Back to results
US 11,618,453 B2Granted
Grid-based road model with multiple layers
AssigneeAptiv Technologies AG
InventorsBin Jia, Sana Sarfraz, David A. Schwartz, Kumar Vishwajeet
Life of this patent
Estimating the term…
Abstract
This document describes techniques, apparatuses, and systems for a grid-based road model with multiple layers. An example road-perception system generates a roadway grid representation that includes multiple cells. The road-perception system uses data from multiple information sources to generate a road model that includes multiple layers. Each layer represents a roadway attribute of each cell in the grid and includes one or more layer hypotheses. In this way, the described techniques and systems can provide an accurate and reliable road model and quantify uncertainty therein.
Claims20
A method comprising:
- generating, by a road-perception system of a vehicle, a grid representation of a roadway, the grid representation including multiple cells;
- generating, by the road-perception system and based on data from multiple information sources, a road model for the roadway, the road model including at least two different layers that represent different respective roadway attributes of the multiple cells in the grid representation of the roadway, the at least two different layers including, for each cell of the multiple cells in each layer of the different layers, at least one respective layer hypothesis that indicates a potential attribute state for that cell;
- determining, by the road-perception system, respective mass values associated with each of the at least one respective layer hypothesis, the respective mass values indicating confidence associated with the data contributing to the at least one respective layer hypothesis;
- determining, by the road-perception system and using the respective mass values, belief parameters and plausibility parameters associated with each of the at least one respective layer hypothesis, the belief parameters indicating a confidence in the potential attribute state for that cell, the plausibility parameters indicating a likelihood in the potential attribute state being accurate for that cell;
- determining whether the belief parameters and the plausibility parameters associated with at least one layer hypothesis satisfy a respective threshold value;
- and
- responsive to determining that the belief parameters and the plausibility parameters associated with at least one layer hypothesis satisfy the respective threshold value, using the at least one layer hypothesis as an input to an autonomous-driving system or an assisted-driving system that operates the vehicle on the roadway.
4 more elements
A computer-readable storage media comprising computer-executable instructions that, when executed, cause a processor in a vehicle to:
- generate a grid representation of a roadway, the grid representation including multiple cells;
- generate, based on data from multiple information sources, a road model for the roadway, the road model including at least two different layers that represent different respective roadway attributes of the multiple cells in the grid representation of the roadway, the at least two different layers including, for each cell of the multiple cells in each layer of the different layers, at least one respective layer hypothesis that indicates a potential attribute state for that cell;
- determine respective mass values associated with each of the at least one respective layer hypothesis, the respective mass values indicating confidence associated with the data contributing to the at least one respective layer hypothesis;
- determine, using the respective mass values, belief parameters and plausibility parameters associated with each of the at least one respective layer hypothesis, the belief parameters indicating a confidence in the potential attribute state for that cell, the plausibility parameters indicating a likelihood in the potential attribute state being accurate for that cell;
- determine whether the belief parameters and the plausibility parameters associated with at least one layer hypothesis satisfy a respective threshold value;
- and
- responsive to a determination that the belief parameters and the plausibility parameters associated with at least one layer hypothesis satisfy the respective threshold value, use the at least one layer hypothesis as an input to an autonomous-driving system or an assisted-driving system that operates the vehicle on the roadway.
4 more elements
Dependencies are inferred from the claim text.