Back to results
US 12,741,664 B2Granted
Implementing synthetic scenes for autonomous vehicles
AssigneeWaymo LLC
InventorsCongrui Hetang, Yi Shen, Youjie Zhou, Jiyang Gao
Life of this patent
Estimating the term…
Abstract
A system includes a memory device, and a processing device, operatively coupled to the memory device, to receive a set of input data including a roadgraph, the roadgraph including an autonomous vehicle driving path, modify the roadgraph to obtain a modified roadgraph by adjusting a trajectory of the autonomous vehicle driving path, place a set of artifacts along one or more lane boundaries of the modified roadgraph to generate a synthetic scene, and train a machine learning model used to navigate an autonomous vehicle based on the synthetic scene.
Claims20
A system for generating and utilizing synthetic scenes, comprising:
- a memory device;
- and
- a processing device, operatively coupled to the memory device, to:
- receive, at the system, a set of input data including a roadgraph, the roadgraph representing drivable paths and object configurations associated with a segment of road driven and imaged by a first autonomous vehicle, and the drivable paths comprising an autonomous vehicle driving path of the first autonomous vehicle, wherein the autonomous vehicle driving path comprises a plurality of path connection nodes disposed on the autonomous vehicle driving path;
- modify the roadgraph by adjusting a trajectory of the autonomous vehicle driving path, wherein adjusting the trajectory of the autonomous vehicle driving path comprises:
- generating between a first pair of path connection nodes of the plurality of path connection nodes, a first synthetic path segment to address a disabled path interval of a path of the roadgraph, the disabled path interval being bounded by the pair of path connection nodes;
- and
- generating between a second pair of path connection nodes of the plurality of path connection nodes, a second synthetic path segment connecting the autonomous vehicle driving path to a neighboring drivable path of the drivable paths;
- place a set of artifacts along one or more lane boundaries of the modified roadgraph comprising the first synthetic path segment and the second synthetic path segment to generate a synthetic scene, wherein placing the set of artifacts comprises placing candidate artifacts along one or more lane boundaries of the first synthetic path segment, one or more lane boundaries of the second synthetic path segment, and one or more lane boundaries of the disabled path interval;
- train a machine learning model to navigate a second autonomous vehicle based on the synthetic scene;
- and
- cause a steering mechanism of the second autonomous vehicle to perform a steering maneuver.
9 more elements
A method comprising:
- receiving, by a processing device of a system for generating and utilizing synthetic scenes, a set of input data including a roadgraph, the roadgraph representing drivable paths and object configurations associated with a segment of road driven and imaged by a first autonomous vehicle, and the drivable paths comprising an autonomous vehicle driving path of the first autonomous vehicle, wherein the autonomous vehicle driving path comprises a plurality of path connection nodes disposed on the autonomous vehicle driving path;
- modifying, by the processing device, the roadgraph by adjusting a trajectory of the autonomous vehicle driving path, wherein adjusting the trajectory of the autonomous vehicle driving path comprises:
- generating between a first pair of path connection nodes of the plurality of path connection nodes, a first synthetic path segment to address a disabled path interval of a path of the roadgraph, the disabled path interval being bounded by the pair of path connection nodes;
- and
- generating between a second pair of path connection nodes of the plurality of path connection nodes, a second synthetic path segment connecting the autonomous vehicle driving path to a neighboring drivable path of the drivable paths;
- placing, by the processing device, a set of artifacts along one or more lane boundaries of the modified roadgraph comprising the first synthetic path segment and the second synthetic path segment to generate a synthetic scene, wherein placing the set of artifacts comprises placing candidate artifacts along one or more lane boundaries of the first synthetic path segment, one or more lane boundaries of the second synthetic path segment, and one or more lane boundaries of the disabled path interval;
- training, by the processing device, a machine learning model to navigate a second autonomous vehicle based on the synthetic scene;
- and
- causing a steering mechanism of the second autonomous vehicle to perform a steering maneuver.
6 more elements
A method comprising:
- obtaining a trained machine learning model used to navigate a first autonomous vehicle, wherein the trained machine learning model is trained at a system for generating and utilizing synthetic scenes and is trained based on a synthetic scene comprising a modified roadgraph modified from an original roadgraph representing drivable paths and object configurations associated with a segment of road driven and imaged by a second autonomous vehicle,
- the drivable paths comprising an autonomous vehicle driving path of the second autonomous vehicle that comprises a plurality of path connection nodes disposed on the autonomous driving path,
- the modified roadgraph having a modified autonomous vehicle driving path that comprises a first synthetic path segment generated between a first pair of path connection nodes of the plurality of path connection nodes to address a disabled path interval bounded by the first pair of path connection nodes of a path of the roadgraph, and a second synthetic path segment generated between a second pair of path connection nodes of the plurality of path connection nodes connecting the autonomous vehicle driving path to a neighboring drivable path of the drivable paths, and a set of synthetic artifacts along at least one lane boundary of the modified roadgraph, wherein the set of synthetic artifacts comprises candidate artifacts placed along one or more lane boundaries of the first synthetic path segment, one or more lane boundaries of the second synthetic path segment, and one or more lane boundaries of the disabled path interval;
- receiving detection results including a set of artifacts within a scene while the first autonomous vehicle is proceeding along a driving path;
- causing a modification of the driving path using the trained machine learning model in view of the detection results;
- and
- causing a steering mechanism of the first autonomous vehicle to perform a steering maneuver based on the modified driving path.
4 more elements
Dependencies are inferred from the claim text.