Back to results
US 10,437,252 B1Granted
High-precision multi-layer visual and semantic map for autonomous driving
AssigneePerceptln Shenzhen Limited
InventorsShaoshan Liu, Zhe Zhang
Life of this patent
Estimating the term…
Abstract
Roughly described, a three-dimensional, multi-layer map is built employing sensory data gathering and analysis. The sensory data are gathered from multiple operational cameras and one or more auxiliary sensors. The multi-layer maps are stored in a map stored to be distributed to one or more autonomous vehicles and robots in the future. The techniques herein are described with reference to specific example implementations to implement improvements in navigation in autonomous vehicles and robots.
Claims19
A method for building multi-layer maps of roads using information sourced by one or more moving autonomous units, including:
- distributing a proto-roadmap including only roads to a first autonomous unit that includes at least a quad camera visual sensor and at least one selected from a global positioning system and an inertial measurement unit;
- receiving from the first autonomous unit a set of keyrigs, each keyrig is a set of quad images with a pose generated using combinations of global positioning system, inertial measurement unit, and visual information of a scene by the first autonomous unit during travel along one of the roads in the proto-roadmap;
- determining a ground perspective view including at least road marking information for at least one of the roads in the proto-roadmap from the visual information captured;
- determining a spatial perspective view including objects along at least one of the roads in the proto-roadmap from the visual information captured;
- classifying objects from the spatial perspective view into moving objects and non-moving objects;
- building at least one multi-layer map including a stationary portion consisting of the proto-roadmap, the non-moving objects from the spatial perspective view and the road markings from the ground perspective view, wherein at least one multi-layer map is accurate within 10 centimeters;
- and
- providing the multi-layer map via a communications link to one or more additional autonomous units to guide the one or more additional autonomous units at a future time.
5 more elements
A system, including:
- one or more autonomous units, including a first autonomous unit and a second autonomous unit, each autonomous unit including at least a quad camera visual sensor and at least one selected from a global positioning system and an inertial measurement unit;
- and
- a map server to build multi-layer maps of roads using information sourced by the one or more autonomous units, and configured to:
- distributing a proto-roadmap including only roads to a first autonomous unit that includes at least a quad camera visual sensor and at least one selected from a global positioning system and an inertial measurement unit;
- receiving from the first autonomous unit a set of keyrigs, each keyrig is a set of quad images with a pose generated using combinations of global positioning system, inertial measurement unit, and visual information of a scene by the first autonomous unit during travel along one of the roads in the proto-roadmap;
- determining a ground perspective view including at least road marking information for at least one of the roads in the proto-roadmap from the visual information captured;
- determining a spatial perspective view including objects along at least one of the roads in the proto-roadmap from the visual information captured;
- classifying objects from the spatial perspective view into moving objects and non-moving objects;
- building at least one multi-layer map including a stationary portion consisting of the proto-roadmap, the non-moving objects from the spatial perspective view and the road markings from the ground perspective view, wherein at least one multi-layer map is accurate within 10 centimeters;
- and
- providing the multi-layer map via a communications link to one or more additional autonomous units to guide the one or more additional autonomous units at a future time.
8 more elements
A non-transitory computer readable medium storing instructions for building multi-layer maps of roads using information sourced by one or more moving autonomous units, which instructions when executed by a processor perform:
- distributing a proto-roadmap including only roads to a first autonomous unit that includes at least a quad camera visual sensor and at least one selected from a global positioning system and an inertial measurement unit;
- receiving from the first autonomous unit a set of keyrigs, each keyrig is a set of quad images with a pose generated using combinations of global positioning system, inertial measurement unit, and visual information of a scene by the first autonomous unit during travel along one of the roads in the proto-roadmap;
- determining a ground perspective view including at least road marking information for at least one of the roads in the proto-roadmap from the visual information captured;
- determining a spatial perspective view including objects along at least one of the roads in the proto-roadmap from the visual information captured;
- classifying objects from the spatial perspective view into moving objects and non-moving objects;
- building at least one multi-layer map including a stationary portion consisting of the proto-roadmap, the non-moving objects from the spatial perspective view and the road markings from the ground perspective view, wherein at least one multi-layer map is accurate within 10 centimeters;
- and
- providing the multi-layer map via a communications link to one or more additional autonomous units to guide the one or more additional autonomous units at a future time.
5 more elements
Dependencies are inferred from the claim text.