Autonomous vehicle lane routing and navigation

• US 9,939,284 B2
• Filed: 08/01/2016
• Issued: 04/10/2018
• Est. Priority Date: 05/30/2014
• Status: Active Grant

• Current Assignee: Nissan Motor Co., Ltd.
• Original Assignee: Nissan North America Incorporated (Nissan Motor Co., Ltd.)
• Inventors: Meuleau, Nicolas
• Primary Examiner(s): Black, Thomas G
• Assistant Examiner(s): Huynh, Luat T
• Application Number:
  US15/225,151
• Publication Number:
  US 20160341565A1
• Time in Patent Office: 617 Days
• Field of Search: 701 23, 701 25
• CPC Class Codes: G01C 21/3453 Special cost functions, i.e. other than distance or default speed limit of road segments
• CPC Class Codes: G01C 21/3469 Fuel consumption; Energy use; Emission aspects
• CPC Class Codes: G01C 21/3658 Lane guidance
• CPC Class Codes: G05D 1/0088 characterized by the autonomous decision making process, e.g. artificial intelligence, predefined behaviours using knowledge based models G06N5/00
• CPC Class Codes: G05D 1/0217 in accordance with energy consumption, time reduction or distance reduction criteria

Abstract

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.

Claims

1. An autonomous vehicle comprising:

a processor configured to execute instructions stored on a non-transitory computer readable medium to;

identify, from vehicle transportation network information representing a vehicle transportation network, first location information representing a first location in the vehicle transportation network;

identify, from the vehicle transportation network information, second location information representing a second location in the vehicle transportation network; and

generate, based on the vehicle transportation network information, 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; and

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.

2. The autonomous vehicle of claim 1, wherein the vehicle transportation network information indicates that the first lane has a first direction of travel and the second lane has the first direction of travel.

3. The autonomous vehicle of claim 1, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:

generate the route information using a Markov decision process.

4. The autonomous vehicle of claim 1, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to:

generate the route information using a discrete time stochastic control process.

5. The autonomous vehicle of claim 1, wherein the vehicle transportation network information includes waypoint information representing a first waypoint for the first lane, and wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to generate the route information by:

identifying a first routing state, the first routing state including an indication of the road segment, an indication of the first lane, and an indication of the first waypoint;

identifying a second routing state, the second routing state including an indication of a second road segment, an indication of a third lane of the second road segment, and an indication of a second waypoint for the second lane such that the second waypoint is immediately adjacent to the first waypoint; and

estimating an action cost representing a cost to transition from the first routing state to the second routing state.

6. The autonomous vehicle of claim 5, wherein estimating the action cost includes evaluating at least one of a plurality of cost metrics.

7. The autonomous vehicle of claim 6, wherein the plurality of cost metrics includes at least one of a distance cost metric, a duration cost metric, a fuel cost metric, or an acceptability cost metric.

8. The autonomous vehicle of claim 7, wherein estimating the action cost includes calculating a cost function that is minimizing with respect to the distance cost metric, minimizing with respect to the duration cost metric, minimizing with respect to the fuel cost metric, and maximizing with respect to the acceptability cost metric.

9. The autonomous vehicle of claim 6, wherein estimating the action cost includes identifying a weighting factor associated with each respective cost metric from the plurality of cost metrics.

10. The autonomous vehicle of claim 6, wherein estimating the action cost includes generating a plurality of weighted cost metrics such that each weighted cost metric from the plurality of weighted cost metrics is based on a product of a respective cost metric from the plurality of cost metrics and a weighting factor associated with the respective cost metric.

11. The autonomous vehicle of claim 10, wherein estimating the action cost includes calculating a sum of the plurality of weighted cost metrics.

12. An autonomous vehicle comprising:

a processor configured to execute instructions stored on a non-transitory computer readable medium to;

generate, based on vehicle transportation network information representing a vehicle transportation network, route information representing a route via the vehicle transportation network from a first location in the vehicle transportation network to a second location in the vehicle transportation network, such that the route information includes first lane information indicating that the route includes a first lane having a first direction of travel, wherein the vehicle transportation network information includes second lane information representing a second lane immediately adjacent to the first lane and having the first direction of travel, road segment information representing a road segment of the vehicle transportation network that includes the first lane and the second lane, and waypoint information representing a first waypoint for the first lane, by;

identifying a first routing state, the first routing state including an indication of the road segment, an indication of the first lane, and an indication of the first waypoint;

identifying a second routing state, the second routing state including an indication of a second road segment, an indication of a third lane of the second road segment, and an indication of a second waypoint for the second lane such that the second waypoint is immediately adjacent to the first waypoint; and

estimating an action cost representing a cost to transition from the first routing state to the second routing state, wherein estimating the action cost includes evaluating at least one of a plurality of cost metrics, and wherein the plurality of cost metrics includes at least one of a distance cost metric, a duration cost metric, a fuel cost metric, or an acceptability cost metric; and

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.

13. The autonomous vehicle of claim 12, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to generate the route information by:

generating candidate route information representing distinct candidate routes via the vehicle transportation network from the first location in the vehicle transportation network to a second location in the vehicle transportation network, wherein the route is one of the distinct candidate routes; and

identifying the route information representing the route from the candidate route information such that the route has a minimal expected cost among the distinct candidate routes.

14. The autonomous vehicle of claim 13, wherein the processor is configured to execute instructions stored on the non-transitory computer readable medium to identify the route information using a Markov decision process or a discrete time stochastic control process.

15. The autonomous vehicle of claim 12, wherein estimating the action cost includes calculating a cost function that is minimizing with respect to the distance cost metric, minimizing with respect to the duration cost metric, minimizing with respect to the fuel cost metric, and maximizing with respect to the acceptability cost metric.

16. An autonomous vehicle comprising:

a processor configured to execute instructions stored on a non-transitory computer readable medium to;

identify candidate routes for a vehicle to traverse a vehicle transportation network from a first location in the vehicle transportation network to a second location in the vehicle transportation network by generating candidate route information representing each respective candidate route from the candidate routes based on vehicle transportation network information representing the vehicle transportation network; and

identify route information from the candidate route information representing a route from the candidate routes, the route information including first lane information indicating that the route includes a first lane having a first direction of travel, wherein the vehicle transportation network information includes second lane information representing a second lane immediately adjacent to the first lane in the vehicle transportation network and having the first direction of travel, road segment information representing a road segment of the vehicle transportation network that includes the first lane and the second lane, waypoint information representing a first waypoint for the first lane, by;

identifying a first routing state, the first routing state including an indication of the road segment, an indication of the first lane, and an indication of the first waypoint;

identifying a second routing state, the second routing state including an indication of a second road segment, an indication of a third lane of the second road segment, and an indication of a second waypoint for the second lane such that the second waypoint is immediately adjacent to the first waypoint; and

estimating an action cost representing a cost to transition from the first routing state to the second routing state, wherein estimating the action cost includes evaluating at least one of a plurality of cost metrics, and wherein the plurality of cost metrics includes at least one of a distance cost metric, a duration cost metric, a fuel cost metric, or an acceptability cost metric; and

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.