Machine learning enhanced vehicle merging
First Claim
1. A method comprising:
- receiving a first image set depicting a merging zone, the first image set including one or more first images associated with a first timestamp;
determining, using a trained first machine learning logic, a first state describing a traffic condition of the merging zone at the first timestamp using the first image set;
determining, from a sequence of states describing the traffic condition of the merging zone at a sequence of timestamps, using a trained second machine learning logic, one or more second states associated with one or more second timestamps prior to the first timestamp of the first state using a trained backward time distance;
computing, using a trained third machine learning logic, one or more impact metrics for one or more merging actions using the first state, the one or more second states, and the one or more merging actions;
selecting, from the one or more merging actions, a first merging action based on the one or more impact metrics; and
providing a merging instruction including the first merging action to a merging vehicle, the merging instruction instructing the merging vehicle to perform the first merging action in the merging zone.
1 Assignment
0 Petitions
Accused Products
Abstract
A method receives a first image set depicting a merging zone, the first image set including first image(s) associated with a first timestamp; determines, using a trained first machine learning logic, a first state describing a traffic condition of the merging zone at the first timestamp using the first image set; determines, from a sequence of states describing the traffic condition of the merging zone at a sequence of timestamps, using a trained second machine learning logic, second state(s) associated with second timestamp(s) prior to the first timestamp of the first state using a trained backward time distance; computes, using a trained third machine learning logic, impact metric(s) for merging action(s) using the first state, the second state(s), and the merging action(s); selects, from the merging action(s), a first merging action based on the impact metric(s); and provides a merging instruction including the first merging action to a merging vehicle.
-
Citations
16 Claims
-
1. A method comprising:
-
receiving a first image set depicting a merging zone, the first image set including one or more first images associated with a first timestamp; determining, using a trained first machine learning logic, a first state describing a traffic condition of the merging zone at the first timestamp using the first image set; determining, from a sequence of states describing the traffic condition of the merging zone at a sequence of timestamps, using a trained second machine learning logic, one or more second states associated with one or more second timestamps prior to the first timestamp of the first state using a trained backward time distance; computing, using a trained third machine learning logic, one or more impact metrics for one or more merging actions using the first state, the one or more second states, and the one or more merging actions; selecting, from the one or more merging actions, a first merging action based on the one or more impact metrics; and providing a merging instruction including the first merging action to a merging vehicle, the merging instruction instructing the merging vehicle to perform the first merging action in the merging zone. - View Dependent Claims (2, 3, 4, 5, 6, 7, 8)
-
-
9. A system comprising:
-
one or more processors; one or more memories storing instructions that, when executed by the one or more processors, cause the system to; receive a first image set depicting a merging zone, the first image set including one or more first images associated with a first timestamp; determine, using a trained first machine learning logic, a first state describing a traffic condition of the merging zone at the first timestamp using the first image set; determine, from a sequence of states describing the traffic condition of the merging zone at a sequence of timestamps, using a trained second machine learning logic, one or more second states associated with one or more second timestamps prior to the first timestamp of the first state using a trained backward time distance; compute, using a trained third machine learning logic, one or more impact metrics for one or more merging actions using the first state, the one or more second states, and the one or more merging actions; select, from the one or more merging actions, a first merging action based on the one or more impact metrics; and provide a merging instruction including the first merging action to a merging vehicle, the merging instruction instructing the merging vehicle to perform the first merging action in the merging zone. - View Dependent Claims (10, 11, 12, 13, 14, 15, 16)
-
Specification