Back to results
US 12,222,722 B2Granted
Platform for path planning system development for automated driving system
AssigneeZenseact AB
InventorsMagnus Gyllenhammar, Carl Zandén, Majid Khorsand Vakilzadeh
Life of this patent
Estimating the term…
Abstract
The present invention relates to a method and apparatus that utilize production vehicles to develop new path planning features for Automated Driving Systems (ADSs) by using federated learning. To achieve this the “under-test” path planning module's output is evaluated in closed-loop in order to produce a cost-function that is subsequently used to update or train a path planning model of the path planning development-module.
Claims15
A method performed by an in-vehicle computing system for automated development of a path planning development-module of a vehicle, wherein the vehicle is equipped with an Automated Driving System, ADS, the method comprising:
- obtaining a candidate path from the path planning development-module, wherein the path planning development-module is configured to generate the candidate path for execution by the vehicle based on a path planning model and data indicative of the surrounding environment of the vehicle;
- obtaining a risk map of a surrounding environment of the vehicle, wherein the risk map is formed based on an actuation capability of the vehicle and a location of free-space areas in the surrounding environment, the actuation capability including an uncertainty estimation for the actuation capability and the location of free-space areas comprising an uncertainty estimation for the estimated location of free-space areas,
- wherein the risk map comprises a risk parameter for each of a plurality of area segments comprised in the surrounding environment of the vehicle, and
- wherein the risk map further has a temporal component indicative of a time evolution of the risk parameters of the area segments based on a predicted temporal evolution of the free-space areas for at least a duration of time defined by a predicted duration of the candidate path;
- determining a risk value for the candidate path based on the risk parameters of the area segments to be intersected by the candidate path;
- and
- if the determined risk value satisfies at least one risk criterion, the method further comprises:
- generating, at an output, a first control signal indicative of an instruction for the ADS to execute the candidate path;
- obtaining at least one quality parameter of the executed candidate path, wherein the at least one quality parameter is indicative of a performance of the candidate path in terms of quality and/or comfort of the executed candidate path;
- determining a cost function indicative of a performance of the path planning development-module based on the obtained at least one quality parameter;
- and
- updating one or more parameters of the path planning model by means of an optimization algorithm configured to optimize the determined cost function.
9 more elements
An apparatus for automated development a path planning development-module of a vehicle, wherein the vehicle is equipped with an Automated Driving System, ADS, the apparatus comprising control circuitry configured to:
- obtain a candidate path from the path planning development-module, wherein the path planning development-module is configured to generate the candidate path for execution by the vehicle based on a path planning model and data indicative of the surrounding environment of the vehicle;
- obtain a risk map of a surrounding environment of the vehicle, wherein the risk map is formed based on an actuation capability of the vehicle and a location of free-space areas in the surrounding environment, the actuation capability including an uncertainty estimation for the actuation capability and the location of free-space areas comprising an uncertainty estimation for the estimated location of free-space areas,
- wherein the risk map comprises a risk parameter for each of a plurality of area segments comprised in the surrounding environment of the vehicle, and
- wherein the risk map further has a temporal component indicative of a time evolution of the risk parameters of the area segments based on a predicted temporal evolution of the free-space areas for at least a duration of time defined by a predicted duration of the candidate path;
- determine a risk value for the candidate path based on the risk parameters of the area segments to be intersected by the candidate path;
- and
- if the determined risk value satisfies at least one risk criterion, the control circuitry is further configured to:
- generate, at an output, a first control signal indicative of an instruction for the ADS to execute the candidate path;
- obtain at least one quality parameter of the executed candidate path, wherein the at least one quality parameter is indicative of a performance of the candidate path in terms of quality and/or comfort of the executed candidate path;
- determine a cost function indicative of a performance of the path planning development-module based on the obtained at least one quality parameter;
- and
- update one or more parameters of the path planning model by means of an optimization algorithm configured to optimize the determined cost function.
9 more elements
A vehicle comprising:
- a set of vehicle-mounted sensors configured to monitor a surrounding environment of the vehicle;
- an automated driving system, ADS, comprising:
- a perception system configured to generate perception data based on sensor data obtained from one or more of the set of vehicle-mounted sensors;
- a production-platform path planner;
- a path planning development-module configured to generate a candidate path for execution by the vehicle;
- and
- an apparatus for automated development the path planning development-module of the vehicle, wherein the vehicle is equipped with ADS, the apparatus comprising control circuitry configured to:
- obtain a candidate path from the path planning development-module, wherein the path planning development-module is configured to generate the candidate path for execution by the vehicle based on a path planning model and data indicative of the surrounding environment of the vehicle;
- obtain a risk map of a surrounding environment of the vehicle, wherein the risk map is formed based on an actuation capability of the vehicle and a location of free-space areas in the surrounding environment, the actuation capability including an uncertainty estimation for the actuation capability and the location of free-space areas comprising an uncertainty estimation for the estimated location of free-space areas,
- wherein the risk map comprises a risk parameter for each of a plurality of area segments comprised in the surrounding environment of the vehicle, and
- wherein the risk map further has a temporal component indicative of a time evolution of the risk parameters of the area segments based on a predicted temporal evolution of the free-space areas for at least a duration of time defined by a predicted duration of the candidate path;
- determine a risk value for the candidate path based on the risk parameters of the area segments to be intersected by the candidate path;
- and
- if the determined risk value satisfies at least one risk criterion, the control circuitry is further configured to:
- generate, at an output, a first control signal indicative of an instruction for the ADS to execute the candidate path;
- obtain at least one quality parameter of the executed candidate path, wherein the at least one quality parameter is indicative of a performance of the candidate path in terms of quality and/or comfort of the executed candidate path;
- determine a cost function indicative of a performance of the path planning development-module based on the obtained at least one quality parameter;
- and
- update one or more parameters of the path planning model by means of an optimization algorithm configured to optimize the determined cost function.
16 more elements
Dependencies are inferred from the claim text.