CDIO ACADEMY 2017#2 – Technological 

Autonomous vehicles are packed with technology. There is a wide variety of sensing and control technology used, including cameras, lidar, GPS, infrared, and others.

        The different types of technology that may be found in autonomous vehicles


Video cameras detect traffic lights, read road signs and keep track of other vehicles, while also looking out for pedestrians and other obstacles.

B.Radar(Long/Medium/Short-range radar):
Radar sensors dotted around the car monitor the position of vehicles nearby.

Radar uses radio waves that have a much longer wavelength compares to sound waves used in sonar. This waves with smaller wavelength gives more accuracy at shorter ranges while radar is more suitable for detecting obstacles at a large distance like in air or underwater as sound does not have enough energy or enough speed to do the round trip.In addition, ultrasonic transducers cost only a few dollars each, while radar units are much more expensive.

A global navigation satellite system that provides geolocation and time information to a GPS receiver.

E.Lidar (laser scan):
Lidar sensors help to detect the edges of roads and identify lane markings by bouncing pulses of light off the car’s surroundings.



(2)Software(combined with hardware):

A.emergency braking prior to a rear-end collision:
Vehicles system connected with sensors pull the brake as it detected that the potential of car collision.

The car park itself without human control.

C.lane-keeping assist:
To alert the driver when the system detects that the vehicle is about to deviate from a traffic lane

D.rollover prevention:
A system that recognizes impending rollover and selectively applies brakes to resist

The vehicle is controlled by the computer system.

(3)Machine Learning


2. Select one type of technology and look at it in greater detail. How is it currently being used? What are its benefits and drawbacks? What is its future potential? Don’t forget to include references to any sources you may have used.

Machine Learning on vehicles


(1)How is it currently being used?

A.It learns by observation most of the time, logging the behavior of the human drivers over a stretch of road while Autopilot is disengaged.
B.It learns by reinforcement in scenarios when Autopilot is engaged

A.less human errors
Human performance: 1 fatality per 100,000,000 miles
Error rate: for AI to improve on: 0.000001%

B.self corrected

A.Lacks Reasoning:
e.g.Humans only need simple instructions: “You’re in control of a paddle and you can move it up and down, and your task is to bounce the ball past the other player controlled by AI.”
B.Requires big data: inefficient at learning from data
C.Requires supervised data: costly to annotate real-world data

(4)Future potential:
A.Ilya Sutskever, Research Director of OpenAI:
Deeper models, models that need fewer examples for training.

B.Christian Szegedy, Senior Research Scientist at Google:
Become so efficient that they will be able to run on cheap mobile devices.

C.Pieter Abbeel, Associate Professor in Computer Science at UC Berkeley:
Significant advances in deep unsupervised learning and deep reinforcement learning.





在下方填入你的資料或按右方圖示以社群網站登入: 標誌

您的留言將使用 帳號。 登出 /  變更 )

Google photo

您的留言將使用 Google 帳號。 登出 /  變更 )

Twitter picture

您的留言將使用 Twitter 帳號。 登出 /  變更 )


您的留言將使用 Facebook 帳號。 登出 /  變更 )

連結到 %s