Mobileye Vision Technologies Ltd.

Mobileye Technologies Limited

Yoav Taieb

Gideon Stein

Amnon Shashua

Yoram Gdalyahu

Shai Shalev-Shwartz

Ofer Fridman

Itai Ben Shalom

Shaked Shammah

Daniel Braunstein

Eyal Bagon

David Huberman

Yoel Krupnik

Ofer Springer

Anna Clarke

Dor Eagelberg

Yair Kapach

Kfir Viente

Harel Livyatan

Uri Wolfovitz

Ori Shachar

Levi Bellaiche

Aran Reisman

Ori Buberman

Oded Schwarz

Igor Tubis

Yuval Hochman

Yahel Guberman

Chagay Ki-tov

Gideon P Stein

Shai Shalev-Schwarz

Uri Worlfovitz

Systems and methods for creating maps used in navigating autonomous vehicles are disclosed. In one implementation at least one processor is programmed to receive drive information from each of a plurality of vehicles that traverse different entrance-exit combinations of a road junction; for each of the entrance-exit combinations, align three-dimensional feature points in the drive information to generate a plurality of aligned three-dimensional feature point groups, one for each entrance-exit combination of the road junction; correlate one or more three-dimensional feature points in each of the plurality of aligned three-dimensional feature point groups with one or more three-dimensional feature points included in every other aligned three-dimensional feature point group from among the plurality of aligned three-dimensional feature point groups; and generate a sparse map based on the correlation, the sparse map including a target trajectory associated with each of the entrance-exit combinations.

Fully aligned junctions

Systems and methods are provided for navigating an autonomous vehicle. In one implementation, a system includes a processing device programmed to receive a plurality of images representative of an environment of the host vehicle. The environment includes a road on which the host vehicle is traveling. The at least one processing device is further programmed to analyze the images to identify a target vehicle traveling in a lane of the road different from a lane in which the host vehicle is traveling; analyze the images to identify a lane mark associated with the lane in which the target vehicle is traveling; detect lane mark characteristics of the identified lane mark; use the detected lane mark characteristics to determine a type of the identified lane mark; determine a characteristic of the target vehicle; and determine a navigational action for the host vehicle based on the determined lane mark type and the determined characteristic of the target vehicle.

Systems and methods for navigating lane merges and lane splits

Systems and methods are provided for vehicle navigation. The systems and methods may detect traffic lights. For example, one or more traffic lights may be detected using detection-redundant camera detection paths, a fusion of information from a traffic light transmitter and one or more cameras, based on contrast enhancement for night images, and based on low resolution traffic light candidate identification followed by high resolution candidate analysis. Additionally, the systems and methods may navigation based on a worst time to red estimation.

Low resolution traffic light candidate identification followed by high resolution candidate analysis

A navigation system may include a processor programmed to analyze a first image to identify a non-semantic road feature; identify a first image location, in the first image, of one point associated with the non-semantic road feature; analyze a second image to identify a representation of the non-semantic road feature in the second image; identify a second image location, in the second image, of the one point associated with the non-semantic road feature; determine, based on a difference between the first and second image locations and based on motion information for a vehicle between a capture of the first image and a capture of the second image, three-dimensional coordinates for the one point associated with the non-semantic road feature; and send the three-dimensional coordinates for the one point associated with the non-semantic road feature to a server for use in updating a road navigation model.

Updating road navigation model using non-semantic road feature points

A system for autonomously navigating a vehicle through a road junction may include at least one processor programmed to receive from an image capture device at least one image representative of an environment of the vehicle. The processor may also be configured to analyze the image to identify two or more landmarks located in the environment of the vehicle and to determine, for each of the two or more landmarks, a directional indicator relative to the vehicle. The processor may be configured to determine a current location of the vehicle relative to the road junction based on an intersection of the directional indicators a heading for the vehicle based on the directional indicators for the two or more landmarks. The processor may be configured to determine a steering angle for the vehicle by comparing the vehicle heading with a predetermined road model trajectory at the current location of the vehicle.

Navigating road junctions

Systems and methods are provided for determining a lane assignment for an autonomous vehicle along a road segment. In one implementation, at least one image representative of an environment of the vehicle is received from a camera. The at least one image may be analyzed to identify at least one recognized landmark, and an indicator of a lateral offset distance between the vehicle and the at least one recognized landmark may be determined. Moreover, a lane assignment of the vehicle along the road segment may be determined based on the indicator of the lateral offset distance between the vehicle and the at least one recognized landmark.

Determining lane assignment based on recognized landmark location

Systems and methods are provided for navigating an autonomous vehicle using reinforcement learning techniques. In one implementation, a navigation system for a host vehicle may include at least one processing device programmed to: receive, from a camera, a plurality of images representative of an environment of the host vehicle, analyze the plurality of images to identify a navigational state associated with the host vehicle, provide the navigational state to a trained navigational system, receive, from the trained navigational system, a desired navigational action for execution by the host vehicle in response to the identified navigational state, analyze the desired navigational action relative to one or more predefined navigational constraints, determine an actual navigational action for the host vehicle, wherein the actual navigational action includes at least one modification of the desired navigational action determined based on the one or more predefined navigational constraints, and cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined actual navigational action for the host vehicle.

Constraint relaxation in a navigational system

Systems and methods are provided for navigating an autonomous vehicle using reinforcement learning techniques. In one implementation, a navigation system for a host vehicle may include at least one processing device programmed to: receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the plurality of images to identify a navigational state associated with the host vehicle; provide the navigational state to a trained navigational system; receive, from the trained navigational system, a desired navigational action for execution by the host vehicle in response to the identified navigational state; analyze the desired navigational action relative to one or more predefined navigational constraints; determine an actual navigational action for the host vehicle, wherein the actual navigational action includes at least one modification of the desired navigational action determined based on the one or more predefined navigational constraints; and cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined actual navigational action for the host vehicle.

Constraint augmentation in a navigational system

A navigation system for a host vehicle is provided. The system may comprise at least one processing device programmed to receive, from a camera, a plurality of images representative of an environment of the host vehicle; analyze the plurality of images to identify a navigational state associated with the host vehicle; determine a first predefined navigational constraint implicated by at least one aspect of the navigational state; identify, based on analysis of the plurality of images, a presence of at least one navigational constraint augmentation factor; determine a second navigational constraint based on identification of the at least one navigational constraint augmentation factor; determine, based on the identified navigational state, a navigational action for the host vehicle satisfying the second navigational constraint; and cause at least one adjustment of a navigational actuator of the host vehicle in response to the determined navigational action.

Systems and methods are provided for detecting traffic signs. In one implementation, a traffic sign detection system for a vehicle include at least one image capture device configured to acquire at least one image of a scene including a traffic sign ahead of the vehicle. The traffic sign detection system also includes a data interface and at least one processing device programmed to receive the at least one image via the data interface, transform the at least one image, sample the transformed at least one image to generate a plurality of images having different sizes, convolve each of the plurality of images with a template image, compare each pixel value of each convolved image to a predetermined threshold, and select local maxima of pixel values within local regions of each convolved image as attention candidates, the local maxima being greater than the predetermined threshold.

Systems and methods for detecting traffic signs

Systems and methods are provided for interacting with a plurality of autonomous vehicles. In one implementation, a system may include at least one processor. The at least one processor may be programmed to receive from each of the plurality of autonomous vehicles navigational situation information associated with an occurrence of an adjustment to a determined navigational maneuver, analyze the navigational situation information, determine, based on the analysis of the navigational situation information, whether the adjustment to the determined navigational maneuver was due to a transient condition, and update the predetermined model representative of the at least one road segment if the adjustment to the determined navigational maneuver was not due to a transient condition.

Growing community of inventors

Jerusalem, Israel

Yoav Taieb