Smart routing, POIs optimization
  • Intelliggence in vehicle via big data analytics
  • Computer Vision
  • Predictive decisions based on data
  • Car predictive maintenance

Moreover, with access to traffic data from various sources and industries, OLP has a much greater potential. It can connect the pipes of cities' infrastructure, merchants, and suppliers to become one large data hub for map users and drivers. Analyzing previous places visited by the driver, product companies can suggest a better deal for a potential customer, and not just the right turn to escape a traffic jam.

The accelerated improvement of HD maps will take autonomous driving at a home-straight line. Raw data from sensors can be accumulated as the common source of the easily accessible data about the route, traffic situation, and environment changes. The key to land all this big data at one place is the Open Location Platform.

machine-learning-diagram

4. Autonomous Car Connectivity and Communication

Would you be ready to entrust your life to an AI without even being aware of how it behaves? The issue of human’s trust to a vehicle could be resolved with the car’s communication abilities. A vehicle should be connected not only to the cloud to receive geo-data or map updates, but also to human (V2H), other vehicles (V2V), and infrastructure (V2I) to be treated as a trustful traffic participant.

Vehicle-to-human communication is based on human-machine interface that enables the driver to observe vehicle's AI intention before it makes a move. Based on natural language processing, voice V2H communication can bring an extra link between the self-driving cars and their owners.

connectivity-and-communication
  • Head unit applications
  • RSE software
  • Head-Up Display software
  • Instrumental cluster UI software
  • Mobile & web integrate solutions
  • Voice recognition and voice guidance
  • Realistic & high performance 3d rendering
  • UI/UX design & usability research

Vehicle-to-Vehicle communication brings autonomous driving to the most efficient and safe course. By communicating with other traffic participants, self-driving car receives information about upcoming obstacles, traffic congestion, and pedestrians on the road long before they occur in front of the vehicle or appear on the map.

Development of advanced V2V communication systems will make it much easier for the autonomous vehicle to understand traffic behavior. Basically, the reason is that vehicles will communicate in their own language among each other. Currently, vehicle's AI has to adapt to the human-made system of signs and signals to predict further moves of other human-driven vehicles.

communication-systems

Vehicle-to-Infrastructure communication allows an autonomous car to exchange data with the surrounding environment, including buildings, traffic lights, and road signs. For example, when driving too fast, you can receive a signal from a traffic light about possible red light violation. Also, you can receive a signal about a potential green line for further 30 km if you drive at 50 km/h.

communication-systems communication-systems

The perspective of V2I development brings us closer to the smart cities that can spread data-driven decision-making even further than the automotive industry.

smart-cities

5. Cybersecurity and Autonomous Cars

Driverless cars are already very smart. But are they smart enough not to be hacked? The answer is that they have to become that smart.

  • OBD II
  • Remote Link
    Type App
  • Airbag ECU
  • Bluetouth
  • USB
  • ADAS
    System ECU
  • Remote key
  • DSRB - Based
    Receiver (V2X)
  • TPMS
  • Passive
    Keyless Entry
  • Steering snd
    Braking ECU
  • Lighting System ECU
    (Interior and Exterior)
  • Vehicle Access
    System ECU
  • Engine and
    Transmission ECU
  • Potential attack surfaces

For example, the advanced driver assistance system (ADAS) can stop your car when you’re driving to a wall. But do you want your car stops without any reason only because of the hack attack? The importance of cybersecurity rises dramatically in the world where hacker can drive, stop, and control your car remotely.

Security systems built in the right way can be a strong barrier in a thief's halt. If the car system detects abnormality in the usual vehicle’s behavior, it can block the data access or even the car connection. In addition, preliminary penetration tests and prediction of possible threat scenarios make the security burden much easier.

  • Investigation CAN bus and ways to attack it
  • Analyzing TCP/IP and Ethemet inside the vehicle
  • TCP-Over-USB and remote attacks to services available in same network segment
  • Insecure in-car data transmission detection
  • Dos attacks on the infotainment system Android auto, Apple CarPlay and MirrorLink solutions, Bluetooth testing
  • 2G / 3G / 4G testing
  • Different kinds of XML attacks on the internal vehicle services
  • Critical vehicle’s subsystems attacks (just as break or steering)
    vis head unit

Tesla driverless car was intentionally attacked several times a day with the reward ranging from $100 to $10,000 only to find a critical bug or any other potential vulnerability. In one week, Tesla Model S was hacked in a variety of ways allowing to remotely open the door, change music, control air conditioning system, and even start the vehicle. There are many similar examples with other manufacturers. After all, we must understand that only by finding those security gaps in field conditions, autonomous cars can become safer.

Car makers and security software providers are forced to funnel into one pipeline to prevent the risks. The most likely strategy is to create an advanced architecture capable of detecting and preventing penetration or any conflict with standard vehicle algorithms.


Despite the roadblocks on its way, autonomous driving is quickly approaching the global traffic. It intends to change a common perception of urban mobility, mapping, supply services, smart cities, and AI capabilities in a larger sense.

In this race to win the driverless future, the tech part plays the role of a catalyst for a wider span of industries to consider autonomous driving as the most competitive though promising field in the nearest years.

In front of the red ribbon, endorsed with tech pillars to make it happen, autonomous driving raises the automotive industry as the benchmark for other cross-industry fields, which are relying on extra connectivity, embedded solutions, and deep AI integration as the driving forces of our common future.

At this point, one small step aside the wheel has already been taken. The giant leap that change the world has just begun.


If you were interested reading the article, you can follow this link to find more information about the automotive expertise that contribute to the emerging future of autonomous driving.