Driving assistance systems and method implemented in such a system

Patent metadata

Field	Value
Publication number	US-10346690-B2
Application number	US-201515501324-A
Country	US
Kind code	B2
Filing date	Jul 23, 2015
Priority date	Aug 6, 2014
Publication date	Jul 9, 2019
Grant date	Jul 9, 2019

Abstract

A driving assistance system includes at least one receiving module designed to receive perception data from a driving environment, a control module designed to control an on-board system, a conversion module designed to generate, on the basis of the perception data, a plurality of instances of classes of an ontology stored by the driving assistance system and defining relations between classes, and a reasoning tool designed to deduce, on the basis of the ontology, at least one property of an instance of the plurality. The control module is designed to control the on-board system on the basis of the deduced property.

First claim

The invention claimed is:

1. A driving assistance system for a vehicle, comprising:
at least one receiving module designed to receive perception data from a driving environment of the vehicle;
a control module designed to control an on-board system of the vehicle;
a conversion module designed to:
identify objects based on the perception data;
generating an electronic horizon for the vehicle from a digital map, the electronic horizon being limited to a portion of the digital map over which the vehicle will maneuver in a predetermined time;
classify, on the basis of the perception data, each of the objects into one of a plurality of classes of an ontology stored by the driving assistance system, the ontology defining relations between the classes based on rules that define the relations when predetermined criteria are met;
construct a digital world comprising the objects within the electronic horizon;
create an instance for each of the objects in the digital world based on the ontology; and

a reasoning tool designed to deduce, on the basis of the ontology, at least one property of one of the instances,
wherein the control module is designed to control the on-board system on the basis of the deduced property.

2. The driving assistance system as claimed in claim 1 , wherein the perception data comprise proprioceptive data transmitted by an on-board computer.

3. The driving assistance system as claimed in claim 1 , wherein the perception data comprise localization data generated by a localization system.

4. The driving assistance system as claimed in claim 1 , wherein the perception data comprise localization data generated by a localization system, and wherein the conversion module comprises a subunit for the generation of the electronic horizon.

5. The driving assistance system as claimed in claim 1 , wherein the perception data comprise measurement data generated by a sensor.

6. The driving assistance system as claimed in claim 1 , wherein the perception data comprise external knowledge data received from a communication system.

7. The driving assistance system as claimed in claim 1 , wherein the on-board system is a warning device.

8. The driving assistance system as claimed in claim 1 , wherein the on-board system is an actuator.

9. The driving assistance system as claimed in claim 1 , wherein the digital world comprises each of the objects and a location of each of the objects in space.

10. The driving assistance system as claimed in claim 1 , wherein the objects include a pedestrian, a first vehicle that includes the driving assistance system, a second vehicle, and a pedestrian crossing.

11. The driving assistance system as claimed in claim 1 , wherein the ontology defines the relations between the classes based on rules that are applied when the objects possess predetermined conditions.

12. The driving assistance system as claimed in claim 11 , wherein the reasoning tool deduces the at least one property based on the rules that are applied.

13. The driving assistance system as claimed in claim 12 , wherein the objects include a pedestrian, a first vehicle that includes the driving assistance system, a second vehicle, and a pedestrian crossing, and the rules include, based on the objects, that the pedestrian near the pedestrian crossing is likely to cross a road and that the second vehicle slows down when the pedestrian is likely to cross the road.

14. A method implemented in a driving assistance system of a vehicle, comprising:
receiving perception data from a driving environment of the vehicle;
identifying objects within the driving environment based on the perception data;
generating an electronic horizon for the vehicle from a digital map, the electronic horizon being limited to a portion of the digital map over which the vehicle will maneuver in a predetermined time;
classifying, on the basis of the perception data, each of the objects into one of a plurality of classes of an ontology stored by the driving assistance system, the ontology defining relations between the classes based on rules that define the relations when predetermined criteria are met;
constructing a digital world comprising the objects within the electronic horizon;
creating an instance for each of the objects based on the ontology;
deducing, by a reasoning tool and on the basis of the ontology, at least one property of one of the instances; and
controlling an on-board system on the basis of the deduced property.

Assignees

• Renault Sas

Inventors

• Armand Alexandre
• Ibanez-Guzman Javier
• Filliat David

Classifications

• B60R2300/307

  virtually distinguishing relevant parts of a scene from the background of the scene · CPC title

• B60R2300/8093

  for obstacle warning · CPC title

• B60W30/0956

  the prediction being responsive to traffic or environmental parameters · CPC title

• B60K2031/0016

  Identification of obstacles; Selection of a target vehicle · CPC title

• B60W2556/50

  of positioning data, e.g. GPS [Global Positioning System] data · CPC title