Event data recordation to identify and resolve anomalies associated with control of driverless vehicles

Patent metadata

Field	Value
Publication number	US-2019220011-A1
Application number	US-201815872555-A
Country	US
Kind code	A1
Filing date	Jan 16, 2018
Priority date	Jan 16, 2018
Publication date	Jul 18, 2019
Grant date	—

Abstract

Various embodiments relate to recording event data to identify and resolve anomalies associated with control of driverless vehicles. Some examples include computing vehicular drive parameters to facilitate driverless transit, monitoring control signals, detecting an event, triggering storage of event data, determining transmission control criteria, and transmitting the event data based on the transmission control criteria. Other examples include receiving event data via a communications network from an autonomous vehicle, identifying a computed vehicular drive parameter, extracting sensor data associated with the event, detecting application of control signals, analyzing the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event, and generating update executable instructions responsive to the type of event.

First claim

What is claimed is:

1 . A method comprising:
computing vehicular drive parameters with which to apply to a vehicle controller to facilitate driverless transit of an autonomous vehicle coextensive with a path of travel; monitoring data representing control signals originating at one or more control devices in the autonomous vehicle; detecting an event; triggering storage of event data; determining transmission control criteria; and transmitting the event data via a communications network to a logic adaption computing platform.

2 . The method of claim 1 wherein the computed vehicular drive parameters comprise one or more of a degree of wheel angle, an amount of throttle, an amount of brake pressure, and a state of transmission and further comprising:
detecting the event in which values of either a subset of the data representing control signals or a subset of the vehicular drive parameters, or both, deviate from a range of expected values;
triggering storage of the event data as representing one or more control signals or one or more vehicular drive parameters, or both, responsive to detecting the event; and
classifying the event as a behavior anomaly.

3 . The method of claim 1 further comprising:
monitoring sensor data signals originating at one or more sensors in the autonomous vehicle;
receiving a subset of sensor data based on the sensor data signals;
identifying object characteristics associated with the subset of sensor data; and
classifying an object based on the identified object characteristics.

4 . The method of claim 4 further comprising one or more of:
detecting at least one control signal of the control signals deviating from a range of values for at least one vehicular drive parameter;
storing data representing the at least one control signal and the least one vehicular drive parameter for transmission in association with the event data;
classifying the event as an environmental anomaly;
selecting data representing a course of action based on the object; and
identifying the course of action based on:
classifying the object; and
selecting at least one set of executable instructions to implement a rule to generate a subset of the vehicular drive parameters based on the object.

5 . The method of claim 6 further comprising:
predicting a subset of trajectories relative to the object;
detecting the event in which a trajectory of the autonomous vehicle is associated with the object, the trajectory being based on the computed vehicular drive parameters;
predicting a path of displacement of the object, the object being a dynamic object;
determining a probability of a trajectory of the autonomous vehicle is associated with the path of displacement; and
selecting data representing a course of action based on the probability and the object.

6 . The method of claim 3 further comprising:
executing instructions to perform vehicle diagnostics to generate data characterizing vehicle anomaly; and
storing characterized vehicle anomaly data for transmission in association with the event data.

7 . The method of claim 3 further comprising:
detecting the event in which values of the sensor data signals deviate from a range of expected sensor values;
classifying the event as a vehicle anomaly;
executing instructions to perform vehicle diagnostics to generate data characterizing vehicle anomaly; and
storing characterized vehicle anomaly data for transmission in association with the event data.

8 . An apparatus comprising:
a memory including executable instructions; and a processor, responsive to executing the instructions, that: computes vehicular drive parameters with which to apply to a vehicle controller to facilitate driverless transit of an autonomous vehicle coextensive with a path of travel; monitors data representing control signals originating at one or more control devices in the autonomous vehicle; detects an event in which values of either a subset of the data representing control signals or a subset of the vehicular drive parameters, or both, deviate from a range of expected values; triggers storage of event data as representing one or more control signals or one or more vehicular drive parameters, or both, responsive to detecting the event; determines transmission control criteria; and transmits the event data via a communications network to a logic adaption computing platform.

9 . The apparatus of claim 8 , wherein the processor further:
classifies the event as a behavior anomaly.

10 . The apparatus of claim 8 , wherein the processor further:
monitors sensor data signals originating at one or more sensors in the autonomous vehicle; receives a subset of sensor data based on the sensor data signals; identifies object characteristics associated with the subset of sensor data; classifies an object based on the identified object characteristics; and classifies the event as an environmental anomaly.

11 . A method comprising:
receiving, by a processor, event data via a communications network from an autonomous vehicle, the event data captured in association with an event at an event recording device in the autonomous vehicle; identifying, by the processor, a subset of computed vehicular drive parameters to facilitate driverless transit of the autonomous vehicle; extracting, by the processor, sensor data associated with the event; detecting, by the processor, application of control signals originating at one or more control devices in the autonomous vehicle; analyzing, by the processor, the control signals, the sensor data, and the subset of computed vehicular drive parameters to identify a type of event; and generating, by the processor, a subset of executable instructions to update executable instructions in an autonomy controller of the autonomous vehicle, the subset of executable instructions being responsive to the type of event.

12 . The method of claim 11 further comprising:
transmitting, by the processor, the subset of executable instructions to the autonomous vehicle to update the executable instructions in the autonomy controller.

13 . The method of claim 11 wherein detecting application of the control signals comprises:
determining, by the processor, human driver intervention and further comprising:
identifying, by the processor, data representing that computed vehicular drive parameters are overridden.

14 . The method of claim 11 wherein detecting application of the control signals comprises:
determining, by the processor, human driver intervention and further comprising:
characterizing, by the processor, values of control signals applied responsive to the human driver intervention relative to the computed vehicular drive parameters.

15 . The method of claim 11 wherein detecting application of the control signals comprises:
determining, by the processor, human driver intervention and further comprising:
correlating, by the processor, the control signals to identify subsets of control signals;
aggregating, by the processor, the control signals in each subset of control signals; and
characterizing, by the processor, behaviors associated with application of the control signals.

16 . The method of claim 11 wherein detecting application of the control signals comprises:
determining, by the processor, human driver intervention and further comprising:
identifying, by the processor, a behavior classification associated with a subset of control signals;
classifying, by the processor, a human driver in accordance with the behavior classification;
ge

Assignees

• Nio Usa Inc

Inventors

• Della Penna Mauro

Classifications

• B60W2556/40

  High definition maps · CPC title

• B60W2556/55

  using telemetry · CPC title

• B60W40/06

  Road conditions · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G08G1/0133

  for classifying traffic situation · CPC title