How to play trick with Autonomous Vehicle? & “V2V”Communication Experiment (No.1)
A car is sitting in the middle of a parking lot has been surrounded by a circle. In the language of road markings, the dotted white lines on the outside say, "Come On In," but the solid white line on the inside says, "Do Not Cross." To the car's built-in cameras, these are indomitable laws of magic for autonomous automobiles.
In this case, the circle being used to arrest an autonomous vehicle—a self-driving car, which relies on machine vision and processing to guide it. By quickly deploying the expected form of road markings—in this case, a No Entry glyph—we can confuse the car's vision system into believing it's surrounded by no entry points, and entrap it
Here is a particular scenario. A blue autonomous vehicle is running on the highway, your car is running behind it. Suddenly, the front truck dropped some obstacles. In this case, by law, the autonomous car is not allowed use the HOV Lane and across the solid line, but the right side has another car so the autonomous car can’t merge to the right lane either. It has to break and stop on the highway!
This is your view in your car when the emergency happens, you can’t see what’s happening in front of the autonomous vehicle. When you find the breaking signal from the autonomous vehicle, it’s too late to slow down.
In this scenario, what if there is a non-autonomous vehicle running in front of you and meet this situation? Might be merging to the HOV Lane and you can avoid the potential car crash or highway congestion.
It makes me think unless we have a dedicated lane for autonomous vehicle or until all the vehicles are replaced by the autonomous vehicle, human drivers have to face the future that we need to share the road with them. But how do I know what types vehicles running surround me? What are autonomous vehicles intentions, can they handle all the traffic situation? How do human drivers set up their expectation?
Through analyzing the cybernetics workflow, when autonomous vehicle detected there are obstacles ahead, central computer quickly analyzing the situation then breaking. Human driver observed the front car breaking signal and slowing down. Since because of the workflow, we need to consider human driver’s reaction time.It will cause the potential car crash.
Based on those questions above, my hypothesis is car recognition and “V2V” intention communication is a way to reduce this concern and correct the expectation from a human driver.
“V2V” communication will better solve the problem, we can easily find the different from the refined cybernetics workflow. When the autonomous vehicle’s central computer decide to break, it will also send the signal to the car behind, human driver’s car will automatically breaking at the same time. Reduce the human driver’s reaction time, in this case, the entire traffic system will coordinate in one disturbance.
Beyond that, human driver will be informed by visual information which overlaid on the windshield and rendered on the dashboard. It is necessary to know what’s happening in their own car to reduce the confusion and concern.