網誌

CDIO ACADEMY 2017#6 – Social

 

Like any new technology, autonomous vehicles are going to experience some pushback from the public. This may be because individuals feel uninformed, or they might simply enjoy being in control of their own vehicle!

Questions:

Do you drive a vehicle? Why or why not?
Would you be interested in having an autonomous vehicle? Why or why not?

Results:

Screen Shot 2017-06-14 at 22.16.30Screen Shot 2017-06-14 at 22.16.42

Conclusion:

Most people that I asked do not have a car, and that was because eighty percent of them are still in college.The reason they did not buy is beacuse they do not have enough money. However, when it comes to the interest of autonomous vehicles, most people do want to have a try. That shows us that there is still great potential for driveless car for people. People are looking forward to how the driveless car add color to their daily lives.

CDIO ACADEMY 2017#5 – Law

The legal issues involving autonomous vehicles.

There are quite a few issues among autonomous vehicles. Not all the states’ laws keep up with the technology. Up to 2014, only six states pass the regulation for autonomous vehicles, on the contrary, fiften states had failed and eighteen states are still pending. That means regulations for autonomous are not truly mature. Lots of challenges stand in front of the regulation.First, who should take the responsibility when an accident occurs? The driver or the manufacturer?  And how if the driver get to control  the car, should the driver take all the responsibility? (As we know, when you sit on driveless car you do not put full attention on the traffic ). I believe that it still takes time for governments to enact more delicate laws.

resources: http://self-driving-car-legislation.silk.co/

CDIO ACADEMY 2017#4 – Personality and Teamwork

1.Do you feel that this report accurately reflects your personality? What do you find most / least accurate?

I think that this report is eighty percent correct. In addition, the most correct accurate is Extraversion. I am quite a out-going person, and the report did truly reflect my personality.On the contrary, the least accurate is the self-disipline part, because sometimes I might procrastinate.

2.What traits stand out as being helpful for working with others and why?

My AGREEABLENESS part stands out and it can help me work with others.
Cooperation, modesty, trust three personalities help me to work well with my teammates.

I do not actively seek out confrontation but I also do not shy away from it.I have a healthy amount of self-respect and are reasonably proud of my accomplishments.I am very trusting of others and believe that everyone will follow through on commitments.

Those personalities help me to work properly with my teammates.

3.What traits stand out as preventing you from working well with others and why?

I enjoy having theoretical discussions and thinking about abstract ideas. This tendency to challenge myrself can help me to improve me understanding and critical reasoning. I might get too caught up in examining ideas that it prevents me from accomplishing simple but important deliverables.

4.What traits do you think could benefit you working alone but could harm you working in a team? With this knowledge, how could you adjust when working in a team?

Same as question 3.

I enjoy having theoretical discussions and thinking about abstract ideas. This tendency to challenge myrself can help me to improve me understanding and critical reasoning.
However, I might get too caught up in examining ideas that it prevents me from accomplishing simple but important deliverables.

The solution to this issue is that I should adjust myself not to dig too deep to one’s question but to think that one’s opinion whether it is suitable for the answers.

 

CDIO ACADEMY 2017#3 – Ethical

When an autonomous vehicle crashes or has an accident of some sort – who is responsible, and to what degree? Consider the following story:

Alice buys an autonomous vehicle from Bob, who sells them. The autonomous vehicle has different settings, some more aggressive (where the autonomous vehicle drives faster and brakes harder), and some less. Alice sets the autonomous vehicle to its most aggressive setting. One night on a dark and wet road, Alice hits a pedestrian, Carlos, who was jaywalking. Carlos is badly hurt.

How should we divide up the responsibility for Carlos’ injury? Here are some immediate suspects: Alice, since she was the owner of the autonomous vehicle, and was using it at the time of the accident; Carlos, who was in the road when he shouldn’t have been; Bob, who sold Alice a car that had the aggressive setting(s).

Perhaps there are some other possible responsible parties as well. For example, we might consider the state (the government) that allows the autonomous vehicle on the roads, to be partly responsible. Or we might think that the autonomous vehicle manufacturers are partly responsible, in that they made the autonomous vehicle with the aggressive settings. Or we might think that the autonomous vehicle itself is partly responsible, since it is somewhat autonomous. Or we might think that the accident was a freak occurrence that no-one is responsible for.

In a blog post of 300-400 words, consider who the parties responsible for Carlos’ injuries are, and why they are so responsible. Given your assessment, what advice might you give to the manufacturers, owners or regulators of AVs to help address these types of issues?

1.Carol should take most of the responsibility(80 percent). The reason is that he jagwalked on the wet road on dark night which was easier to cause car accidents.He did not obey the law so when he was hit, he should take most of the responsibility. On the other hand, Alice should take part of the responsibility(20 percent). The reason is that she chose the most aggressive setting, which put the vehicle into higher risky conditions. If she chose the less aggressive setting, the vehicle may have more time to react, and accidents might not happen.

2.My advices:

(1)For regulations of AVs:
AVs regulation must rule the responsibility between the vehicle manufacturers and the car owners. Manufacturers should design settings for car owners to choose and they should tell owners what will happen in different setting cases. Owners need to know what settings they choose and take 80 percent of the responsibility they decided. (20 percent is for manufacturers.) Besides, the regulation should be practiced strictly to make sure people truly obey.

(2)For manufacturers:
Vehicles should be tested more carefully.Vehicles need to test on road at least for three year in order to collect sufficient data of accidents. In addition, solutions need to be well-prepared when the vehicles come to the similar conditions. For ethical problems, settings should designed  as selections for the car owners to make decision by themselves in order to make sure the drivers know what will happen when accidents occur.Last but not least, setting instructions should be told to the vehicle owners to make sure they know what responsibility to take care of.

(3)For owners:
Bear in mind the responsibility to take between different settings. Do notice what occurence will happen at the settings as car drivers choose in order not to know nothing when accidents occur.

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

(1)Hardware(sensors):

A.Cameras:
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.

C.Sonar:
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.

D.Gps:
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.

B.self-parking:
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

E.autopilot:
The vehicle is controlled by the computer system.

(3)Machine Learning

1.https://www.quora.com/How-does-Teslas-Autopilot-work-What-are-the-sensors-that-it-uses
2.http://www.telegraph.co.uk/cars/features/how-do-driverless-cars-work/
3.https://www.quora.com/Why-do-cars-use-sonar-sensing-technology-instead-of-radar-for-short-distances

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

(2)Benefits:
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

(3)Drawbacks:
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.

1.https://www.dropbox.com/s/gmgmnskg4tw6mmx/lecture1.pdf?dl=1

 


 

CDIO ACADEMY 2017#1 – Introduction

1.  SAE International has a formal classification system for autonomous vehicles, ranging from level 0 (not automated) to level 5 (fully automated). Briefly describe each of the levels.
Screen Shot 2017-05-04 at 20.19.45

http://cyberlaw.stanford.edu/blog/2013/12/sae-levels-driving-automation

level 0 : All human operate.
level 1 : Automated system either steering or acceleration.
level 2 : System operate both steering and acceleration.
level 3 : System take care all dynamics driving task,(including steering, acceleration, and mointoring the environment)but expect people to response.
level 4 : System take care all dynamics driving task,(including steering, acceleration, and mointoring the environment) even people don’t response.
level 5 : System act as driver.

2.  Use the internet to find at least two examples of autonomous vehicles that already exist. Which companies/universities/groups are they from? What autonomous behaviour do they exhibit (i.e., can parallel park itself, can drive itself)? How have they been tested?

(1)Chrysler Pacifica Hybrid minivans–from Google .According to their websites, as Google depicts their vehicle functions:"Our sensors observe that the cyclist has extended their left arm. Detecting the cyclist’s hand signal, our software predicts that the cyclist will move to the left side of the lane."That is to say, They can steer, accelerate,mointor the environment themselves.Tested on road.

(2)Tesla self driving car from Tesla.They can drive themselves.Tested on road.
Tesla self driving car demostration

3.  Consider the SAE classifications from the question 1. At which level would each of the vehicles discussed in question 2 be? Provide rationale for your decisions.

(1)Chrysler Pacifica Hybrid minivans is at level 5. Because it can steer, accelerate,mointor the environment all by themselves
(2)Tesla self driving car is at level 5. Because it can steer, accelerate,mointor the environment all by themselves

4.  Please state at least 3 possible applications for autonomous vehicles, and why they would be beneficial for those applications.

(1)Prevent alcohol driving. Because people won’t drive even when they are drunk.

(2)People can rest on the car. If people are tired, they can take time to sleep during the car trip.

(3)To minimize humon errors. A lot of car accidents occurred owing to human’s wrong decision, the autonomus vehicles can prevent it from happening