The Jaxson

Community => Transportation, Mass Transit & Infrastructure => Topic started by: Ocklawaha on March 07, 2019, 02:40:16 PM

Title: SELF DRIVING BUSES - JTA's Newest Problem?
Post by: Ocklawaha on March 07, 2019, 02:40:16 PM
Volvo Buses and Nanyang Technological University (NTU) in Singapore have demonstrated the world’s first 40-foot autonomous electric bus. The Volvo bus will soon begin trials on the NTU campus.

The bus is equipped with four Lidar sensors, which enables it to detect and stop for objects coming in its way.
The 85-passenger Volvo 7900 Electric bus is equipped with sensors and navigation controls that are managed by a comprehensive artificial intelligence (AI) system. Ensuring maximum safety and reliability, the AI system is also protected with cyber-security measures to prevent unwanted intrusions.
The Volvo bus has undergone preliminary rounds of rigorous testing at the Centre of Excellence for Testing and Research of Autonomous vehicles (CETRAN).

The list of concerns about self-driving cars JTA buses just got longer.
In addition to worrying about how safe they are, how they’d handle tricky moral trade-offs on the road, and how they might make traffic worse, we also need to worry about how they could harm people of color.

If you’re a person with dark skin, you may be more likely than your white friends to get hit by a self-driving bus, according to a new study out of the Georgia Institute of Technology. That’s because automated vehicles may be better at detecting pedestrians with lighter skin tones.
The authors of the study started out with a simple question: How accurately do state-of-the-art object-detection models, like those used by self-driving cars and buses, detect people from different demographic groups? To find out, they looked at a large dataset of images that contain pedestrians. They divided up the people using the Fitzpatrick scale, a system for classifying human skin tones from light to dark.
The researchers then analyzed how often the models correctly detected the presence of people in the light-skinned group versus how often they got it right with people in the dark-skinned group.

The result? Detection was five percentage points less accurate, on average, for the dark-skinned group. That disparity persisted even when researchers controlled for variables like the time of day in images or the occasionally obstructed view of pedestrians.
Title: Re: SELF DRIVING BUSES - JTA's Newest Problem?
Post by: bl8jaxnative on March 10, 2019, 12:30:51 PM
I was going to mention the recent study on skin color.   

I love the idea of robobuses in the abstract.  Wonderful.  The problem is that there's a shit ton of things the human brain is doing when operating a vehicle.    There are a shit ton of problems that need to be resolved before letting robobuses onto our streets.


The question is, what is JTA's plan B?  They're coming up on the end of life of their current Skyway fleet FAST.
Title: Re: SELF DRIVING BUSES - JTA's Newest Problem?
Post by: thelakelander on March 10, 2019, 01:28:50 PM
I don't think they do have a plan B. Thanks for posting the study link!
Title: Re: SELF DRIVING BUSES - JTA's Newest Problem?
Post by: KenFSU on March 14, 2019, 07:28:33 PM
Hopefully JTA is paying attention to the Boeing 737 Max story.

Is 2019 the right time to hedge our entire urban transportation future on software-driven autonomous vehicles?

One bug or glitch can and will shut the entire network down for weeks or months at a time.
Title: Re: SELF DRIVING BUSES - JTA's Newest Problem?
Post by: bl8jaxnative on March 16, 2019, 11:03:05 AM

Can you imagine being in one of those robobuses as it drives off the bridge into the St. Johns River?
Title: Re: SELF DRIVING BUSES - JTA's Newest Problem?
Post by: KenFSU on March 16, 2019, 11:27:37 AM
Bold/not bold prediction:

Whenever JTA's new Skyway system opens, it will be on the existing elevated tracks only.

No universe where this thing is ready to operate in mixed traffic in three years, and no universe where you can safely mix the vehicles described by JTA into traffic coming off the Hart Bridge with the configuration described earlier this week.

We're going to end up with a less efficient replacement for what's already there, with the same limitations in terms of system coverage.