Driverless autos, trucks, taxis etc. Message Board

STOCKTALK

We've detected that you're using an ad content blocking browser plug-in or feature. Ads provide a critical source of revenue to the continued operation of Silicon Investor. We ask that you disable ad blocking while on Silicon Investor in the best interests of our community. If you are not using an ad blocker but are still receiving this message, make sure your browser's tracking protection is set to the 'standard' level.

Technology Stocks : Driverless autos, trucks, taxis etc.

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next

To: Sam who wrote (14)	2/13/2017 5:19:00 PM
From: Sam	Read Replies (1) of 567

Cyclists May Benefit The Most And Be The Greatest Challenge For Self-Driving Cars Kevin Murnane , CONTRIBUTOR forbes.com Humans on bicycles have a lot to gain from self-driving cars that move humans out of the driver’s seat. Why? Because drivers are judged to be at fault in the majority of cycling accidents that result in serious injury or death. Unfortunately, it’s harder for an autonomously driven vehicle to avoid a bicycle than a car. The problem, part one. A number of studies from different countries have found that drivers are solely responsible for between 60% and 80% of collisions between cars and adult cyclists. The numbers are similar for collisions that result in serious injury or death. It should be kept in mind that the data that supports these percentages is restricted to collisions that are reported to police or that result in visits to a hospital. Many collisions between cars and bikes go unreported. Also, it is unknown how many collisions result from drivers who are purposely aggressive and attempt to intimidate cyclists on the road. Self-driving cars should eliminate accidents caused by purposeful intimidation and greatly reduce collisions caused by driver error. But before that can happen, the detection system in the vehicle must be able to recognize that a bicycle is present in the roadway. That can be a problem. Bicycles are small and they can appear suddenly from unexpected places. Moreover, their visual envelopes can differ markedly. A commuter sitting upright on a hybrid bike with their bag in a pannier presents a very different profile from a rider in full kit on a road bike out on a training run. All of these things make bicycle recognition difficult for detection systems. Deep3DBox is a deep convolutional neural network that recognizes objects and is able to predict their three-dimensional shape and the direction they’re facing from two-dimensional images. The ability to predict shape in addition to location is important for vehicle detection systems because knowing where an object is located isn’t always enough to avoid hitting it. You also need to know how much space the object takes up. Deep3DBox was developed by researchers at George Mason University and Zoox, a company developing autonomous taxis. continues at the link

Report TOU Violation

Share This Post

Public Reply Prvt Reply Mark as Last Read File

Previous 10 Next 10 Previous Next