Nissan North America, Inc.

Apple Inc.

Nicolas F Meuleau

Daisuke Saito

Siddharth Thakur

Naoki Kojo

Nikhil Lele

Martin Levihn

Luke Burke Johnson

Joshua D Redding

Sebastian Brechtel

Luke B Johnson

A behavior planner for a vehicle generates a plurality of conditional action sequences of the vehicle using a tree search algorithm and heuristics obtained from one or more machine learning models. Each sequence corresponds to a sequence of anticipated states of the vehicle. At least some of the action sequences are provided to a motion selector of the vehicle. The motion selector generates motion-control directives based on the received conditional action sequences and on data received from one or more sensors of the vehicle, and transmits the directives to control subsystems of the vehicle.

Decision making for autonomous vehicle motion control

A method and apparatus for autonomous vehicle routing and navigation using passenger docking locations are disclosed. Autonomous vehicle routing and navigation using passenger docking locations may include an autonomous vehicle identifying map information representing a vehicle transportation network, the vehicle transportation network including a primary destination and a docking location, wherein identifying the map information includes identifying the map information such that the map information includes docking location information representing the docking location. The autonomous vehicle may identify the docking location as a target docking location for the primary destination based on the map information, generate, based on the map information, route information representing a route for the autonomous vehicle to traverse the vehicle transportation network from an origin in the vehicle transportation network to the target docking location, and traverse the vehicle transportation network from the origin to the target docking location in accordance with the route information.

Autonomous vehicle routing and navigation using passenger docking locations

An autonomous vehicle may include a processor configured to execute instructions to identify, from vehicle transportation network information representing a vehicle transportation network, first and second location information representing a first and second location in the vehicle transportation network, and generate route information representing a route from the first location to the second location via the vehicle transportation network, wherein the route information includes first lane information indicating that the route includes a first lane of a road segment, wherein the vehicle transportation network information includes second lane information representing a second lane of the road segment and adjacent to the first lane, the route having a minimal expected cost among available candidate routes. The autonomous vehicle may include a trajectory controller configured to operate the autonomous vehicle to traverse the vehicle transportation network from the first location to the second location via the route based on the route information.

Autonomous vehicle lane routing and navigation

A method and apparatus for passenger docking location selection are disclosed. Passenger docking location selection may include an autonomous vehicle identifying transportation network information representing a vehicle transportation network, the vehicle transportation network including a primary destination, wherein identifying the transportation network information includes identifying the transportation network information such that it includes docking location information representing a plurality of docking locations, wherein each docking location corresponds with a respective location in the vehicle transportation network, and such that at least one docking location is associated with the primary destination, determining a target docking location for the primary destination based on the transportation network information and pedestrian travel time, identifying a first route from an origin to the target docking location in the vehicle transportation network using the transportation network information, and traveling from the origin to the target docking location using the first route.

Passenger docking location selection

A method and apparatus for associating passenger docking locations with destinations are disclosed. Associating passenger docking locations with destinations may include an autonomous vehicle identifying transportation network information representing a vehicle transportation network, including a primary destination, wherein identifying the transportation network information includes identifying the transportation network information such that the transportation network information includes docking location information representing a plurality of docking locations, wherein each docking location corresponds with a respective location in the vehicle transportation network, and such that at least one docking location from the plurality of docking locations is associated with the primary destination. The autonomous vehicle may determine a target docking location from the plurality of docking locations for the primary destination based on the transportation network information, identify a route from an origin to the target docking location, and travel from the origin to the target docking location using the route.

Associating passenger docking locations with destinations

A method and apparatus for autonomous vehicle routing and navigation using passenger docking locations are disclosed. Autonomous vehicle routing and navigation using passenger docking locations may include an autonomous vehicle identifying vehicle transportation network information representing a vehicle transportation network, the vehicle transportation network including a primary destination, wherein identifying the vehicle transportation network information includes identifying the vehicle transportation network information such that it includes docking location information representing a plurality of docking locations, wherein each docking location corresponds with a respective location in the vehicle transportation network. The autonomous vehicle may determine a target docking location for the primary destination based on the vehicle transportation network information, identify a route from an origin to the target docking location in the vehicle transportation network using the vehicle transportation network information, and travel from the origin to the target docking location using the route.

A method and apparatus for associating passenger docking locations with destinations using vehicle transportation network partitioning are disclosed. Associating passenger docking locations with destinations using vehicle transportation network partitioning may include an autonomous vehicle identifying transportation network information representing a vehicle transportation network, the vehicle transportation network including a primary destination, wherein identifying the transportation network information includes identifying the transportation network information such that it includes docking location information representing a plurality of docking locations, wherein each docking location corresponds with a respective location in the vehicle transportation network, such that at least one docking location is associated with the primary destination based on pedestrian travel time, determining a target docking location, identifying a route from an origin to the target docking location in the vehicle transportation network using the transportation network information, and traveling from the origin to the target docking location using the route.

Associating passenger docking locations with destinations using vehicle transportation network partitioning

A method and apparatus for autonomous vehicle lane routing and navigation are provided. Autonomous vehicle lane routing and navigation may include identifying vehicle transportation network information including road segment information and lane information, wherein the road segment information for at least one road segment from the plurality of road segments includes lane information representing at least two adjacent lanes, identifying an origin, identifying a destination, generating a plurality of candidate routes from the origin to the destination, wherein each route from the plurality of routes indicates a distinct combination of road segments and lanes, and wherein at least one candidate route from the plurality of candidate routes includes at least one of the adjacent lanes, identifying an optimal route from the plurality of candidate routes, the optimal route having a minimal route cost, and operating the autonomous vehicle to travel from the origin to the destination using the optimal route.

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.

Growing community of inventors

San Francisco, CA, United States of America

Nicolas F Meuleau