Driver assistance systems
AssigneeArriver Software AB
InventorsSylvia Pietzsch, Christina Lichtenthaeler, Ajay Prasanna
Life of this patent
Estimating the term…
Abstract
A driver assistance apparatus being configured to generate a list of objects, each object being located in a vicinity of the vehicle and each object having been identified using data from at least one object sensor on the vehicle. The apparatus also searches for lane markings on a road on which the vehicle travels using data from at least one lane marking sensor on the vehicle. Finally, a region of interest (“ROI”) is established on the basis of at least one detected lane marking, wherein the ROI includes an ROI ego lane, an ROI left lane and an ROI right lane. A corresponding method is also provided.
Claims26
An apparatus comprising:
- a memory;
- and
- a processor coupled to the memory, the processor configured to:
- receive sensor data from at least one sensor;
- detect lane markings on a road on which a vehicle travels using the sensor data from the at least one sensor;
- establish a region of interest (“ROI”) on the basis of at least one detected lane marking of the detected lane markings, wherein establishing the ROI includes:
- determining a width based on the at least one detected lane marking;
- generating an ROI ego lane based on the width, the vehicle being located in the ROI ego lane;
- and
- generating at least one ROI adjacent lane on a side of the ROI ego lane;
- identify a plurality of objects using data from at least one object sensor on the vehicle;
- assign at least one of a plurality of objects to one of the ROI ego lane or the at least one ROI adjacent lane, each of the plurality of objects being located within a distance of the vehicle;
- select a closest object to the vehicle from the assigned objects;
- generate a candidate list as a subset of the list of objects, the candidate list including at least one object chosen from the assigned objects, wherein the candidate list contains the closest object to the vehicle in each of a plurality of regions;
- and
- adjust an operational parameter of the ego vehicle based on the candidate list.
A method for a motor vehicle driver assistance system, the method comprising the steps of:
- receiving data from at least one sensor;
- detecting lane markings on a road on which a vehicle travels using the sensor data from the at least one sensor;
- establishing a region of interest (“ROI”) on the basis of at least one detected lane marking of the detected lane markings, wherein establishing the ROI includes:
- determining a width based on the at least one detected lane marking;
- generating an ROI ego lane based on the, the vehicle being located in the ROI ego lane;
- and
- generating at least one ROI adjacent lane on a side of the ROI ego lane;
- identifying a plurality of objects using data from at least one object sensor on the vehicle;
- assigning at least one of a plurality of objects to one of the ROI ego lane or the at least one ROI adjacent lane, each of the plurality of objects being located within a distance of the vehicle;
- selecting a closest object to the vehicle from the assigned objects;
- generating a candidate list as a subset of the list of objects, the candidate list including at least one object chosen from the assigned objects, the candidate list including the closest object to the vehicle in each of a plurality of regions;
- and
- adjusting an operational parameter of the ego vehicle based on the candidate list.
Dependencies are inferred from the claim text.