Roads, especially while shared with human drivers, are unpredictable places. Training a self-driving car for every possible situation is a monumental task.

The AI developed by Microsoft and MIT compares the action taken by humans in a given scenario to what the driverless car’s own AI would do. Where the human decision is more optimal, the vehicle’s behaviour is updated for similar future occurrences.

Ramya Ramakrishnan, an author of the report, says:

“The model helps autonomous systems better know what they don’t know.

Many times, when these systems are deployed, their trained simulations don’t match the real-world setting [and] they could make mistakes, such as getting into accidents.

The idea is to use humans to bridge that gap between simulation and the real world, in a safe way, so we can reduce some of those errors.”

For example, if an emergency vehicle is approaching then a human driver should know to let them pass if safe to do so. These situations can get complex dependent on the surroundings.

On a country road, allowing the vehicle to pass could mean edging onto the grass. The last thing you, or the emergency services, want a driverless car to do is to handle all country roads the same and swerve off a cliff edge.

Humans can either ‘demonstrate’ the correct approach in the real world, or ‘correct’ by sitting at the wheel and taking over if the car’s actions are incorrect. A list of situations is compiled along with labels whether its actions were deemed acceptable or unacceptable.

The researchers have ensured a driverless car AI does not see its action as 100 percent safe even if the result has been so far. Using the Dawid-Skene machine learning algorithm, the AI uses probability calculations to spot patterns and determine if something is truly safe or still leaves the potential for error.

We’re yet to reach a point where the technology is ready for deployment. Thus far, the scientists have only tested it with video games. It offers a lot of promise, however, to help ensure driverless car AIs can one day safely respond to all situations.

The post Microsoft and MIT develop AI to fix driverless car ‘blind spots’ appeared first on AI News.

While Uber brought us on-demand taxi rides at the press of a button, Sony wants to use AI to further improve on the model. By studying conditions such as traffic, weather, and current events — taxis can be dispatched automatically where needed.

One example, which many of us will have experienced, is the frustration of getting transport home after a concert. Sony’s algorithm would ensure a fleet of taxis are ready to pick up a surge of attendees exiting the event. More taxis could be dispatched if the weather conditions are poor and people are less likely to walk and use alternative transport such as buses.

Sony is currently focusing on its native market of Japan for the initial release; with no word of plans to release elsewhere. Japan has a ban on the use of private vehicles for ridesharing which enables Sony to gain a foothold in a market with little competition.

However, the company will have to move fast. Automotive giant Toyota is also looking for a slice of the market and poured $70 million into JapanTaxi, another company which is working on an AI-powered taxi system.

The taxi companies involved in Sony’s alliance includes Checker Cab, Daiwa Motor Transportation, Green Cab, Hinomaru Kotsu, and Kokusai Motorcars.

As self-driving cars grow in prominence, AI hailing systems like what Sony is developing will become invaluable. The company has a chance at becoming a leader in what’s set to become a very lucrative market.

What are your thoughts on Sony developing an AI-powered taxi system?

The post Sony is working on an AI-powered taxi system appeared first on AI News.