Imagry (israel) Ltd

Adham Ghazali

Ariel Keselman

Majed Jubeh

Suhail Habib

Sergey Ten

Nikolai Nikola

Itai Orr

Khaled Fahoum

Jose Ariel Keselman

Abed Abu Dbai

A computer program product, a computerized apparatus and a method for generating movement pattern for an autonomous vehicle. The method comprises obtaining a driving scenario comprising a representation of a road segment and a driving destination of an autonomous vehicle driving in the road segment. The driving scenario comprises a second vehicle in the road segment. The method comprises selecting a driving model for the second vehicle from a plurality of driving models. The plurality of driving models comprises at least an autonomous vehicle driving model and a human driver driving model. The method comprises predicting, using the driving model, a predicted movement pattern of the second vehicle within the driving scenario; and based on the predicted movement pattern of the second vehicle, generating a movement pattern for the autonomous vehicle.

Alternative driving models for autonomous vehicles

A method, an apparatus and a computer program for real-time generation of functional road maps. The method comprises obtaining a real-time input from a sensor mounted on a vehicle, that captures a front view of a road ahead of the vehicle and processing thereof by a neural network to generate a functional map of the road ahead of the vehicle. Each pixel in the functional map is associated with a predetermined relative position to the vehicle. A content of each pixel is assigned a set of values, each of which represents a functional feature relating to a location at a corresponding predetermined relative position to the pixel. The processing is performed without relying on a pre-determined precise mapping. The method further comprises providing the functional map to an autonomous navigation system of the vehicle, to autonomously drive the vehicle in accordance with functional features represented by the functional map.

Real-time generation of functional road maps

Producing a motion planning policy for an Autonomous Driving Machine (ADM) may include producing a search tree, including a root node representing a current condition of the ADM and derivative nodes linked thereto, representing predicted conditions of the ADM, following application of an action on the ADM. The nodes may be interlinked by actions and associated quality factors. A neural network (NN) may select a plurality of quality factors. The search tree may be expended to add interlinked derivative nodes according to the NN's selection, until a terminating condition is met. Backward propagating and updating one or more quality factors along trajectories of the expanded tree may occur. The NN may be trained according to the current condition of the ADM and the updated quality factors to select an optimal action. The selected optimal action may be applied on at least one physical element of the ADM.

System and method for motion planning of an autonomous driving machine

A system and method of image classification may include linking between a plurality of predetermined objects and categories, assigning a set of attributes for each object until relationships between all categories are determined, storing at least one classified image for each object in an object database, receiving an unclassified image, comparing the received unclassified image to the at least one classified image, determining at least one attribute of the received unclassified image, based on the comparison and based on the assigned attributes for each object, assigning a classification of the received unclassified image, with correlation between the at least one determined attribute of the received unclassified image, and relationships between the categories.

System and method for image classification

A method and a system for training a machine-learning model to identify real-world elements using a simulated environment (SE) may include (a) receiving at least one set of appearance parameters, corresponding to appearance of real-world element; (b) generating one or more realistic elements, each corresponding to a variant of at least one real-world element; (c) generating one or more abstract-elements; (d) placing the elements within the SE; (e) producing at least one synthetic image from the SE; (f) providing the at least one synthetic image to a machine-learning model; and (g) training the machine-learning model to identify at least one real-world element from the at least one synthetic image, that corresponds to at least one realistic element in the SE.

Growing community of inventors

Haifa, Israel

Adham Ghazali