发明名称 |
Vehicle trajectory optimization for autonomous vehicles |
摘要 |
A method for controlling an autonomous vehicle includes obtaining information describing a roadway; defining a plurality of layers along the roadway between a starting position and a goal position, each layer having a first width, and each layer having a plurality of nodes that are spaced from one another transversely with respect to the roadway within the first width; and determining a first trajectory from the starting position to the goal position, by minimizing a cost value associated with traversing the layers. Determining the first trajectory includes, for each layer, determining layer-specific weighting factors for each of a plurality of cost components, based on information associated with the respective layer, and determining, for each node of the respective layer, a cost for travelling to one or more of the nodes in a subsequent layer based on the plurality of cost components and the layer-specific weighting factors. |
申请公布号 |
US9405293(B2) |
申请公布日期 |
2016.08.02 |
申请号 |
US201414291411 |
申请日期 |
2014.05.30 |
申请人 |
NISSAN NORTH AMERICA, INC |
发明人 |
Meuleau Nicolas |
分类号 |
G05D1/00;G01C21/34;G06Q10/04;G05D1/02;G01C21/26;B62D15/00 |
主分类号 |
G05D1/00 |
代理机构 |
Young Basile Hanlon & MacFarlane, P.C. |
代理人 |
Young Basile Hanlon & MacFarlane, P.C. |
主权项 |
1. A method for controlling an autonomous vehicle, comprising:
obtaining, by one or more processors, information describing a roadway from a starting position to a goal position; defining, by the one or more processors, a plurality of layers along the roadway at spaced locations between the starting position and the goal position, each layer having a respective first width, and each layer having a plurality of nodes that are spaced from one another transversely with respect to the roadway within the respective first width; determining, by the one or more processors, a trajectory from the starting position to the goal position, by minimizing a cost value associated with traversing the layers, including, for each layer:
obtaining a plurality of cost components;obtaining information associated with the respective layer;determining layer-specific weighting factors for each of the plurality of cost components, based on the information associated with the respective layer, anddetermining, for each node of the respective layer, a cost for travelling to one or more of the nodes in a subsequent layer based on the plurality of cost components and the layer-specific weighting factors; defining a plurality of refinement layers along the roadway at spaced locations between the starting position and the goal position, each refinement layer having a respective second width that extends transversely outward from the trajectory and is less than or equal to a transverse width between transversely adjacent pairs of the nodes from each layer of the plurality of layers, and each layer having a plurality of refinement nodes that are spaced from one another transversely with respect to the roadway; modifying the trajectory by minimizing a cost value associated with traversing the refinement layers, wherein modifying the trajectory includes, for each refinement layer:
determining refinement layer-specific weighting factors for each of a plurality of refinement cost components, based on information associated with the respective refinement layer, anddetermining, for each refinement node of the respective refinement layer, a cost for travelling to one or more of the refinement nodes in a subsequent refinement layer based on the plurality of refinement cost components and the refinement layer-specific weighting factors; outputting a steering control signal based on the trajectory to a steering device for controlling operation of the steering device; and changing a steering angle of at least one steered wheel using the steering device in response to the steering control signal. |
地址 |
Franklin TN US |