In Peter Phleps’s talk, he came up with several new concepts while summarizing and predicting what is going to happen in the future. Firstly, he mentioned autonomous vehicles not only facilitate the life of the elderly and the handicapped, but also people, he called, “super-commuters”, by which he means people could have more working space and time during their commuting. Therefore fluent working process will be guaranteed seamlessly. Secondly, he said more car ride sharing could be widely used and living rhythms would be more efficient for urban people. Afterwards, several drawbacks were mentioned, for example congestion and the number of cars will be increased due to the easy access and controls of cars. Finally, he summarized the whole presentation by going back to the old question: Could autonomous vehicles be morally accepted by people? Actually, we do believe autonomous vehicles are always technically feasible, however, what is in the way is that if they are desirable to all the relevant people. So, it can be a brand-new topic for Beyond Engineering in Group T
It will be really good for the engineers to know exactly about all the information of all the vehicles on the road so the autonomous vehicles can drive much safer and much energy efficient. But what kind of security level should this information be.
Remind that when there are autonomous vehicles, the smart technology in the vehicle will not only have the information of the vehicle parameters only. Information like which websites you were surfing when you drive, how many tickets you got from the policeman for the last month,what kind of the stores you shopped, the clubs and the restaurants you went can all be gathered from your vehicle. This information from your vehicles is very valuable to the advertising companies. You will receive more specific ads as a results. Good or bad, I can’t say.
If you want cheat your wife and hook up with hot girls, take care of your vehicles! Your wife will know that.
Also, what if hackers hack into your vehicle control system? This kind of murder is even hard for Sherlock.
Before we talk about our vehicles, let’s see what’s happening when we have other “smart” technologies. Before the smart phones get popular in China, I can still remember when family gathered together and had a nice conversation with each other. But thanks to smart phones, more and more people are almost “controlled” by their phones.
The same thing may happen for autonomous vehicles. When the vehicle is autonomous, people may stay more inside their vehicles, and vehicles may become so important that almost becomes their “home”. When this technology becomes so advanced, you don’t need to drive your children to school and you vehicle is able to do that. But is that good? As the technology is becoming more and more dominant in our life, the face-to-face social life is becoming less and less. If we accept this technology, we have to accept everything it will bring.
For now, the vehicles are still the most dangerous way to travel, when compared to the train and airplane. There are always some drivers they are not really reliable. Maybe they are just careless, they are drunk or just because they are not really good at driving. If you meet the emergency situations, an experienced driver may take some special actions to avoid accident. But these things are too “strange” and difficult to handle because of the unpredictability of these careless drivers.
So in conclusion, if you want to have the autonomous vehicles and human driving vehicles together on the road, the human drivers must also change a little bit and reach a higher level.
That’s another challenge may make the driver license harder to get.
Even if the technology and law are all ok for the autonomous vehicles, the complex road condition can still be a problem. When it’s icy on the road, the vehicle may have some difficulties detecting these icy areas. The same goes for the sudden changes of the road. For example, the storm causes trees on the road, or traffic accident just happened in the front. So information must be updated as soon as possible.
Also because the driver may be sleeping and the computer is driving the vehicle, it may be hard to have the gesture communication. For example, if you are riding your bicycle, and point your hand at left side showing you are going to turn left. The autonomous vehicles are not able to recognize your gestures (That’s too challenge for the computer). It’s not also feasible for the policeman to use gesture to ask the driver to pull over.
As known, autonomous vehicles have to run themselves in an optimal way (time-optimal, energy optimal…). With the rapid development of modern optimization techniques, the way to make vehicles smart and autonomous has been more and more.Take time-optimal problems as an example (going from point A to point B with least time spent), we have following available algorithms to specify the optimal control profiles (velocity profile or acceleration profile).
1. Genetic algorithms.
Different velocity combinations behave like genes, they belong to different chromosomes and they exchange genes with a certain rate of mutation. In this way numerous combinations can be found and tried on the model by computers until the one combination which makes time least is found.
2.Particle Swarm Optimization
Different combinations of velocities (the solution of the optimization problem) are represented as dots which are flying at certain velocity and altitude in 3D space. The velocity and altitude of each of these dots will be influenced by other dots, and the way they influence each other is towards the direction of optimization. Therefore, every velocity combination will be tried on the internal model until the optimal one found.
The common thing that these two algorithms share is that they have a mechanism of “mutation” to make sure the velocity combinations are diverse so that they can find a global optimal solution instead of a local one. With the same principle, there are more similar algorithms.
This one is really a part of artificial intelligence because it makes vehicles behave like human beings! Just like ourselves, we have the complete neuronetwork around our body so we can feel the surroundings and make decisions based on these feelings. And we tend to make more correct decisions with the feeling experience accumulated. Cars can be like this as well! We can teach them to feel the surroundings, to try different actions , and when they grow up, they will behave in a more and more smart way! Just like the growth of children!
Firstly, we would like to wish everyone a happy new year!
The past year was a great year for autonomous vehicles, during which many car manufactures launched their research plan on autonomous vehicles. As such, it is likely that nearly all cars are expected to be autonomous by 2050.
Here comes a small summary of what major manufacturers did during the past year,
Audi launched its research plan last January and obtained the first license for self-driving cars in Nevada. What’s in particular in this case is that it is also a big step of laws concerned about autonomous vehicles.
Ford debuted a fusion hybrid autonomous research vehicle which means the first combination of green vehicles and “smart” autonomous vehicles.
Tesla expressed its openness to autonomous working fields as the CEO announced in September that “engineers interested in working on autonomous driving should email Tesla”.
Volvo even launched a pilot project which will unleash a fleet of 100 self-driving Volvos onto about 30 miles of busy roadways around its home city Gothenburg, Sweden.
Knowing that laws and liability issues are the biggest hurdle to let autonomous vehicles be accepted by users, we will still need to wait for some breakthroughs in ethical aspects while technologies are rapidly developed. Hopefully, we will already have numerous autonomous vehicles running on streets.