Back to results
US 11,938,927 B2Granted
Track mergence module and method
AssigneesHyundai Motor Company, Kia Corporation
InventorBo Young Yun
Life of this patent
Estimating the term…
Abstract
Disclosed are a track mergence module and a method by which track deletion conditions are set to be varied depending on various situations and a track corresponding to the set track deletion conditions is deleted. The track mergence module includes a track deletion condition generation and storage unit, a phenomenon determination unit and a track mergence unit. A track to be deleted may be accurately deleted by generating the track deletion conditions so as to adaptively correspond to the performance of a sensor and various situations in which a host vehicle is placed, thereby being capable of erroneous braking of the autonomously driving host vehicle.
Claims21
A track mergence module comprising:
- a track deletion condition generation and storage unit configured to generate and store track deletion conditions corresponding to a plurality of phenomena;
- a phenomenon determination unit configured to determine a phenomenon, among the plurality of phenomena, corresponding to a current situation by analyzing a plurality of sensor fusion tracks;
- and
- a track mergence unit configured to delete a sensor fusion track among the plurality of sensor fusion tracks based on a track deletion condition which is selected among the stored track deletion conditions and corresponds to the determined phenomenon,
- wherein the phenomenon determination unit is configured to determine that the current situation corresponds to one of:
- a first phenomenon associated with a situation in which a roof lidar track having a small size with respect to one target is additionally generated;
- a second phenomenon associated with a situation in which an unstable false roof lidar track is generated;
- a third phenomenon associated with a situation in which two sensor fusion tracks having heading angles parallel to each other overlap each other;
- and
- a fourth phenomenon associated with a situation in which two sensor fusion tracks having heading angles in opposite directions overlap each other, and
- wherein the track deletion condition generation and storage unit is configured to generate and store a first track deletion condition corresponding to a function of deletion variables configured to indicate physical characteristics of a fusion track (FT1) and a roof lidar-only track (FT2) corresponding to each of the first to fourth phenomena, and a second track deletion condition corresponding to a deletion condition for a position of the fusion track satisfying the first track deletion condition.
8 more elements
A track mergence method comprising:
- generating track deletion conditions corresponding to a plurality of predetermined phenomena, respectively, and storing the generated track deletion conditions;
- determining a phenomenon, among the plurality of predetermined phenomena, corresponding to a current situation by analyzing a plurality of received tracks;
- retrieving the track deletion conditions corresponding to the determined phenomenon among the stored track deletion conditions corresponding to the phenomena;
- and
- deleting a single track or a fusion track corresponding to the track deletion conditions,
- wherein the phenomena comprises:
- a first phenomenon associated with a situation in which a roof lidar track having a small size with respect to one target is additionally generated;
- a second phenomenon associated with a situation in which an unstable false roof lidar track is generated;
- a third phenomenon associated with a situation in which two sensor fusion tracks having heading angles parallel to each other overlap each other;
- and
- a fourth phenomenon associated with a situation in which two sensor fusion tracks having heading angles in opposite directions overlap each other, and
- wherein the track deletion conditions comprise:
- a first track deletion condition corresponding to a function of deletion variables configured to indicate physical characteristics of a fusion track (FT1) and a roof lidar-only track (FT2) corresponding to each of the first to fourth phenomena;
- and
- a second track deletion condition corresponding to a deletion condition for a position of the fusion track satisfying the first track deletion condition.
12 more elements
A non-transitory computer-readable recording medium having a program recorded thereon, the program to direct a processor to perform acts of:
- generating track deletion conditions corresponding to a plurality of predetermined phenomena, respectively, and storing the generated track deletion conditions;
- determining a phenomenon, among the plurality of predetermined phenomena, corresponding to a current situation by analyzing a plurality of received tracks;
- retrieving the track deletion conditions corresponding to the determined phenomenon among the stored track deletion conditions corresponding to the phenomena;
- and
- deleting a single track or a fusion track corresponding to the track deletion conditions
- wherein the phenomena comprises:
- a first phenomenon associated with a situation in which a roof lidar track having a small size with respect to one target is additionally generated;
- a second phenomenon associated with a situation in which an unstable false roof lidar track is generated;
- a third phenomenon associated with a situation in which two sensor fusion tracks having heading angles parallel to each other overlap each other;
- and
- a fourth phenomenon associated with a situation in which two sensor fusion tracks having heading angles in opposite directions overlap each other, and
- wherein the track deletion conditions comprise:
- a first track deletion condition corresponding to a function of deletion variables configured to indicate physical characteristics of a fusion track (FT1) and a roof lidar-only track (FT2) corresponding to each of the first to fourth phenomena;
- and
- a second track deletion condition corresponding to a deletion condition for a position of the fusion track satisfying the first track deletion condition.
12 more elements
Dependencies are inferred from the claim text.