Skip to main content

Assignment II: Technological

The technologies of autonomous vehicles


I. The technologies:

The Autonomous vehicles (AVs) are equipped with these technologies:
  • Cameras: they are used to monitor the traffic, other vehicles, barriers,...
  • Ultra-Sonic Sensors: Imitating the navigation process of bats, ultrasonic sensors send out sound waves. When the waves hit an object they produce echoes – revealing the exact location of the obstacle
  • GPS: GPS or Global Positioning System is a network of orbiting satellites that send precise details of their position in space back to earth. The signals are obtained by GPS receivers, such as navigation devices and are used to calculate the exact position, speed and time at the vehicles location.
  • Infrared: It's used at night to detect moving objects.
  • Lidar Sensors: Light Detection and Ranging (LIDAR) sensors scan the environment with a non-visible laser beam. The low intensity, non-harmful beam visualizes objects and measures ranges- creating a 3D image of the car's environment.
  • Radar Sensors: Known from ship and plane navigation, Radio Detection and Ranging (Radar) sensors send out electromagnetic waves. If they hit an obstacle, they waves are reflected, revealing how far away an object is and how fast it is approaching. 
  • Clouds: The clouds serve as a dynamic electronic horizon – it offers highly accurate real-time map data that vehicles draw on. The data will be constantly updated thanks to the collective intelligence of the vehicles, for instance, reporting closed lanes or defective traffic lights – therefore it also is a type of sensor, providing the AV of its surrounding.

II. Details for Clouds:

Autonomous vehicles require intensive parallel computation cycles to process sensors’ data and efficient path planning in the real-world environment. It is certainly not practical to deploy massive onboard computing power with each agent of autonomous vehicle. Such deployments will be cost-intensive and may have certain limitations in parallel processing. Cloud provides massively parallel on demand computation, up to the computing power of super computers, which was previously not possible in standalone on board implementations. Nowadays, a wide range of commercial sources (including Amazon’s EC2, Microsoft’s Azure and Google’s Compute Engine) are available for cloud computing services, with the aim to provide access to tens of thousands of processors for on-demand computing tasks. Initially, web/mobile apps developers used such services; however, they have increasingly been used in technical high-performance applications. Cloud computing can be used for computationally extensive tasks, such as to find out uncertainties in models, sensing and controls, analysis of videos and images, generate rapidly growing graphs (e.g. RRT*) and mapping, etc. . Many applications require real-time processing of computational tasks, in such applications cloud can be prone to varying network latency and quality of service (QoS), and this has been an active research area nowadays.

III. References:

- Here is how the sensors in autonomous cars work: http://www.thedrive.com/tech/8657/heres-how-the-sensors-in-autonomous-cars-work

Comments

Post a Comment

Popular posts from this blog

Assignment I: Introduction to Autonomous veihicle

Introduction to Autonomous Vehicle I. Six levels of Autonomous Vehicle There are 6 levels of Autonomous Vehicle: Level 0: No Automation : Driver has to control all the system on their own and receive no support from the system Level 1: Driver Assistance : Driver receives assist from either steering or acceleration/deceleration using the information from about the driving environment. Level 2: Partial Automation :  Both steering and acceleration/deceleration will be controlled by the system. Driver still has to perform all remaining aspects of the driving task. Level 3: Conditional Automation : Automated driving system can now perform all aspects of the driving task but still need the control from the driver when needed. Level 4: High Automation : Performance by an automated driving system of all aspects of the driving task, even if a human driver does not respond appropriately to a system request or warning for human intervention. (deliver the capability in a defined
Post a Comment
Read more

Assignment VI: Social

Social This is the result I got after interviewed with 10 people. Questions: 1) Do you drive a car? Why or why not? 2) Are you interested in having an autonomous vehicle? Why or why not? 3) In your opinion, what is the biggest challenge that the autonomous vehicle is facing? First question's result: Do you drive a car? People I asked are mostly either student or foreigners. For student, they can't afford a car at this moment while they are still studying, but most of them have the plan to switch to a car when they had a proper job and got enough money for a car. With foreigners, most of they used to have a car when they were still in the others country (Germany, Canada,....) but after coming to Vietnam, the traffic here is not suitable for the car, so they switch to a motobike for convenience. Second question's result: Are you interested in having a autonomous vehicle? Most of them want to have an autonomous vehicle and actually, some was very excite
Post a Comment
Read more

Assignment V: Law

Basic Assignment On Law Self-driving cars are very new, and like all other technologies, the law always comes after it. As we can see in the picture above, there are just a few states in USA created and approved the law for self-driving cars, so many other states are still developing it and even some of them were failed to approve the law, also a a lot of states are not even considering for making the law for the self-driving cars. So it will need a very long time until all the states conduct and announcing a completed law for the autonomous vehicles. So, allowing the self-driving cars to travel around the world now is significantly dangerous, especially for human life. When there is an accident happened, it would be very hard to determine who will take the responsibility for it, every harder on the countries that haven't provided the law for self-driving cars yet. Next, without a full set of law, there will be no clear standards for the manufacturers to make t
Post a Comment
Read more