Method for a scene interpretation of an environment of a vehicle

A processing unit of a vehicle, the processing unit comprising a processor system including at least one processor, wherein the processor system is configured to:

• receive environment sensor data from at least one environment sensor of the vehicle;
• carry out an object detection based on the environment sensor data by which first objects in an environment of the vehicle are detected;
• carry out a scene analysis of the environment by taking into consideration the detected first objects and second objects stored in a map display of the environment, the map display being a representation of valid map data, the scene analysis including comparing the first objects detected in the object detection based on the environment sensor data to the second objects of the map display;
• generate a scene representation based on the scene analysis;
• and
• perform an automated control of the vehicle according to the generated scene representation;
• wherein the processing unit is configured to additionally perform at least one of the following steps (I)-(II):
• (I) prior to the comparison, adapt a perspective of the map display to align with a perspective of the environment sensor data, thereby providing spatial agreement of the map display with the environment sensor data;
• and
• (II) determine, on an object-by-object basis, respective reliabilities of the first objects and respective reliabilities of the second objects, wherein the generation of the scene representation includes selecting which of the first objects to include in the scene representation and which of the second objects to include in the scene representation depending on the respective reliabilities of the first objects and the second objects.

A non-transitory computer-readable medium on which is stored a computer program that is executable by a data processing unit of a vehicle, and that, when executed by the processing unit, causes the data processing unit to perform a method, the method comprising the following steps:

• receiving environment sensor data from at least one environment sensor of the vehicle;
• carrying out an object detection based on the environment sensor data by which first objects in an environment of the vehicle are detected;
• carrying out a scene analysis of the environment by taking into consideration the detected first objects and second objects stored in a map display of the environment, the map display being a representation of valid map data, the scene analysis including comparing the first objects detected in the object detection based on the environment sensor data to the second objects of the map display;
• generating a scene representation based on the scene analysis;
• and
• performing an automated control of the vehicle according to the generated scene representation;
• wherein the method includes at least one of the following two features (I)-(II):
• (I) the method further comprises, prior to the comparing, adapting a perspective of the map display to align with a perspective of the environment sensor data, thereby providing spatial agreement of the map display with the environment sensor data;
• and
• (II) the method further comprises determining, on an object-by-object basis, respective reliabilities of the first objects and respective reliabilities of the second objects, wherein the generating of the scene representation includes selecting which of the first objects to include in the scene representation and which of the second objects to include in the scene representation depending on the respective reliabilities of the first objects and the second objects.