Mobility manager trainer for improved autonomy in exception handling

Patent metadata

Field	Value
Publication number	US-12524006-B2
Application number	US-201916398901-A
Country	US
Kind code	B2
Filing date	Apr 30, 2019
Priority date	Apr 30, 2019
Publication date	Jan 13, 2026
Grant date	Jan 13, 2026

Abstract

A method for resolving an exception situation in autonomous driving includes receiving telemetry data from an autonomous vehicle (AV); identifying, using the telemetry data, features and feature values; identifying, using the features and the feature values, a solution to the exception situation; determining a confidence level of the solution; in response to the confidence level exceeding a threshold, transmitting the solution to the AV; and in response to the confidence level not exceeding the threshold, forwarding the solution to a mobility manager, obtaining, from the mobility manager, a validated solution, and transmitting the validated solution to the AV.

First claim

What is claimed is:

1 . A method for resolving an exception situation in autonomous driving, comprising:
receiving, at an autonomous system, a request for assistance from an autonomous vehicle (AV), wherein the request comprises telemetry data that include sensor data from at least one sensor of the AV; identifying, using the telemetry data, features and feature values, wherein the autonomous system is remote from and communicatively connected to the AV, and the autonomous system includes a trajectory planning module that is different and separate from a trajectory planning module of the AV; identifying, by the trajectory planning module of the autonomous system and that accesses and uses at least one of the features and the feature values, an automatic solution to the exception situation; determining, at the autonomous system, a confidence level of the automatic solution; determining, by the autonomous system, whether to transmit the automatic solution to the AV or whether to forward the automatic solution to a mobility manager based on whether the confidence level exceeds a threshold; in response to determining, by the autonomous system, that the confidence level exceeds the threshold, transmitting the automatic solution from the autonomous system to the AV, wherein the automatic solution causes the AV to be autonomously controlled according to the automatic solution; in response to determining, by the autonomous system, that the confidence level does not exceed the threshold:
forwarding the automatic solution from the autonomous system to the mobility manager;
obtaining, at the autonomous system and from the mobility manager, a validated solution; and
transmitting the validated solution to the AV;
subsequent to transmitting, as a transmitted solution, one of the automatic solution or the validated solution to the AV, forwarding the transmitted solution to a second mobility manager for review; receiving a feedback from the second mobility manager regarding the transmitted solution; receiving, from a second AV, a second request for assistance to resolve a second exception situation encountered by the second AV; and generating, using at least the feedback from the second mobility manager, a second automatic solution to the second exception situation.

2 . The method of claim 1 , wherein obtaining, from the mobility manager, the validated solution comprises:
receiving, from the mobility manager, an updated feature value for a feature of the features.

3 . The method of claim 1 , wherein obtaining, from the mobility manager, the validated solution comprises:
receiving, from the mobility manager, a new feature and a new feature value based on the telemetry data, wherein the new feature is not included in the features.

4 . The method of claim 1 , wherein the feedback from the mobility manager relates to at least one of a feature of the features, a feature value of the feature values, or a subset of the telemetry data.

5 . The method of claim 4 , further comprising:
training an exception handling system using the feedback from the mobility manager.

6 . The method of claim 1 , further comprising:
receiving a first instruction from the mobility manager to navigate the AV to a location of the exception situation; and transmitting a second instruction to the AV to navigate to the location of the exception situation.

7 . A system that is remote from and communicatively connected to an autonomous vehicle (AV), comprising:
a memory; and a processor, the processor configured to execute instructions stored in the memory to:
receive, from the AV, a request for assistance, wherein the request comprises telemetry data that include radar measurements;
identify, using the telemetry data, features and feature values;
identify, using instructions of a trajectory planning module that accesses at least one of telemetry data or the features and the feature values, a solution to an exception situation, wherein the trajectory planning module is different and separate from a trajectory planning module of the AV;
determine a confidence level of the solution;
determine whether to transmit the solution to the AV or to forward the solution to a mobility manager based on whether the confidence level exceeds a threshold;
in response to the confidence level exceeding the threshold, transmit the solution to the AV, wherein the solution is configured to cause the AV to be autonomously controlled according to the solution;
in response to the confidence level not exceeding the threshold:
forward the solution to the mobility manager;
obtain, from the mobility manager, a validated solution; and
transmit the validated solution to the AV;

subsequent to transmitting, as a transmitted solution, one of the solution or the validated solution to the AV, forward the transmitted solution to a second mobility manager for review;
receive feedback from the second mobility manager regarding the transmitted solution;
receive, from a second AV, a second request for assistance to resolve a second exception situation encountered by the second AV; and
generate, using at least the feedback from the second mobility manager, a second automatic solution to the second exception situation.

8 . The system of claim 7 , wherein to obtain, from the mobility manager, the validated solution comprises to:
receive, from the mobility manager, an updated feature value for a feature of the features.

9 . The system of claim 7 , wherein to obtain, from the mobility manager, the validated solution comprises to:
receive, from the mobility manager, a new feature and a new feature value based on the telemetry data, wherein the new feature is not included in the features.

10 . The system of claim 7 , wherein the feedback from the mobility manager relates to at least one of a feature of the features, a feature value of the feature values, or a subset of the telemetry data.

11 . The system of claim 10 , wherein the instructions further comprise instructions to:
train an exception handling system using the feedback from the mobility manager.

12 . The system of claim 7 , wherein the instructions further comprise instructions to:
receive a first instruction from the mobility manager to navigate the AV to a location of the exception situation; and transmit a second instruction to the AV to navigate to the location of the exception situation.

13 . A system for resolving exception situations in autonomous driving, comprising:
a first autonomous vehicle (AV) comprising a first processor; and an autonomous system comprising a second processor,
wherein the autonomous system is remote from and communicatively connected to the first AV,
wherein the first processor of the first AV is configured to:
obtain, using instructions of a trajectory planning module of the first AV that uses sensor data comprising at least one of LiDAR or radar data, a solution for resolving a first exception situation;
responsive to a determination that a risk associated with the solution exceeds a risk threshold, initiate a request for assistance to the autonomous system;
receive a transmitted solution from the autonomous system; and
autonomously control the first AV according to the transmitted solution; and

wherein the second processor of the autonomous system is configured to:
receive, from the first AV, the request for assistance to resolve the first exception situation encountered by the first AV;
generate, using instructions of a trajectory planning module of the autonomous system that is different from the trajectory planning module of the first AV and that uses th

Assignees

• Nissan North America Inc
• Renault Sas

Inventors

• Poulet Kevin
• Witwicki Stefan
• Bentahar Omar
• Cesafsky Laura

Classifications

• G08G1/202 Primary

  Dispatching vehicles on the basis of a location, e.g. taxi dispatching · CPC title

• G08G1/096775

  where the origin of the information is a central station · CPC title

• G08G1/096725

  where the received information generates an automatic action on the vehicle control · CPC title

• G08G1/0145

  for active traffic flow control · CPC title

• G08G1/0133

  for classifying traffic situation · CPC title