RESEARCH

Autonomous Driving

Autonomous driving is the future of automotive industry and is moving forward globally as defined by the levels of autonomy of vehicles. These levels now clearly defined the scope of autonomous vehicles and how this technology is heading to full autonomy where the driver of the vehicle becomes optional and is even not needed.

Dependent

  • The driver is in full control

Part Autonomous

  • automated acceleration pedal

Part Autonomous

  • automated acceleration pedal
  • lane keeping
  • semi-automatic lane changing

Commercial Level

Part Autonomous

  • automated acceleration pedal
  • lane keeping
  • lane changing full automated
  • steering full automated
  • automatic Highway changing

Semi Autonomous

  • The driver awareness needed is minimum
  • The car will inform the driver to take control

Full Autonomous

  • The driver is optional and not needed

We are working on development of Level 4 and 5 vehicles that are autonomous in all situation and driving environments, and not just under certain limited circumstances.

Our vision is to develop a system that can not only drive autonomously in organised traffic conditions, for example, in Munich but also in less organised conditions, for example, in Shanghai and challenging conditions, for example, in Cairo and Mumbai. Our approach the autonomous driving is from a global perspective.


Traffic in Munich, Germany
Traffic in Shanghai, China
Traffic in Cairo, Egypt
Traffic in Mumbai, India

SIGRA Autonomous Vehicle

What is Autonomous Driving?

Autonomous cars can detect surroundings using a variety of techniques such as radar, lidar, GPS, odometry, and computer vision. Advanced control systems interpret sensory information to identify appropriate navigation paths, as well as obstacles and relevant signage. Autonomous cars have control systems that are capable of analyzing sensory data to distinguish between different cars on the road, which is very useful in planning a path to the desired destination.

Control Systems

Some of the obstacles to identify

Surrounding Sensors

To reach full autonomy, the vehicle should be able perceive complete 360° environment around it. This is achieved by using multiple sensors on the vehicle. These sensors include LiDARs, Radars, Cameras, and Ultrasonic Sensors.


This 360° perception of the environment is important for the vehicle to detect oncoming and surrounding vehicles, obstacle determination and avoidance, pedestrian detection, and object movements, to be able to take actions governed by the “brain” of autonomous driving system to achieve active functionalities of braking, steering, accelerating and so on.

Maps and navigation data is another important input to the “brain” to enable fully autonomous journey from point to point and is also required to achieve functionalities like merging on highway merging, exit and interchanges on highway.


Future Solutions

"The electric light did not come from the continuous improvement of candles."

What is beeing done different in Autonomous Driving?

We are using deep learning based approach to teach our system to drive autonomously.

The “brain” of our autonomous driving system takes inputs from various sensors on a vehicle, maps and navigation data, external sensors and information, to control the complete powertrain and all other control aspects to drive the vehicle autonomously and safely. Our system observes and learns from human drivers until it is mature to start driving autonomously on its own.

We believe that the power of such deep learning based approach is the ability to handle corner cases that are hard to tackle using traditional algorithms.