Controlling driving modes of self-driving vehicles

Patent metadata

Field	Value
Publication number	US-9785145-B2
Application number	US-201514820620-A
Country	US
Kind code	B2
Filing date	Aug 7, 2015
Priority date	Aug 7, 2015
Publication date	Oct 10, 2017
Grant date	Oct 10, 2017

Abstract

A computer-implemented method, system, and/or computer program product controls a driving mode of a self-driving vehicle (SDV). Sensor readings describe a current condition of a roadway, which is part of a planned route of a self-driving vehicle (SDV). One or more processors compare a control processor competence level of the on-board SDV control processor that autonomously controls the SDV to a human driver competence level of a human driver in controlling the SDV under the current condition of the roadway. One or more processors then selectively assign control of the SDV to the on-board SDV control processor or to the human driver based on which of the control processor competence level and the human driver competence level is relatively higher to the other.

First claim

What is claimed is:

1. A computer-implemented method for controlling a driving mode of a self-driving vehicle (SDV), the computer-implemented method comprising:
receiving, by one or more processors, sensor readings from a sensor, wherein the sensor readings describe a current condition of a roadway, wherein the roadway is part of a planned route of a self-driving vehicle (SDV), wherein the SDV is capable of being operated in autonomous mode by an on-board SDV control processor, wherein a driving mode module selectively controls whether the SDV is operated in the autonomous mode or in manual mode, and wherein the SDV is controlled by a human driver of the SDV if in the manual mode;
determining, by one or more processors, a control processor competence level of the on-board SDV control processor, wherein the control processor competence level describes a competence level of the on-board SDV control processor in controlling the SDV under the current condition of the roadway;
receiving, by one or more processors, a driver profile of the human driver of the SDV, wherein the driver profile describes a human driver competence level of the human driver in controlling the SDV under the current condition of the roadway;
comparing, by one or more processors, the control processor competence level to the human driver competence level; and
selectively assigning, by one or more processors, control of the SDV to the on-board SDV control processor or to the human driver based on which of the control processor competence level and the human driver competence level is relatively higher to one another.

2. The processor-implemented method of claim 1 , further comprising:
receiving, by one or more processors, a manual input, wherein the manual input describes the current condition of the roadway, and wherein the manual input overrides sensor readings that describe the current condition of the roadway;
defining, by one or more processors, an updated current condition of the roadway based on the manual input;
re-determining, by one or more processors, the control processor competence level of the on-board SDV control processor based on the updated current condition of the roadway from the manual input to create a re-determined control processor competence level;
redefining, by one or more processors, the driver profile of the human driver of the SDV based on the updated current condition of the roadway from the manual input to create a redefined human driver competence level;
comparing, by one or more processors, the re-determined control processor competence level to the redefined human driver competence level; and
selectively assigning, by one or more processors, control of the SDV to the on-board SDV control processor or the human driver based on which of the re-determined control processor competence level and the redefined human driver competence level is relatively higher to one another.

3. The processor-implemented method of claim 1 , wherein the sensor is mounted on the SDV, wherein the sensor readings describe environmental conditions of the SDV in real time, and wherein the processor-implemented method further comprises:
receiving, by one or more processors, an environmental report from an environmental reporting service, wherein the environmental report describes a general condition for the roadway;
comparing, by one or more processors, environmental information from the environmental report to the sensor readings that describe the environmental conditions of the SDV in real time; and
in response to the environmental report disagreeing with the sensor readings, disregarding, by one or more processors, the sensor readings from the sensor and using the environmental report to describe the current condition of the roadway.

4. The processor-implemented method of claim 1 ,
retrieving, by one or more processors, driver profile information about the human driver of the SDV;
assigning, by one or more processors, the human driver of the SDV to a cohort of drivers traveling on the roadway in multiple SDVs, wherein the human driver of the SDV shares more than a predetermined quantity of traits with members of the cohort of drivers;
retrieving, by one or more processors, traffic pattern data for the multiple SDVs occupied by the cohort of drivers traveling on the roadway;
examining, by one or more processors, the traffic pattern data to determine a first traffic flow of the multiple SDVs occupied by members of the cohort of drivers, wherein the multiple SDVs in the first traffic flow are operating in the autonomous mode on the roadway;
examining, by one or more processors, the traffic pattern data to determine a second traffic flow of the multiple SDVs occupied by members of the cohort of drivers, wherein the multiple SDVs in the second traffic flow are operating in the manual mode on the roadway; and
in response to determining that the first traffic flow has a lower accident rate than the second traffic flow, prohibiting, by one or more processors, the SDV from operating in the manual mode.

5. The processor-implemented method of claim 1 , further comprising:
receiving, by one or more processors, sensor readings from multiple sensors, wherein each of the multiple sensors detects a different type of current condition of the roadway;
weighting, by one or more processors, each of the sensor readings for different current conditions of the roadway;
summing, by one or more processors, weighted sensor readings for the different current conditions of the roadway;
determining, by one or more processors, whether the summed weighted sensor readings exceed a predefined level; and
in response to determining that the summed weighted sensor readings exceed a predefined level, prohibiting, by the on-board SDV control processor, the SDV from operating in the manual mode.

6. The processor-implemented method of claim 1 , further comprising:
receiving, by one or more processors, operational readings from one or more operational sensors on the SDV, wherein the operational sensors detect a current state of mechanical equipment on the SDV;
detecting, by the one or more processors and based on received operational readings, a mechanical fault with the mechanical equipment on the SDV; and
in response to detecting the mechanical fault with the mechanical equipment on the SDV, prohibiting, by the on-board SDV control processor, the SDV from operating in the manual mode.

7. The processor-implemented method of claim 1 , further comprising:
setting, by one or more processors, a minimum competence level threshold for the control processor competence level and the human driver competence level;
determining, by one or more processors, that neither the control processor competence level nor the human driver competence level exceeds the minimum competence level threshold; and
in response to determining that neither the control processor competence level nor the human driver competence level exceeds the minimum competence level threshold, directing, by the driving mode module, the on-board SDV control processor to take control of the SDV and to bring the SDV to a stop.

8. A computer program product for controlling a driving mode of a self-driving vehicle (SDV), the computer program product comprising a non-transitory computer readable storage medium having program code embodied therewith, the program code readable and executable by a processor to perform a method comprising:
receiving sensor readings from a sensor, wherein the sensor readings describe a current condition of a roadway, wherein the roadway is part of a planned route of a self-driving vehicle (SDV), wherein the SDV is capable of being operated in autonomous mode by an on-board SDV control processor, wherein a driving

Assignees

• IBM

Inventors

• Gordon Michael S
• Kozloski James R
• Kundu Ashish
• Malkin Peter K
• Pickover Clifford A

Classifications

• B60W2552/05

  Type of road, e.g. motorways, local streets, paved or unpaved roads · CPC title

• B60W2050/0073

  Driver overrides controller · CPC title

• B60W50/0097

  Predicting future conditions · CPC title

• G08G1/096725

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

• B60W2050/0295

  Inhibiting action of specific actuators or systems · CPC title