Tag: mobility

AI is always faced with challenges when it comes to evaluating images

What seems logical and clear to people in pictures, can be a huge challenge for artificial intelligence.

Image noise and knowledge logic require new solutions

Basically, two subject areas pose more or less major problems for artificial intelligence in image evaluation. This is the aleatory (random noise on objects) and the epistemic model.

Epistemic logic is one example, when Artificial Intelligence cannot distinguish a street from the sidewalk next to it, because both elements are made of asphalt.

In 3D recordings, this can perhaps be solved through the third dimension. However, such image sources are always available? Probably only in very few cases.

Live evaluation in autonomous driving is still not possible due to a lack of computing power and a certain level of uncertainty, the 3. dimension in this fineness.

In general, this problem can be solved in the learning phase, if you provide the system with further data and the algorithm approaches it with probabilities, that in our example there is a sidewalk next to the road.

When it ultimately comes down to human safety, objects and machines, Probabilities alone are a poor solution.
In such a sensitive environment, further safeguards must be installed. Whether it's radar electronics or distance sensors, must be tested in case of doubt.

For pure image recognition such as X-rays or similar, The algorithm can only be kept under control through an extended learning phase.

Aleatorics easier to solve

The random noise in images (Random) In many cases, this can be contained with higher resolutions. But there is also something to consider, that this can also trigger other sources of error. If the accuracy is too high, you can create new problem areas – depending on the available image material.

For explanation: In aleatorics, blur does not mean the entire image, but the demarcation of objects from one another. A traffic light or a tree trunk can be perceived by the software as jagged or stepped. No problem for a human, However, it is a disruptive factor that should not be underestimated for the program logic.

If there is enough computing power available, The most elegant solution is often to solve the aleatorics in software. With the help of artificial intelligence and an extensive learning phase, image noise can be minimized.

Instinctive actions only under laboratory conditions

Both subject areas are particularly important in the mobility industry. Heavy rain or even snowfall have so far been difficult problems for image recognition in the field of artificial intelligence. For humans it is instinctively clear, that a snowflake on the window or on a sensor does not pose a dilemma – What and how can you prevent artificial intelligence in an autonomous vehicle?, in this case, initiate emergency braking.

Based on my current knowledge, ultimately only a combination of several systems will ensure safe movement. Until artificial intelligence is ready and can reliably interpret human instincts in traffic, years will pass.

When aleatorics and the problems of the epistemic logic of knowledge are solved, is a huge step towards fully autonomous regional driving- and long-distance train done. In contrast to road traffic, the rules and sources of error in rail traffic are more manageable.

Complexity should not be underestimated

I am aware, that the topic is much more complex. To introduce laypeople to the topic, I allowed myself, only the most serious construction sites need to be mentioned.

Artificial intelligence manages charging stations for electric cars

Artificial intelligence - Electric car
Artificial intelligence – Electric car

Public charging stations will be the fuel pumps for electric cars on longer tours. AI already supports the driver in certain areas.

Modern cars – u. a. of the Mercedes EQC – provide the driver with a route in the integrated navigation system with charging stations close to their route. A great thing!

Is this charging station free on arrival? This question remains unanswered and is a matter of luck. The next step has to be, that you can reserve the charging station fully automatically for your arrival. The arrival time can be calculated quite precisely by the navigation system, taking into account the current traffic situation.

Charging times can also be calculated taking into account the individual parameters, so that time management can take place for each charging point. Networking can avoid long downtimes.

This is technically feasible without great effort. One obstacle is so far, that loaded cars often stay longer than necessary at the stations.

The first step is to notify drivers of the end of the charging process via text message. Who doesn't make room for the next one within a certain period of time, must expect additional costs.

Manufacturer-independent management necessary

Requirement for planning, Reservation and implementation of the vision is a central point, which manages all public charging stations regardless of manufacturer.

To offer the driver the greatest possible comfort, a form of billing must be found, which is modern and transparent.

Whether the billing takes place directly with the driver or an institution – Car manufacturer or automobile club – is interposed, can be set individually.

Build charging stations with common sense

My hair stands on end, when i hear, what a high number of charging stations in public spaces (allegedly) are necessary, to ensure an adequate supply.

According to an article in Handelsblatt (15.04.2019) require experts “until 2030 all in all 600.000 Charging points in public spaces, a million at the workplaces as well 10.000 Fast charging stations mainly at motorway service stations”.

14.000 We have petrol stations with approx. 160.000 Gas pumps

14.118 Gas stations (Stand: 2018) are currently available in Germany – unconfirmed information according to a total of approx. 140.000 – 160.000 Fuel pumps. At over 80 My. Vehicles with diesel / gasoline engines.

Even if the charging process for electric cars takes longer and it does 2030 7 My. planned e-cars, it will be a disaster over economically 600.000 set up public charging points.

Sufficient according to more realistic estimates 350.000 Charging points in parking lots in shopping centers, Leisure facilities as well as the envisaged 10.000 Fast charging points are completely out of the question, mainly near motorways.

Outside of the holiday season, very few people drive in one go beyond the average range of 400 km of an electric car.

Mobile charging stations bridge bottlenecks

During the holiday periods, mobile fast charging stations can be found at truck stops, Avoid service areas and bottlenecks along the transport hubs. Mobile charging stations in exhibition car parks and other event locations such as festivals or concerts are also an issue.

With a healthy basic supply where the action is (job, purchasing, leisure) Isn't it economic madness to provide an abundance of cheap infrastructure.

Artificial intelligence can be of great help in choosing and operating suitable locations.

I see them too 1 My. required charging stations in companies are critical.
Many employees live within a radius of 20 km around the place of residence and on the other hand is the job market – also thanks to artificial intelligence – so changing, that in a few years many jobs in factories will disappear and more and more home workplaces (Homeoffice) develop.

From today's perspective, the number may be correct, but by the end of this decade a far lower number is necessary.

Artificial intelligence protects against car breakdowns

Transparent automobile factories are no longer new. The digital supply chains in the automotive industry are also state-of-the-art – of what is currently possible.
There are already more or less serious visions of this. Even in this decade, cars in deserted factories will only be driven by robots – combined with artificial intelligence – getting produced. The goal is clearly error-free and faster assembly.

My thoughts in this article revolve around the technical integration of individual vehicle parameters into daily use.

Whether warning or tips, In practice everything can be shown on the display or heap up.

Even an automobile only has one life

It may sound childish, You can also do an EKG on a car. Even permanently!
The data is already recorded internally in the car today. Unlike a human, There is no need to create an interface between the real and digital world using a cuff or heart rate monitor. The data is already available digitally. Best conditions for the next step.

Unlike human life, death in machines is more predictable and therefore can be planned. On the other hand, mechanical death can also be prevented.

Thanks to artificial intelligence, this is not a new discovery! The idea is new, that the vehicle data – anonymous or assignable – can be sent live to the automobile manufacturer in G5 status using digital networking.

Real-time evaluation is easy

In times of quantum computers, it is easy to compare parameters in real time and then intervene in a warning manner, when the computer sees, that this development led to engine damage in another car of this series.

May sound simple, but the inclusion of outside temperature and terrain are things, which must be taken into account for a serious presentation.

High engine temperatures and high oil pressure are warning signs on the highway, in a car – possibly even with a heavy caravan in tow – However, completely normal on the mountain road.

It is therefore essential to include the situation before entering the current state in the situation assessment.

Anyone who always drives carefully and the sensors suddenly transmit abnormal vehicle values, should be warned differently than if a person drives his car at the limit every day and extends the engine to the rev limiter.

Every automobile has enough warning lights on board, These already flash well in dangerous situations without artificial intelligence.

However, through the transmission and permanent situation assessment, the decision in the digital control center is compared with similar data from other cars.

Artificial intelligence protects people and machines

When artificial intelligence comes to the conclusion, that there is an acute danger to people and machines, This can be displayed to the driver, including a request to switch off the engine immediately.

Forced external intervention should be avoided as far as possible, because the situation on site is unknown to the control center: Car in the fast lane, Driver may panic during forced stop, are just a few thoughts, who speak against it.

Rather, the data should be used to provide the driver with a suitable workshop and suggested appointment if necessary. If you then have the right spare part ready for the appointment, Artificial intelligence makes life easier. With such convenience, technology will receive a lot of recognition.

AI to combat cold winter days from empty car batteries

Probably nobody has anything against it, if the emptying or. aging batteries are replaced. Nothing is worse than when your car refuses to start on a cold morning.

To be honest, in the first step it has little to do with artificial intelligence. The measurements are based on sensor data.
First the processing, the comparison and correct interpretation of these digital values, brings artificial intelligence into play.

Artificial intelligence can reduce aircraft landing aborts

When artificial intelligence makes your landing safer, you are there?

You hear about it almost every day in the media, that aircraft have to take off on approach and usually after a traffic pattern (“Lap of honor”) prepare to land again.

This process is absolutely normal and even increases security. Nothing would be worse than a plane touching down on the runway at an angle or too late. The consequences would be catastrophic.

Of course, aborted landings cost kerosene and a lot of time – In addition to yours, also the time of the ground staff. Quite apart from that, that the flight plans get mixed up.

AI can recognize behavioral patterns

It would be very interesting to research landing aborts with artificial intelligence: not to attack the pilots or an airline
to be pilloried for poor training, but simply to find out under what conditions, most terminations occur.

When comes out, that certain weather- and/or wind conditions increase the number of aborts, This is how you can take specific action against it – warn the pilots or choose other approach routes.

Artificial intelligence can therefore help reduce landing aborts in the future. In addition to the factors mentioned above, the environment is also protected.

Of course, landings will always remain a challenge for people and machines.
When AI is additionally integrated into the decision-making process, is not just helpful for passengers.

The acceptance of the new technology is increased within a very short time through such popular measures.

Artificial intelligence is a hot topic

On the one hand, it's beautiful, that artificial intelligence is on everyone's lips, But with improper reporting, a lot of good things are ruined. On the one hand, this is due to unqualified journalists and, of course, also to populist interpretations of the technology.

AI is already saving many lives in the background today! As already mentioned in another article, is the strong AI – Robots with human behavior – still miles away from reality.

Only in Hollywood have robots already defeated humanity. congratulations!

If you become aware, that not even biologists agree, how the human brain works in detail, so you can sit back and relax. As long as human behavior cannot be explained, You can't teach this to a robot.