The Google driverless car is a project by Google that involves developing technology for autonomous cars. The project is currently being led by Google engineer Sebastian Thrun, director of the Stanford Artificial Intelligence Laboratory and co-inventor of Google Street View. A recent report quoted Google stating that 'We want to improve people's lives by making driving safer, more enjoyable, and more efficient. We've successfully driven over half a million miles across a wide variety of terrain and road conditions, and we're very pleased with the performance. We're continuing to develop and refine the technology, but we aren't going to elaborate about specific plans at this point." Today, Patent Bolt was first to discover a new Google patent application published by the US Patent Office about some of the referred refinements to the driverless car regarding vehicle control based on perception uncertainty.
Aspects of Google's invention relate generally to maneuvering autonomous vehicles. Specifically, the vehicle may determine the uncertainty in its perception system and use this uncertainty value to make decisions about how to maneuver the vehicle.
For example, the perception system may include sensors, object type models, and object motion models, each associated with uncertainties. The sensors may be associated with uncertainties based on the sensor's range, speed, and /or shape of the sensor field.
The object type models may be associated with uncertainties, for example, in whether a perceived object is of one type (such as a small car) or another type (such as a bicycle). The object motion models may also be associated with uncertainties, for example, not all objects will move exactly as they are predicted to move. These uncertainties may be used to maneuver the vehicle.
Adaptive Cruise Control System
Google states that the driverless vehicle may also include various radar detection units, such as those used for adaptive cruise control systems. The radar detection units may be located on the front and back of the car as well as on either side of the front bumper.
In another example, a variety of cameras may be mounted on the vehicle. The cameras may be mounted at predetermined distances so that the parallax from the images of 2 or more cameras may be used to compute the distance to various objects.
Google states that each sensor may be associated with a particular sensor field in which the sensor may be used to detect objects. In patent FIG. 4A noted below we see a top-down view of the approximate sensor fields of the various sensors. Patent FIG. 4D depicts the approximate sensor fields and cameras based on the fields of view for these sensors.
An autonomous vehicle may drive along a roadway collecting and processing sensor data regarding the vehicle's surroundings. The sensor data may be processed to identify areas of the roadway occupied by objects. For example, patent FIG. 8 depicts an intersection with the detailed map information. The vehicle processes the information received from the sensors and identifies approximate locations, headings, and speeds of objects such as a person (#710), a bike (#720), and another close by vehicle (#730).
The data associated with the detected objects may also be processed using the object type models. Once the object type is determined, a motion model may also be identified.
Overview of Motion Model
Google's patent FIG. 10 depicts an example flow diagram 1000 of some of the features described. In this example, an autonomous vehicle driving along a roadway detects an object in the vehicle's surroundings at block #1002. The object is detected using a sensor associated with a sensor uncertainty. A type of object is identified based on an object type model at block #1004. The object type model is associated with an object type model uncertainty. Based on the identified object type, a motion model, that predicts a future location of the object, is identified at block #1006.
The motion model is associated with a motion model uncertainty. Based on the motion model uncertainty, the object type model uncertainty, and/or the sensor uncertainty, an uncertainty driving strategy is identified at block #1008. The uncertainty driving strategy is then used to maneuver the vehicle at block #1010.
Overview of the Driverless Vehicle
In Google's patent FIG. 1 below we see an overview of an autonomous driving system including its various components. While certain aspects of the disclosure are particularly useful in connection with specific types of vehicles, the vehicle may be any type of vehicle including, but not limited to, cars, trucks, motorcycles, busses, boats, airplanes, helicopters, lawnmowers, recreational vehicles, amusement park vehicles, trams, golf carts, trains, and trolleys.
Google filed their patent application back in Q1 2012. To review the patent's full details, see patent application 20130197736 number. Considering that this is a patent application, the timing of such a product to market is unknown at this time. Google estimates that the driverless vehicle is likely not to arrive before 2018 and industry analysts don't see this rolling out until after 2020.
A Note for Tech Sites covering our Report: We ask tech sites covering our report to kindly limit the use of our graphics to one image. Thanking you in advance for your cooperation.
A new report posted by USA Today titled "States take the Wheel on Driverless Cars" on Monday provides a nice overview of how California, Nevada, Florida and the District of Columbia are now setting the ground rules for self-driving cars on roads. It's an interesting read. Below is the video from that article.
Patent Bolt presents a detailed summary of patent applications with associated graphics for journalistic news purposes as each such patent application is revealed by the U.S. Patent & Trade Office. Readers are cautioned that the full text of any patent application should be read in its entirety for full and accurate details. Revelations found in patent applications shouldn't be interpreted as rumor or fast-tracked according to rumor timetables. About Comments: Patent Bolt reserves the right to post, dismiss or edit comments.