Patent №
US 11,675,366
Granted
2023-06-13
Filed 2020
Owner
MOTIONAL AD LLC
Lab
—
AI components
3
ml · vision · hardware
Assignment
Recorded
Dataset
AIPD
2023_r1 edition
Application
17124288
This disclosure relates in general to systems and methods for tracking objects proximate an autonomous vehicle. In particular, an object tracking system capable of re-identifying objects it has temporarily lost line of sight to is described. Re-identification of the objects allows earlier object detections to be used more effectively to predict motion likely to be taken by the objects.
Machine learningVisionAI hardwareG01S 17/88G05D 1/0274G05D 1/024G05D 1/0242G05D 1/0246G05D 1/0257G06V 20/58
AI classification
Vision1.00
AI hardware0.98
Machine learning0.92
Natural language0.43
Knowledge representation0.10
Evolutionary computation0.01
Planning0.00
Speech0.00
Ownership
MOTIONAL AD LLC
assignment · 570680937
Assignors
GALOOGAHI, HAMED KIANI, DICLE, CAGLAYAN
On an employer assignment, the assignors are typically the inventors.
From the same owner
LIDAR POINT CLOUD SEGMENTATION USING BOX PREDICTIONUS 12,669,608 · 2026TRACK REFINEMENT NETWORKSUS 12,669,823 · 2026DATA PIPELINE FOR CAMERAS WITH MULTIPLE COLOR CHANNELSUS 12,657,774 · 2026PATH GENERATION BASED ON PREDICTED ACTIONSUS 12,617,390 · 2026AGENT IMPORTANCE PREDICTION FOR AUTONOMOUS DRIVINGUS 12,612,081 · 2026METHODS AND APPARATUS WITH HARDWARE LOGIC FOR PRE-PROCESSING LIDAR DATAUS 12,613,342 · 2026IMAGE BASED LIDAR-CAMERA SYNCHRONIZATIONUS 12,581,054 · 2026ENRICHING OBJECT QUERIES USING A BIRD'S-EYE VIEW FEATURE MAP TO GENERATE BOUNDING BOXESUS 12,573,168 · 2026