US 10,831,210 B1Granted

Trajectory generation and optimization using closed-form numerical integration in route-relative coordinates

AssigneeZoox, Inc.

InventorMarin Kobilarov

Life of this patent

Estimating the term…

Loading patent…

Abstract

Techniques are discussed for generating and optimizing a trajectory using closed-form numerical integration in route-relative coordinates. A decision planner component of an autonomous vehicle, for example, can receive or generate a reference trajectory, which may correspond to an ideal route for an autonomous vehicle to traverse through an environment, such as a center of a road segment. Lateral dynamics (e.g., steering angles, curvature values of trajectory segments) and longitudinal dynamics (e.g., velocity and acceleration) can be represented in a single algorithm such that optimizing the reference trajectory (e.g., based on loss functions or costs) can substantially simultaneously optimize the lateral dynamics and longitudinal dynamics in a single convergence operation. In some cases, the trajectory can be used to control the autonomous vehicle to traverse an environment.

Claims20

Dependent claims

A system comprising:

a processor;
and
a computer-readable media storing instructions executable by the processor, wherein the instructions, when executed, cause the system to perform operations comprising:
receiving a reference trajectory comprising a plurality of target velocities and a plurality of target curvatures, wherein a target velocity of the plurality of target velocities is associated with a corresponding target curvature of the plurality of target curvatures;
optimizing a desired trajectory with respect to the reference trajectory to generate an optimized trajectory comprising a plurality of optimized target velocities and a plurality of optimized target curvatures, wherein:
an optimized target velocity of the plurality of optimized target velocities is associated with a corresponding optimized target curvature of the plurality of optimized target curvatures;
an acceleration associated with the plurality of target velocities and the plurality of target curvatures are optimized substantially simultaneously;
and
the optimizing is based at least in part on a closed-form solution of longitudinal dynamics of a vehicle;
and
controlling an autonomous vehicle to traverse an environment based at least in part on the optimized trajectory.

8 more elements

A method comprising:

receiving a reference trajectory comprising a plurality of target velocities and a plurality of target curvatures, wherein a target velocity of the plurality of target velocities is associated with a corresponding target curvature of the plurality of target curvatures;
optimizing a desired trajectory with respect to the reference trajectory to generate an optimized trajectory comprising a plurality of optimized target velocities and a plurality of optimized target curvatures, wherein:
an optimized target velocity of the plurality of optimized target velocities is associated with a corresponding optimized target curvature of the plurality of optimized target curvatures;
an acceleration associated with the plurality of target velocities and the plurality of target curvatures are optimized substantially simultaneously;
and
the optimizing is based at least in part on a closed-form solution of longitudinal dynamics of a robotic platform;
and
controlling the robotic platform to traverse an environment based at least in part on the optimized trajectory.

5 more elements

A non-transitory computer-readable medium storing instructions that, when executed, cause a processor to perform operations comprising:

receiving a reference trajectory comprising a plurality of target velocities and a plurality of target curvatures, wherein a target velocity of the plurality of target velocities is associated with a corresponding target curvature of the plurality of target curvatures;
optimizing a desired trajectory with respect to the reference trajectory to generate an optimized trajectory comprising a plurality of optimized target velocities and a plurality of optimized target curvatures, wherein:
an optimized target velocity of the plurality of optimized target velocities is associated with a corresponding optimized target curvature of the plurality of optimized target curvatures;
an acceleration associated with the plurality of target velocities and the plurality of target curvatures are optimized substantially simultaneously;
and
the optimizing is based at least in part on a closed-form solution of longitudinal dynamics of a robotic platform;
and
controlling the robotic platform to traverse an environment based at least in part on the optimized trajectory.

5 more elements

Dependencies are inferred from the claim text.