Techniques for detecting road blockages and generating alternative routes

Patent metadata

Field	Value
Publication number	US-12195033-B2
Application number	US-202117459829-A
Country	US
Kind code	B2
Filing date	Aug 27, 2021
Priority date	Aug 27, 2021
Publication date	Jan 14, 2025
Grant date	Jan 14, 2025

Abstract

The present disclosure involves systems and methods for detecting road blockages and generating alternative routes. In some cases, a system detects, based at least in part on sensor data associated with an autonomous vehicle, a portion of an environment that impedes a planned path of the autonomous vehicle. The system determines a semantic classification associated with the portion of the environment and transmits a re-routing request comprising the semantic classification to one or more remote computing devices. The system receives an instruction associated with navigating the autonomous vehicle around the portion of the environment from the remote computing devices, where the instruction includes an alternative route determined from a plurality of alternative routes. The system further controls the autonomous vehicle to navigate around the portion of the environment based at least in part on the instruction.

First claim

What is claimed is:

1. A system comprising:
one or more processors; and
one or more non-transitory computer-readable media storing instructions executable by the one or more processors, wherein the instructions, when executed, cause the system to perform operations comprising:
detecting, based at least in part on sensor data associated with an autonomous vehicle, a blocked portion in an environment of the autonomous vehicle;
determining that the blocked portion impedes a planned path of the autonomous vehicle;
determining a semantic classification associated with the blocked portion of the environment;
determining, based at least in part on determining that the blocked portion impedes the planned path, a plurality of alternative paths to navigate the autonomous vehicle around the blocked portion, wherein determining that the blocked portion impedes the planned path is based at least in part on the semantic classification associated with the blocked portion;
transmitting, to one or more remote computing devices, a re-routing request and alternative routing data representing the plurality of alternative paths;
receiving, from the one or more remote computing devices, an instruction associated with navigating the autonomous vehicle around the blocked portion; and
controlling, based at least in part on the instruction, the autonomous vehicle to navigate around the blocked portion.

2. The system of claim 1 , wherein
the semantic classification comprises one of a subset of classes; and
wherein determining the plurality of alternative paths is further based at least in part on a determination that the semantic classification comprises the one of the subset of classes.

3. The system of claim 1 , the operations further comprising:
determining that the autonomous vehicle is operating in a first lane;
determining that the planned path of the autonomous vehicle includes a lane change into a second lane that is different from the first lane;
determining that the blocked portion is located in the second lane proximate the autonomous vehicle; and
determining, based on an overlap between the blocked portion and the planned path, that the autonomous vehicle is unable to perform the lane change.

4. The system of claim 1 , wherein the one or more remote computing devices are associated with a remote operator and the instruction comprises at least one of:
an indication of determination of an alternative path of the plurality of alternative paths;
a re-route path that is generated by the remote operator and is different from the plurality of alternative paths; or
an indication for the autonomous vehicle to continue to wait an additional period of time.

5. The system of claim 1 , wherein the plurality of alternative paths are determined based at least in part on one or more of:
a time cost;
a number of lane changes; or
a number of turns.

6. The system of claim 1 , the operations further comprising:
determining a critical point based on the blocked portion; and
determining to stop the autonomous vehicle at least a threshold distance away from the critical point prior to receiving the instruction.

7. A method comprising:
detecting, based at least in part on sensor data associated with an autonomous vehicle, a portion of an environment that impedes a planned path of the autonomous vehicle;
determining a semantic classification associated with the portion of the environment;
transmitting, to one or more remote computing devices, a re-routing request comprising the semantic classification;
receiving, from the one or more remote computing devices, an instruction associated with navigating the autonomous vehicle around the portion of the environment, the instruction comprising an alternative route determined from a plurality of alternative routes, wherein the instruction is based at least in part on the semantic classification associated with the portion of the environment; and
controlling, based at least in part on the instruction, the autonomous vehicle to navigate around the portion of the environment.

8. The method of claim 7 , further comprising:
determining that the semantic classification comprises one of a subset of classes; and
wherein the re-routing request comprises the plurality of alternative routes.

9. The method of claim 7 , further comprising:
determining that the autonomous vehicle is operating in a first lane;
determining that the planned path of the autonomous vehicle includes a lane change into a second lane that is different from the first lane;
determining that the portion of the environment that impedes the planned path of the autonomous vehicle is associated with the second lane proximate the autonomous vehicle; and
determining, based on an overlap between the portion of the environment and the planned path, that the autonomous vehicle is unable to perform the lane change,
wherein the re-routing request is transmitted based on a determination that the autonomous vehicle is unable to perform the lane change.

10. The method of claim 7 , further comprising:
determining that the autonomous vehicle is operating in a first lane;
determining that the planned path of the autonomous vehicle includes a junction linking the first lane to a second lane;
determining that the portion of the environment impedes the planned path of the autonomous vehicle is associated with the junction or the second lane; and
determining that the autonomous vehicle is unable to travel through the junction,
wherein the re-routing request is transmitted based on a determination that the autonomous vehicle is unable to travel through the junction.

11. The method of claim 7 , wherein the one or more remote computing devices are associated with a remote operator and the alternative route comprises at least one of:
a first route selected by the remote operator from one or more alternative routes provided in the re-routing request; or
a second route that is generated by the remote operator and is different from the one or more alternative routes.

12. The method of claim 7 , wherein the plurality of alternative routes are determined based at least in part on one or more of:
a time cost;
a number of turns; or
a number of lane changes.

13. The method of claim 7 , further comprising:
determining a critical point based on the portion of the environment that impedes the planned path of the autonomous vehicle; and
determining to stop the autonomous vehicle at least a threshold distance away from the critical point.

14. A non-transitory computer-readable media storing instructions that, when executed by one or more processors, cause one or more computing devices to perform operations comprising:
detecting, based at least in part on sensor data associated with an autonomous vehicle, a portion of an environment that impedes a planned path of the autonomous vehicle;
determining a semantic classification associated with the portion of the environment that impedes the planned path of the autonomous vehicle;
transmitting, to one or more remote computing devices, a re-routing request comprising the semantic classification;
receiving, from the one or more remote computing devices, an instruction associated with navigating the autonomous vehicle around the portion of the environment, the instruction comprising an alternative route determined from a plurality of alternative routes, wherein the instruction is based at least in part on the semantic classification associated with the portion of the environment; and
controlling, based at least in part on the instruction, the autonomous vehicle to navigate around the por

Assignees

• Zoox Inc

Inventors

• Garg Lakshay
• Gogna Ravi
• Kiiski Joona Markus Petteri
• Li Caili

Classifications

• B60W30/18163

  Lane change; Overtaking manoeuvres · CPC title

• B60W2552/10

  Number of lanes · CPC title

• B60W2552/50

  Barriers · CPC title

• B60W60/001 Primary

  Planning or execution of driving tasks · CPC title

• B60W60/007 Primary

  Emergency override (Handing over between remote control and on-board control or handing over between remote control arrangements G05D1/227) · CPC title