AI News, Driverless cars change lanes more like humans do

Driverless cars change lanes more like humans do

At the International Conference on Robotics and Automation tomorrow, researchers from MIT's Computer Science and Artificial Intelligence Laboratory (CSAIL) will present a new lane-change algorithm that splits the difference.

It allows for more aggressive lane changes than the simple models do but relies only on immediate information about other vehicles' directions and velocities to make decisions.

'The optimization solution will ensure navigation with lane changes that can model an entire range of driving styles, from conservative to aggressive, with safety guarantees,' says Rus, who is the director of CSAIL.

The buffer zones describe not only the vehicles' current positions but their likely future positions within some time frame.

For any given method of computing buffer zones, algorithm designers must prove that it guarantees collision avoidance, within the context of the mathematical model used to describe traffic patterns.

With the MIT researchers' system, if the default buffer zones are leading to performance that's far worse than a human driver's, the system will compute new buffer zones on the fly -- complete with proof of collision avoidance.

Using the static, precomputed buffer zones would only allow for conservative driving, whereas our dynamic algorithm allows for a broader range of driving styles.'

Making driverless cars change lanes more like human drivers do

In the field of self-driving cars, algorithms for controlling lane changes are an important topic of study.

But most existing lane-change algorithms have one of two drawbacks: Either they rely on detailed statistical models of the driving environment, which are difficult to assemble and too complex to analyze on the fly;

“The optimization solution will ensure navigation with lane changes that can model an entire range of driving styles, from conservative to aggressive, with safety guarantees,” says Rus, who is the director of CSAIL.

For any given method of computing buffer zones, algorithm designers must prove that it guarantees collision avoidance, within the context of the mathematical model used to describe traffic patterns.

With the MIT researchers’ system, if the default buffer zones are leading to performance that’s far worse than a human driver’s, the system will compute new buffer zones on the fly — complete with proof of collision avoidance.

“The autonomous vehicles were not in direct communication but ran the proposed algorithm in parallel without conflict or collisions,” explains Pierson. “Each car used a different risk threshold that produced a different driving style, allowing us to create conservative and aggressive drivers.

Using the static, precomputed buffer zones would only allow for conservative driving, whereas our dynamic algorithm allows for a broader range of driving styles.” This project was supported, in part, by the Toyota Research Institute and the Office of Naval Research.

Making Driverless Cars Change Lanes More Like Human Drivers Do

A new algorithm developed by the Massachusetts Institute of Technology's (MIT) Computer Science and Artificial Intelligence Laboratory (CSAIL) could improve the way driverless vehicles change lanes.

If default buffer zones are leading to performance that is significantly worse than a human driver's, the system will compute new buffer zones on the fly, with proof of collision avoidance.

Based on estimates of the car's direction and velocity, the system generates a logistic function that, when multiplied by the Gaussian distribution, skews the distribution in the direction of the car's movement.

Google: Human drivers are the problem

Google revealed on Monday that its autonomous vehicles have been in 11 'minor' accidents in California since it launched its self-driving car project over six years ago.

Urmson said in a blog post that Google's cars have been side-swiped 'a couple of times,' rear-ended seven times -- 'mainly at traffic lights but also on the freeway' -- and hit by a car that drove through a stop sign.

'The most common accidents our cars are likely to experience in typical day to day street driving — light damage, no injuries — aren't well understood because they're not reported to police,' Urmson explained.

(An AP report said that two of the recent four accidents happened while the car was in 'self-driving' mode, while the other two incidents took place when a person was in control of the vehicle.)

Google has already identified many patterns of driver behavior, such as lane-drifting and red-light running, that are leading indicators of significant collisions, and programmed its cars to adapt.

For example, Google's cars pause after a light turns green before moving through an intersection to avoid potential red-light runners.

If a driver tries to abruptly cut lanes, Google's cars slow down when they sense another vehicle entering a pre-determined buffer zone to avoid collision.

The company's self-driving cars have driven nearly a million miles autonomously, on both freeways and city streets, and Google says it will continue to test drive its cars to gather more data about common driving problems.

NEW 2018 Audi A8 Development

NEW 2018 Audi A8 Development. The experts at Audi long ago abandoned the obsession with using a single material in lightweight design. With a mix of ...

Resilience and Security in Cyber-Physical Systems: Self-Driving Cars and Smart Devices

The future will be defined by autonomous computer systems that are tightly integrated with the environment, also known as Cyber-Physical systems (CPS).

Professor Paul Oyer, "The Gig Economy: Threats and Opportunities for Workers and Employers”

Technology has disrupted the labor market in important ways, both enabling greater productivity from remote workers and displacing workers altogether.

IROS2017: Mobile Robot Autonomous Navigation in Uneven and Unstructured Environments

OURSA Conference Recording

OUR SECURITY ADVOCATES highlights a diverse set of experts from across information security, safety, trust, and other related fields. Agenda is below and at ...

Yelawolf - Daddy's Lambo

Sign up for updates: Music video by Yelawolf performing Daddy's Lambo. (C) 2011 DGC Records Best of Yelawolf: ..

Darryl Anka (Bashar) - Buddha at the Gas Pump Interview

Discussion of this interview in the Batgap Community Facebook Group: Also see ..

Mobile robotic system Stamina

STAMINA ("Sustainable and Reliable Robotics for Part Handling in Manufacturing Automation") European research and development project aims at developing ...

Fendt 900 Vario MT. The New Generation of Fendt Tracked Tractors | TractorLab

Fendt 900 Vario MT. The New Generation of Fendt Tracked Tractors | TractorLab New Video: Most Popular Video: .

Energy: Tesla Motors Just Put its Growth Pedal to the Metal *** INDUSTRY FOCUS ***

If Tesla Motors plans for growth and its new Model 3 weren't ambitious enough, it now wants to make it all happen by 2018. Plus, earnings from Royal Dutch ...