US20210339764A1 - System and method for detecting and/or preventing automation expectation mismatch in vehicle - Google Patents
System and method for detecting and/or preventing automation expectation mismatch in vehicle Download PDFInfo
- Publication number
- US20210339764A1 US20210339764A1 US17/379,099 US202117379099A US2021339764A1 US 20210339764 A1 US20210339764 A1 US 20210339764A1 US 202117379099 A US202117379099 A US 202117379099A US 2021339764 A1 US2021339764 A1 US 2021339764A1
- Authority
- US
- United States
- Prior art keywords
- vehicle
- driver
- mismatch
- expectation
- visual attention
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Abandoned
Links
- 238000000034 method Methods 0.000 title claims abstract description 63
- 230000000007 visual effect Effects 0.000 abstract description 56
- 230000000704 physical effect Effects 0.000 abstract description 15
- 238000012544 monitoring process Methods 0.000 abstract description 3
- 238000011156 evaluation Methods 0.000 description 20
- 230000000116 mitigating effect Effects 0.000 description 19
- 230000004043 responsiveness Effects 0.000 description 17
- 238000010586 diagram Methods 0.000 description 15
- 101100135611 Arabidopsis thaliana PAP12 gene Proteins 0.000 description 5
- 101100348113 Mus musculus Neurod6 gene Proteins 0.000 description 5
- 230000001747 exhibiting effect Effects 0.000 description 5
- 210000003128 head Anatomy 0.000 description 5
- 230000035945 sensitivity Effects 0.000 description 5
- 238000012360 testing method Methods 0.000 description 5
- 230000001276 controlling effect Effects 0.000 description 4
- 238000001514 detection method Methods 0.000 description 4
- 238000012545 processing Methods 0.000 description 4
- 230000004044 response Effects 0.000 description 4
- 230000009471 action Effects 0.000 description 3
- 230000008901 benefit Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 230000001149 cognitive effect Effects 0.000 description 2
- 230000009977 dual effect Effects 0.000 description 2
- 230000006870 function Effects 0.000 description 2
- 238000013507 mapping Methods 0.000 description 2
- 241001465754 Metazoa Species 0.000 description 1
- 230000001133 acceleration Effects 0.000 description 1
- 238000009227 behaviour therapy Methods 0.000 description 1
- 230000006998 cognitive state Effects 0.000 description 1
- 230000000295 complement effect Effects 0.000 description 1
- 230000007850 degeneration Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000001788 irregular Effects 0.000 description 1
- 230000003340 mental effect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000001105 regulatory effect Effects 0.000 description 1
Images
Classifications
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W50/16—Tactile feedback to the driver, e.g. vibration or force feedback to the driver on the steering wheel or the accelerator pedal
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K28/00—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions
- B60K28/02—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver
- B60K28/06—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver responsive to incapacity of driver
- B60K28/066—Safety devices for propulsion-unit control, specially adapted for, or arranged in, vehicles, e.g. preventing fuel supply or ignition in the event of potentially dangerous conditions responsive to conditions relating to the driver responsive to incapacity of driver actuating a signalling device
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K35/00—Instruments specially adapted for vehicles; Arrangement of instruments in or on vehicles
- B60K35/10—Input arrangements, i.e. from user to vehicle, associated with vehicle functions or specially adapted therefor
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W30/00—Purposes of road vehicle drive control systems not related to the control of a particular sub-unit, e.g. of systems using conjoint control of vehicle sub-units
- B60W30/10—Path keeping
- B60W30/12—Lane keeping
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W40/09—Driving style or behaviour
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/085—Changing the parameters of the control units, e.g. changing limit values, working points by control input
-
- G—PHYSICS
- G05—CONTROLLING; REGULATING
- G05D—SYSTEMS FOR CONTROLLING OR REGULATING NON-ELECTRIC VARIABLES
- G05D1/00—Control of position, course, altitude or attitude of land, water, air or space vehicles, e.g. using automatic pilots
- G05D1/02—Control of position or course in two dimensions
- G05D1/021—Control of position or course in two dimensions specially adapted to land vehicles
-
- G06K9/00845—
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V20/00—Scenes; Scene-specific elements
- G06V20/50—Context or environment of the image
- G06V20/59—Context or environment of the image inside of a vehicle, e.g. relating to seat occupancy, driver state or inner lighting conditions
- G06V20/597—Recognising the driver's state or behaviour, e.g. attention or drowsiness
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60K—ARRANGEMENT OR MOUNTING OF PROPULSION UNITS OR OF TRANSMISSIONS IN VEHICLES; ARRANGEMENT OR MOUNTING OF PLURAL DIVERSE PRIME-MOVERS IN VEHICLES; AUXILIARY DRIVES FOR VEHICLES; INSTRUMENTATION OR DASHBOARDS FOR VEHICLES; ARRANGEMENTS IN CONNECTION WITH COOLING, AIR INTAKE, GAS EXHAUST OR FUEL SUPPLY OF PROPULSION UNITS IN VEHICLES
- B60K2360/00—Indexing scheme associated with groups B60K35/00 or B60K37/00 relating to details of instruments or dashboards
- B60K2360/149—Instrument input by detecting viewing direction not otherwise provided for
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W40/00—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models
- B60W40/08—Estimation or calculation of non-directly measurable driving parameters for road vehicle drive control systems not related to the control of a particular sub unit, e.g. by using mathematical models related to drivers or passengers
- B60W2040/0818—Inactivity or incapacity of driver
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B60—VEHICLES IN GENERAL
- B60W—CONJOINT CONTROL OF VEHICLE SUB-UNITS OF DIFFERENT TYPE OR DIFFERENT FUNCTION; CONTROL SYSTEMS SPECIALLY ADAPTED FOR HYBRID VEHICLES; ROAD VEHICLE DRIVE CONTROL SYSTEMS FOR PURPOSES NOT RELATED TO THE CONTROL OF A PARTICULAR SUB-UNIT
- B60W50/00—Details of control systems for road vehicle drive control not related to the control of a particular sub-unit, e.g. process diagnostic or vehicle driver interfaces
- B60W50/08—Interaction between the driver and the control system
- B60W50/14—Means for informing the driver, warning the driver or prompting a driver intervention
- B60W2050/143—Alarm means
Definitions
- the present invention relates to a method and system for evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle, and to a vehicle.
- a method of evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle comprising the steps of: monitoring, during driving automation operation of the vehicle, at least one physical property of the driver indicative of a gaze direction of the driver; determining, based on the at least one physical property, at least a first visual attention metric value indicative of a current level of visual attention to a traffic scene ahead of the vehicle; comparing the at least first visual attention metric value to at least a first threshold value indicative of a first predefined threshold level of visual attention to the traffic scene ahead of the vehicle; and providing, when the comparison indicates that the current level of visual attention to the traffic scene ahead of the vehicle is lower than the first threshold level, a signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- the above-mentioned “physical property indicative of gaze direction” may include head rotation and position, and glance direction.
- a glance is made up of a sequence of eye fixations towards an area-of-interest (e.g. instrument cluster, mirror, vehicle path, forward roadway, etc).
- a “visual attention metric value indicative of a level of visual attention to a traffic scene ahead of the vehicle” should be understood to mean the value of any metric that can indicate how attentive the driver is to events occurring along the vehicle path in front of the vehicle. Such a metric may be devised to indicate how much attention the driver pays to events occurring elsewhere than in the front of the vehicle, and may, for example, capture a frequency of off-road glances and/or a duration of off-road glances etc.
- the signal indicative of an elevated risk of mismatch may be any signal useable to trigger one or several measures aimed at removing the mismatch.
- this signal may be an analog or digital signal, which may be an internal signal in a control unit, or a signal between different control units, etc.
- the method may include the step of determining the gaze direction of the driver based on the at least one physical property of the driver.
- the at least one visual attention metric may be determined based on the gaze direction.
- the at least one visual attention metric may be determined directly based on the monitored at least one physical property of the driver.
- the present inventors have performed behavioral tests indicating that as many as 28% of drivers crashed despite having their eyes on the conflict object (garbage bag, or parked car) while using highly reliable (but not perfect) driving automation.
- the inventors surprisingly found that, although crashing drivers looked ahead when the crash occurred, there is a strong correlation between drivers exhibiting a low level of visual attention to the forward roadway prior to encountering the conflict object, and drivers who did not intervene, but allowed the vehicle to crash into the conflict object.
- the present inventors have surprisingly found that there is a strong correlation between low levels of visual attention to the forward roadway during autonomous vehicle operation and an elevated risk of mismatch between actual driving automation capabilities of a vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- AEM Automatic Expectation Mismatch
- the step of determining the at least one visual attention metric value may comprise the steps of: determining, for a predetermined first period of time, a measure indicative of a proportion of the first period of time during which the driver looks towards the traffic scene ahead of the vehicle; and determining the at least one visual attention metric value based on the measure.
- the number of long (such as longer than three seconds) off-road glances during a predefined period of time may be used as a visual attention metric.
- the method according to the present invention may further comprise the steps of providing an alert for the driver; determining at least one alert responsiveness metric value, indicative of the driver's responsiveness to the alert; comparing the at least one alert responsiveness metric value to at least one threshold value indicative of a predefined threshold level of alert responsiveness; and providing, when the comparison indicates that the alert responsiveness of the driver is lower than the threshold level, the signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- alert may also be referred to as a “reminder” or “warning”.
- a “reminder” or “warning” may be provided by a system according to embodiments of the present invention, or any other driving related system of the vehicle.
- the alert may request the driver to put his/her hands back on the steering wheel, or to look at the road, etc.
- the alert could also be an instruction for the driver that is not directly related to the driving situation, such as an instruction for the driver to push a particular button, or similar.
- the alert may include an indication of a desired change in behavior of the driver; and the at least one alert responsiveness metric value may be determined based on a time from an onset of the alert until the desired change in behavior of the driver is detected. For instance, the time from the provision of instructions to hold the steering wheel with both hands, until the driver actually holds the steering wheel with both hands can be measured and used as an alert responsiveness metric. If the measured time until the driver again properly holds the steering wheel may then be used in the identification of an elevated risk of expectation mismatch.
- the method may further comprise the steps of determining, based on the at least one physical property of the driver indicative of a gaze direction of the driver, at least a second visual attention metric value indicative of a current level of visual attention to a traffic scene ahead of the vehicle; comparing the at least second visual attention metric value to at least a second threshold value indicative of a second predefined threshold level of visual attention to the traffic scene ahead of the vehicle; and providing, when the comparison indicates that the current level of visual attention to the traffic scene ahead of the vehicle is higher than the second threshold level, the signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- the method may further comprise the step of modifying, following detection of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle, at least one driving automation property of the vehicle.
- the present inventors have found that an efficient way of reducing the risk of expectation mismatch is to reduce the perceived driving automation capabilities of the vehicle. This serves to reduce the driving automation capabilities of the vehicle expected by the driver.
- a driving automation method for a vehicle comprising the steps of: identifying a lane of a road traveled by the vehicle; controlling a steering of the vehicle towards keeping the vehicle within a first regulation corridor in the lane, the first regulation corridor having a first width; and intermittently controlling the steering of the vehicle towards keeping the vehicle within a second regulation corridor in the lane, the second regulation corridor having a second width greater than the first width.
- the steering When the steering is not controlled towards the second regulation corridor, the steering may be controlled back towards the first regulation corridor.
- a driving automation system including processing circuitry configured to identify a lane of a road traveled by the vehicle; control a steering of the vehicle towards keeping the vehicle within a first regulation corridor in said lane, said first regulation corridor having a first width; and intermittently control the steering of the vehicle towards keeping the vehicle within a second regulation corridor in said lane, said second regulation corridor having a second width greater than said first width.
- a dual corridor deadband means that the vehicle with a randomized frequency switches between regulating toward a smaller and a wider regulation corridor (smaller vs wider lane center if you will), with the frequency of “falling through” from the smaller to the larger corridor happening with a lower frequency while drivers have eyes on the road and higher frequency when drivers' eyes are off the road.
- a system for evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle comprising: at least one sensor for sensing at least one physical property of a driver indicative of a gaze direction of the driver; and processing circuitry coupled to the at least one sensor and configured to: receive, from the at least one sensor, a signal indicative of the at least one physical property of the driver; determine, based on the at least one physical property, at least a first visual attention metric value indicative of a current level of visual attention to a traffic scene ahead of the vehicle; compare the at least first visual attention metric value to at least a first threshold value indicative of a first predefined threshold level of visual attention to the traffic scene ahead of the vehicle; and provide, when the comparison indicates that the current level of visual attention to the traffic scene ahead of the vehicle is lower than the first threshold level, a signal indicative of an elevated risk of mismatch between actual driving automation capabilities of
- the present invention relates to a method of evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle and driving automation capabilities of the vehicle expected by a driver.
- the method comprises monitoring at least one physical property of the driver indicative of a gaze direction; determining a first visual attention metric value indicative of a level of visual attention to the road ahead; comparing the first visual attention metric value to a first threshold value; and providing, when the comparison indicates that the current level of visual attention to the road is lower than the first threshold level, a signal indicative of an elevated risk of expectation mismatch.
- FIG. 1 is an illustration of a driving situation in which expectation mismatch may result in a collision
- FIG. 2A is a schematic simplified block diagram schematically illustrating a system according to an embodiment of the present invention.
- FIG. 2B illustrates an example interior or the vehicle in FIG. 1 ;
- FIG. 3 is a flow-chart schematically illustrating a first embodiment of a method according to the present invention
- FIG. 4 schematically illustrates determination of an example visual attention metric used in the method in FIG. 3 ;
- FIG. 5 schematically illustrates determination of an example visual attention metric used in the method in FIG. 3 ;
- FIG. 6 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 3 and observed collisions due to expectation mismatch;
- FIG. 7 is a flow-chart schematically illustrating a second embodiment of a method according to the present invention.
- FIG. 8 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 7 and observed collisions due to expectation mismatch;
- FIG. 9 is a flow-chart schematically illustrating a third embodiment of a method according to the present invention.
- FIG. 10 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 9 and observed collisions due to expectation mismatch;
- FIG. 11 is a flow-chart schematically illustrating a fourth embodiment of a method according to the present invention.
- FIG. 12 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 11 and observed collisions due to expectation mismatch;
- FIG. 13 schematically illustrates a method of reducing or avoiding expectation mismatch.
- FIG. 1 schematically shows a vehicle 1 traveling on a road 3 towards an obstacle 5 on the road 3 .
- the vehicle 1 in FIG. 1 has certain driving automation capabilities, but is not a fully autonomous car. Therefore, a driver 7 has to be ready to intervene when a traffic situation requires driving capabilities going beyond the actual driving automation capabilities of the vehicle 1 .
- the obstacle 5 in FIG. 1 may be taken to represent an object with which the vehicle 1 would collide without intervention by the driver 7 . It should be understood that this is for illustrative purposes only.
- FIG. 2A is a schematic simplified block diagram schematically illustrating a combined driving automation system and an embodiment of a system for evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle.
- the latter system will be referred to as a risk evaluation and mitigation system.
- the combined system 9 thus comprises a driving automation system 11 and a risk evaluation and mitigation system 13 .
- the driving automation system 11 comprises processing circuitry, here in the form of a driving automation control unit 15 , various sensors 17 a - d , the steering system 19 of the vehicle 1 , the propulsion system 21 of the vehicle 1 , and the braking system 23 of the vehicle 1 .
- the risk evaluation and mitigation system 13 comprises processing circuitry, here in the form of control unit 25 , a gaze sensor 27 , and a driver alert interface 29 .
- the control unit 25 comprises a counter 31 .
- the driving automation control unit 15 is coupled to the various sensors 17 a - d for acquiring driving-related information sensed by the sensors, and to the control unit 25 of the risk evaluation and mitigation system 13 for receiving commands from the risk evaluation and mitigation system 13 .
- the driving automation control unit 15 is further coupled to the steering system 19 , the propulsion system 21 , and the braking system 23 , for controlling these systems based on the information received from the sensors 17 a - d , the commands from the control unit 25 of the risk evaluation and mitigation system 13 , and other data not indicated in the simplified illustration in FIG. 2A .
- control unit 25 is coupled to the gaze sensor 27 for acquiring information indicative of a gaze direction of the driver 7 from the gaze sensor 27 , and to the driver alert interface 29 for controlling the driver alert interface 29 to provide alerts to the driver 7 .
- FIG. 2B is a schematic illustration of the interior of the vehicle 1 in FIG. 1 , mainly for showing a possible location of the gaze sensor 27 in relation to the driver 7 .
- FIG. 3 is a flow-chart schematically illustrating a first embodiment of a method according to the present invention.
- a first step 301 at least one physical property indicative of the gaze direction of the driver 7 is monitored.
- the control unit 25 of the risk evaluation and mitigation system 13 may control the gaze sensor 27 to acquire information indicative of eye and/or head orientation of the driver 7 .
- At least a first visual attention metric A 1 indicative of a level of visual attention to the traffic scene ahead of the vehicle 1 is determined by the control unit 25 based on the information acquired from the gaze sensor 27 .
- a gaze towards the traffic scene ahead of the vehicle 1 may be represented by a gaze being within the angular range ⁇ th to + ⁇ th. It should be noted that this is a simplified illustration, and that a “forward gaze” would in practice be defined by a more complex geometric constraint.
- one example of a suitable first visual attention metric A 1 may be based on a measure indicative of a proportion of a first period of time T 1 during which the driver 7 looks towards the traffic scene ahead of the vehicle 1 .
- the first visual attention metric A 1 may be defined according to the following:
- the first visual attention metric value determined in step 302 is compared to at least a first threshold value Ath 1 indicative of a first predefined threshold level of visual attention to the road ahead of the vehicle 1 .
- two values of the first visual attention metric A 1 ( t ), for different times, may be compared to respective thresholds according to the following:
- Ath 1 a 3% of the time during the last 6 minutes.
- Ath 1 b 3% of the time during the last 30 minutes.
- step 304 the control unit 25 of the risk evaluation and mitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. This signal may, for example, be provided to the driving automation system 11 . Otherwise, the method returns to step 301 .
- FIG. 6 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 3 and observed collisions due to expectation mismatch.
- the drivers 7 exhibiting a current level of visual attention to the road ahead of the vehicle 1 that is sufficiently low to indicate an elevated risk of expectation mismatch are those in the bottom left rectangle 31 .
- the method according to the first embodiment of the present invention achieved an accuracy of 0.778, a sensitivity of 0.571, and a specificity of 0.769.
- TP True Positive is the number of drivers for which the method predicted a collision and a collision actually occurred.
- FP False Positive
- TN True Negative
- FN False Negative
- Ntot is the total number of drivers.
- FIG. 7 is a flow-chart schematically illustrating a second embodiment of a method according to the present invention.
- a first step 701 at least one physical property indicative of the gaze direction of the driver 7 is monitored.
- the control unit 25 of the risk evaluation and mitigation system 13 may control the gaze sensor 27 to acquire information indicative of eye and/or head orientation of the driver 7 .
- an alert is provided to the driver 7 .
- Examples of possible alerts were provided in the Summary section above.
- the control unit 25 of the risk evaluation and mitigation system 13 may control the driver alert interface 29 to provide a driver alert.
- an alert responsiveness value R is determined.
- the alert responsiveness metric R may be defined according to the following:
- R Mean response time from alert onset to driver compliance.
- the alert responsiveness value determined in step 703 is compared to at least a first threshold value Rth indicative of a predefined threshold level of alert responsiveness.
- the responsiveness metric R may be compared to the threshold value Rth according to the following:
- step 705 the control unit 25 of the risk evaluation and mitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. This signal may, for example, be provided to the driving automation system 11 . Otherwise, the method returns to step 701 .
- FIG. 8 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 7 and observed collisions due to expectation mismatch.
- the drivers 7 exhibiting a responsiveness that is sufficiently low to indicate an elevated risk of expectation mismatch are those to the right of the dashed line 33 in FIG. 8 .
- the method according to the second embodiment of the present invention achieved an accuracy of 0.741, a sensitivity of 0.333, and a specificity of 0.702.
- FIG. 9 is a flow-chart schematically illustrating a third embodiment of a method according to the present invention.
- a first step 901 at least one physical property indicative of the gaze direction of the driver 7 is monitored.
- the control unit 25 of the risk evaluation and mitigation system 13 may control the gaze sensor 27 to acquire information indicative of eye and/or head orientation of the driver 7 .
- At least a second visual attention metric A 2 indicative of a level of visual attention to the traffic scene ahead of the vehicle 1 is determined by the control unit 25 based on the information acquired from the gaze sensor 27 .
- the second visual attention metric A 2 may be defined according to the following:
- the second visual attention metric value determined in step 902 is compared to at least a second threshold value Ath 2 indicative of a second predefined threshold level of visual attention to the road ahead of the vehicle 1 .
- two values of the second visual attention metric A 2 ( t ), for different times, may be compared to respective thresholds according to the following:
- Ath 2 a 38% of the time during the last 6 minutes.
- Ath 2 b 38% of the time during the last 30 minutes.
- step 904 the control unit 25 of the risk evaluation and mitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. This signal may, for example, be provided to the driving automation system 11 . Otherwise, the method returns to step 901 .
- FIG. 10 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method in FIG. 9 and observed collisions due to expectation mismatch.
- the drivers 7 exhibiting a current level of visual attention to the road ahead of the vehicle 1 that is sufficiently high to indicate an elevated risk of expectation mismatch are those in the first 35 and second 37 indicated rectangles in FIG. 10 .
- the method according to the third embodiment of the present invention achieved an accuracy of 0.685, a sensitivity of 0.238, and a specificity of 0.667.
- FIG. 11 is a flow-chart schematically illustrating a fourth embodiment of a method according to the present invention.
- a first step 1101 at least one physical property indicative of the gaze direction of the driver 7 is monitored.
- the control unit 25 of the risk evaluation and mitigation system 13 may control the gaze sensor 27 to acquire information indicative of eye and/or head orientation of the driver 7 .
- At least a first visual attention metric value A 1 , a responsiveness metric value R, and a second visual attention metric value A 2 are determined as described above.
- the first visual attention metric value A 1 determined in step 1102 is compared to at least a first threshold value as described above in connection with FIG. 3 .
- step 1104 the control unit 25 of the risk evaluation and mitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. Otherwise, the method proceeds to step 1105 .
- step 1105 the responsiveness metric value R determined in step 1102 is compared to at least a first threshold value as described above in connection with FIG. 7 . If the comparison indicates a low level of alert responsiveness, the method proceeds to step 1104 . Otherwise, the method proceeds to step 1106 .
- step 1106 the second visual attention metric value A 2 determined in step 1102 is compared to at least a second threshold value as described above in connection with FIG. 9 . If the comparison indicates a high level of alert responsiveness, the method proceeds to step 1104 . Otherwise, the method returns to step 1101 .
- the signal generated in step 1104 is provided to the driving automation control unit 15 of the driving automation system 11 .
- the control unit 15 of the driving automation system 11 modifies at least one driving automation property of the driving automation system 11 .
- FIG. 12 is a diagram illustrating determined correlations between elevated risk of expectation mismatch determined using the methods according to the first, second, third, and fourth example embodiments described above. As is schematically indicated in FIG. 12 , a rule for identifying drivers exhibiting an elevated risk of expectation mismatch is better the higher up to the left it is in the diagram in FIG. 12 . As can be clearly seen in the diagram of FIG. 12 , the method according to the fourth embodiment above provides the best result, followed by the method according to the first embodiment. As will be immediately obvious to one of ordinary skill in the art, there are many other combinations of the methods described herein and other variants that may provide almost as good results (or better) than that achieved using the fourth embodiment described above with reference to the flow-chart in FIG. 11 .
- the method according to the fourth embodiment of the present invention achieved an accuracy of 0.907, a sensitivity of 0.952, and a specificity of 0.967.
- FIG. 13 schematically shows the vehicle 1 , equipped with a driving automation system 11 , in a lane 39 of the road 3 .
- the solid line 41 in the lane 39 indicates the path of the vehicle 1 under the control of the driving automation system 11 .
- the driving automation control unit 15 of the driving automation system 11 controls the steering system 19 of the vehicle 1 towards keeping the vehicle 1 within a first regulation corridor 43 in the lane 39 .
- the first regulation corridor 43 has as first width w 1 .
- the risk evaluation and mitigation system 13 detects an elevated risk of expectation mismatch, in a manner described above, and the control unit 25 of the risk evaluation and mitigation system 13 provides a signal indicative thereof to the driving automation system 11 .
- the driving automation control unit 15 of the driving automation system 11 controls the steering system 19 of the vehicle 1 towards keeping the vehicle 1 within a second regulation corridor 45 in the lane 39 .
- the second regulation corridor 45 has as second width w 2 , greater than the first width w 1 of the first regulation corridor 43 .
- the driving automation system 11 will control the vehicle 1 to move more from side to side in the lane 39 . This will result in the driver 7 perceiving a reduced capability of the driving automation system 11 of the vehicle 1 , which will in turn result in a reduced or eliminated expectation mismatch.
- the risk evaluation and mitigation system 13 may have determined that the risk of expectation mismatch has become sufficiently low to allow the driving automation system 11 to again apply the first regulation corridor 43 .
- the switch between the first regulation corridor 43 and the second regulation corridor 45 may take place at irregular times, and without a prior indication of an elevated risk of expectation mismatch.
- the alternation between the two or more regulation corridors may be used to reduce the risk that expectation mismatch occurs.
Landscapes
- Engineering & Computer Science (AREA)
- Automation & Control Theory (AREA)
- Transportation (AREA)
- Mechanical Engineering (AREA)
- Physics & Mathematics (AREA)
- Combustion & Propulsion (AREA)
- General Physics & Mathematics (AREA)
- Mathematical Physics (AREA)
- Human Computer Interaction (AREA)
- Chemical & Material Sciences (AREA)
- Aviation & Aerospace Engineering (AREA)
- Radar, Positioning & Navigation (AREA)
- Remote Sensing (AREA)
- Theoretical Computer Science (AREA)
- Multimedia (AREA)
- Traffic Control Systems (AREA)
- Control Of Driving Devices And Active Controlling Of Vehicle (AREA)
Abstract
The present invention relates to a method of evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle and driving automation capabilities of the vehicle expected by a driver. The method comprises monitoring at least one physical property of the driver indicative of a gaze direction; determining a first visual attention metric value indicative of a level of visual attention to the road ahead; comparing the first visual attention metric value to a first threshold value; and providing, when the comparison indicates that the current level of visual attention to the road is lower than the first threshold level, a signal indicative of an elevated risk of expectation mismatch.
Description
- The present disclosure is a divisional (DIV) of co-pending U.S. patent application Ser. No. 16/601,682, filed on Oct. 15, 2019, and entitled “SYSTEM AND METHOD FOR DETECTING AND/OR PREVENTING AUTOMATION EXPECTATION MISMATCH IN VEHICLE,” which claims the benefit of priority of co-pending European Patent Application No. 18200909.2, filed on Oct. 17, 2018, and entitled “SYSTEM AND METHOD FOR DETECTING AND/OR PREVENTING AUTOMATION EXPECTATION MISMATCH IN VEHICLE,” the contents of both of which are incorporated in full by reference herein.
- The present invention relates to a method and system for evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle, and to a vehicle.
- One key challenge in development of automated vehicles is overreliance, whereby drivers disengage too much with driving because they believe the automation has more capability than it actually does. Before automated vehicles are perfect, the driver will need to occasionally intervene while using highly reliable (but not perfect) automation. Thus, understanding how to design automated vehicle systems to achieve good driver supervision engagement and conflict intervention performance is critical. The reason why drivers must supervise (should not exhibit overreliance) is because imperfect automation and crash avoidance systems have limitations. Common limitations for current automated vehicles include, for example, restrictions in operating speed ranges, how much steering, braking and acceleration the system can apply, and limitations in lane and object detection (e.g. pedestrians, animals, on-road objects, and oncoming vehicles). Additionally, the driver needs to supervise for system faults ranging from sensor blockage to brake pump failure, as these may require immediate intervention. Thus the driver both supervises ongoing automation performance and detection of pre-crash conditions.
- It is a well-known irony of automation that the better automation becomes, the less capable operators are at detecting and acting on automation failures. Key challenges in deploying vehicle automation are therefore:
- (1) to avoid driver mental model mistakes regarding their expectations of automation performance, and
- (2) to ensure that the requirements on driver behavior by vehicle automation are met when failures and limitations of automation occur.
- One important aspect in the strive towards safer operation of autonomous vehicles that may sometimes need driver intervention is thus the ability to correctly evaluate the risk of a mismatch between the actual driving automation capabilities of the vehicle and the driving automation capabilities that the driver expects the vehicle to have.
- In view of this, it is thus an object of the present invention to enable reliable detection of a mismatch between the actual driving automation capabilities of the vehicle and the driving automation capabilities that the driver expects the vehicle to have.
- According to a first aspect of the present invention, it is therefore provided a method of evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle, the method comprising the steps of: monitoring, during driving automation operation of the vehicle, at least one physical property of the driver indicative of a gaze direction of the driver; determining, based on the at least one physical property, at least a first visual attention metric value indicative of a current level of visual attention to a traffic scene ahead of the vehicle; comparing the at least first visual attention metric value to at least a first threshold value indicative of a first predefined threshold level of visual attention to the traffic scene ahead of the vehicle; and providing, when the comparison indicates that the current level of visual attention to the traffic scene ahead of the vehicle is lower than the first threshold level, a signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- The above-mentioned “physical property indicative of gaze direction”: may include head rotation and position, and glance direction. A glance is made up of a sequence of eye fixations towards an area-of-interest (e.g. instrument cluster, mirror, vehicle path, forward roadway, etc).
- In the context of the present application, a “visual attention metric value indicative of a level of visual attention to a traffic scene ahead of the vehicle” should be understood to mean the value of any metric that can indicate how attentive the driver is to events occurring along the vehicle path in front of the vehicle. Such a metric may be devised to indicate how much attention the driver pays to events occurring elsewhere than in the front of the vehicle, and may, for example, capture a frequency of off-road glances and/or a duration of off-road glances etc.
- The signal indicative of an elevated risk of mismatch may be any signal useable to trigger one or several measures aimed at removing the mismatch. Thus, this signal may be an analog or digital signal, which may be an internal signal in a control unit, or a signal between different control units, etc.
- In embodiments, the method may include the step of determining the gaze direction of the driver based on the at least one physical property of the driver. The at least one visual attention metric may be determined based on the gaze direction. Alternatively, the at least one visual attention metric may be determined directly based on the monitored at least one physical property of the driver.
- The present inventors have performed behavioral tests indicating that as many as 28% of drivers crashed despite having their eyes on the conflict object (garbage bag, or parked car) while using highly reliable (but not perfect) driving automation. When analyzing these tests, the inventors surprisingly found that, although crashing drivers looked ahead when the crash occurred, there is a strong correlation between drivers exhibiting a low level of visual attention to the forward roadway prior to encountering the conflict object, and drivers who did not intervene, but allowed the vehicle to crash into the conflict object. In other words, the present inventors have surprisingly found that there is a strong correlation between low levels of visual attention to the forward roadway during autonomous vehicle operation and an elevated risk of mismatch between actual driving automation capabilities of a vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- This mismatch, which may be referred to as “Automation Expectation Mismatch” (AEM) demonstrates that a key component of driver engagement while using automation is cognitive (understanding the need for action), rather than purely visual (looking at the threat), or having hands-on-wheel. Cognitive understanding of the need to act is a crucial component of driver engagement while using driving automation systems that are not perfect. AEM is thus a newly discovered cognitive state of mind.
- According to various embodiments of the present invention, the step of determining the at least one visual attention metric value may comprise the steps of: determining, for a predetermined first period of time, a measure indicative of a proportion of the first period of time during which the driver looks towards the traffic scene ahead of the vehicle; and determining the at least one visual attention metric value based on the measure.
- Alternatively, or as a complement, the number of long (such as longer than three seconds) off-road glances during a predefined period of time may be used as a visual attention metric.
- In various embodiments, the method according to the present invention may further comprise the steps of providing an alert for the driver; determining at least one alert responsiveness metric value, indicative of the driver's responsiveness to the alert; comparing the at least one alert responsiveness metric value to at least one threshold value indicative of a predefined threshold level of alert responsiveness; and providing, when the comparison indicates that the alert responsiveness of the driver is lower than the threshold level, the signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- The above-mentioned “alert” may also be referred to as a “reminder” or “warning”. Such an alert may be provided by a system according to embodiments of the present invention, or any other driving related system of the vehicle. For instance, the alert may request the driver to put his/her hands back on the steering wheel, or to look at the road, etc. The alert could also be an instruction for the driver that is not directly related to the driving situation, such as an instruction for the driver to push a particular button, or similar.
- Advantageously, the alert may include an indication of a desired change in behavior of the driver; and the at least one alert responsiveness metric value may be determined based on a time from an onset of the alert until the desired change in behavior of the driver is detected. For instance, the time from the provision of instructions to hold the steering wheel with both hands, until the driver actually holds the steering wheel with both hands can be measured and used as an alert responsiveness metric. If the measured time until the driver again properly holds the steering wheel may then be used in the identification of an elevated risk of expectation mismatch.
- In various embodiments of the method according to the present invention, the method may further comprise the steps of determining, based on the at least one physical property of the driver indicative of a gaze direction of the driver, at least a second visual attention metric value indicative of a current level of visual attention to a traffic scene ahead of the vehicle; comparing the at least second visual attention metric value to at least a second threshold value indicative of a second predefined threshold level of visual attention to the traffic scene ahead of the vehicle; and providing, when the comparison indicates that the current level of visual attention to the traffic scene ahead of the vehicle is higher than the second threshold level, the signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- Using this second evaluation of the visual attention to the traffic scene ahead of the vehicle, drivers tending to spend much time looking at the road ahead can be identified. Since it has been surprisingly found that this class of drivers also exhibit an elevated risk of expectation mismatch behavior (and thus an increased risk of failing to take over driving command in situations when this is required for crash avoidance), these embodiments provide for improved identification of drivers with an elevated risk.
- In various embodiments of the method according to the present invention, the method may further comprise the step of modifying, following detection of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle, at least one driving automation property of the vehicle.
- When an elevated risk of expectation mismatch is detected, various actions may be taken to reduce the risk of expectation mismatch. These actions may be escalated for detected higher risks, and could end with interventions and/or safely stopping the vehicle.
- The present inventors have found that an efficient way of reducing the risk of expectation mismatch is to reduce the perceived driving automation capabilities of the vehicle. This serves to reduce the driving automation capabilities of the vehicle expected by the driver.
- According to a further aspect of the present invention, it is thus provided a driving automation method for a vehicle, the method comprising the steps of: identifying a lane of a road traveled by the vehicle; controlling a steering of the vehicle towards keeping the vehicle within a first regulation corridor in the lane, the first regulation corridor having a first width; and intermittently controlling the steering of the vehicle towards keeping the vehicle within a second regulation corridor in the lane, the second regulation corridor having a second width greater than the first width.
- When the steering is not controlled towards the second regulation corridor, the steering may be controlled back towards the first regulation corridor.
- A driving automation system is also provided, including processing circuitry configured to identify a lane of a road traveled by the vehicle; control a steering of the vehicle towards keeping the vehicle within a first regulation corridor in said lane, said first regulation corridor having a first width; and intermittently control the steering of the vehicle towards keeping the vehicle within a second regulation corridor in said lane, said second regulation corridor having a second width greater than said first width.
- To achieve degeneration with a sufficiently non-robust mapping between inputs and outputs, a dual corridor deadband can be used. A dual corridor deadband means that the vehicle with a randomized frequency switches between regulating toward a smaller and a wider regulation corridor (smaller vs wider lane center if you will), with the frequency of “falling through” from the smaller to the larger corridor happening with a lower frequency while drivers have eyes on the road and higher frequency when drivers' eyes are off the road.
- To the driver, an implementation that follows this principle will not be possible for a driver to rely on for developing automated behavior, because the input-output mapping from the drivers perspective, as well as objectively, will be stochastic. In math terms, the dual-deadband corridor principle represents regulation toward two sinusoidal functions, on top of which the actual road geometry adds a third sinusoidal. It is mathematically proven that summing three sinusoidal curves of different amplitude and frequency provides randomized output.
- According to a further aspect of the present invention, it is provided a system for evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle, the system comprising: at least one sensor for sensing at least one physical property of a driver indicative of a gaze direction of the driver; and processing circuitry coupled to the at least one sensor and configured to: receive, from the at least one sensor, a signal indicative of the at least one physical property of the driver; determine, based on the at least one physical property, at least a first visual attention metric value indicative of a current level of visual attention to a traffic scene ahead of the vehicle; compare the at least first visual attention metric value to at least a first threshold value indicative of a first predefined threshold level of visual attention to the traffic scene ahead of the vehicle; and provide, when the comparison indicates that the current level of visual attention to the traffic scene ahead of the vehicle is lower than the first threshold level, a signal indicative of an elevated risk of mismatch between actual driving automation capabilities of the vehicle and driving automation capabilities of the vehicle expected by the driver operating the vehicle.
- In summary, according to various embodiments the present invention relates to a method of evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle and driving automation capabilities of the vehicle expected by a driver. The method comprises monitoring at least one physical property of the driver indicative of a gaze direction; determining a first visual attention metric value indicative of a level of visual attention to the road ahead; comparing the first visual attention metric value to a first threshold value; and providing, when the comparison indicates that the current level of visual attention to the road is lower than the first threshold level, a signal indicative of an elevated risk of expectation mismatch.
- These and other aspects of the present invention will now be described in more detail, with reference to the appended drawings showing an example embodiment of the invention, wherein:
-
FIG. 1 is an illustration of a driving situation in which expectation mismatch may result in a collision; -
FIG. 2A is a schematic simplified block diagram schematically illustrating a system according to an embodiment of the present invention; -
FIG. 2B illustrates an example interior or the vehicle inFIG. 1 ; -
FIG. 3 is a flow-chart schematically illustrating a first embodiment of a method according to the present invention; -
FIG. 4 schematically illustrates determination of an example visual attention metric used in the method inFIG. 3 ; -
FIG. 5 schematically illustrates determination of an example visual attention metric used in the method inFIG. 3 ; -
FIG. 6 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 3 and observed collisions due to expectation mismatch; -
FIG. 7 is a flow-chart schematically illustrating a second embodiment of a method according to the present invention; -
FIG. 8 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 7 and observed collisions due to expectation mismatch; -
FIG. 9 is a flow-chart schematically illustrating a third embodiment of a method according to the present invention; -
FIG. 10 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 9 and observed collisions due to expectation mismatch; -
FIG. 11 is a flow-chart schematically illustrating a fourth embodiment of a method according to the present invention; -
FIG. 12 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 11 and observed collisions due to expectation mismatch; and -
FIG. 13 schematically illustrates a method of reducing or avoiding expectation mismatch. -
FIG. 1 schematically shows avehicle 1 traveling on aroad 3 towards an obstacle 5 on theroad 3. Thevehicle 1 inFIG. 1 has certain driving automation capabilities, but is not a fully autonomous car. Therefore, adriver 7 has to be ready to intervene when a traffic situation requires driving capabilities going beyond the actual driving automation capabilities of thevehicle 1. For the purpose of explaining embodiments of the present invention, the obstacle 5 inFIG. 1 may be taken to represent an object with which thevehicle 1 would collide without intervention by thedriver 7. It should be understood that this is for illustrative purposes only. -
FIG. 2A is a schematic simplified block diagram schematically illustrating a combined driving automation system and an embodiment of a system for evaluating a current risk of mismatch between actual driving automation capabilities of a vehicle having a driving automation system and driving automation capabilities of the vehicle expected by a driver operating the vehicle. The latter system will be referred to as a risk evaluation and mitigation system. - Referring to
FIG. 2A , the combinedsystem 9 thus comprises adriving automation system 11 and a risk evaluation andmitigation system 13. Thedriving automation system 11 comprises processing circuitry, here in the form of a drivingautomation control unit 15, various sensors 17 a-d, thesteering system 19 of thevehicle 1, thepropulsion system 21 of thevehicle 1, and thebraking system 23 of thevehicle 1. The risk evaluation andmitigation system 13 comprises processing circuitry, here in the form ofcontrol unit 25, agaze sensor 27, and adriver alert interface 29. As is schematically indicated inFIG. 2A , thecontrol unit 25 comprises acounter 31. - In the
driving automation system 11, the drivingautomation control unit 15 is coupled to the various sensors 17 a-d for acquiring driving-related information sensed by the sensors, and to thecontrol unit 25 of the risk evaluation andmitigation system 13 for receiving commands from the risk evaluation andmitigation system 13. As is indicated inFIG. 2A , the drivingautomation control unit 15 is further coupled to thesteering system 19, thepropulsion system 21, and thebraking system 23, for controlling these systems based on the information received from the sensors 17 a-d, the commands from thecontrol unit 25 of the risk evaluation andmitigation system 13, and other data not indicated in the simplified illustration inFIG. 2A . - In the risk evaluation and
mitigation system 13, thecontrol unit 25 is coupled to thegaze sensor 27 for acquiring information indicative of a gaze direction of thedriver 7 from thegaze sensor 27, and to thedriver alert interface 29 for controlling thedriver alert interface 29 to provide alerts to thedriver 7. -
FIG. 2B is a schematic illustration of the interior of thevehicle 1 inFIG. 1 , mainly for showing a possible location of thegaze sensor 27 in relation to thedriver 7. -
FIG. 3 is a flow-chart schematically illustrating a first embodiment of a method according to the present invention. - In a
first step 301, at least one physical property indicative of the gaze direction of thedriver 7 is monitored. Referring toFIGS. 2A-B , thecontrol unit 25 of the risk evaluation andmitigation system 13 may control thegaze sensor 27 to acquire information indicative of eye and/or head orientation of thedriver 7. - In the
subsequent step 302, at least a first visual attention metric A1 indicative of a level of visual attention to the traffic scene ahead of thevehicle 1 is determined by thecontrol unit 25 based on the information acquired from thegaze sensor 27. - Referring to
FIG. 4 , a gaze towards the traffic scene ahead of thevehicle 1 may be represented by a gaze being within the angular range −θth to +θth. It should be noted that this is a simplified illustration, and that a “forward gaze” would in practice be defined by a more complex geometric constraint. - Turning now to
FIG. 5 , one example of a suitable first visual attention metric A1 may be based on a measure indicative of a proportion of a first period of time T1 during which thedriver 7 looks towards the traffic scene ahead of thevehicle 1. - According to one illustrative example, the first visual attention metric A1 may be defined according to the following:
- A1(t)=The fraction of time the
driver 7 looks ahead less than 30% of a moving time window having the duration T1 (for the example case of T1=4 s, this means that thedriver 7 has his eyes on the road 5 ahead during less than 1.2 s, and off the road 5 ahead more than 2.8 s). - In the
next step 303, the first visual attention metric value determined instep 302 is compared to at least a first threshold value Ath1 indicative of a first predefined threshold level of visual attention to the road ahead of thevehicle 1. - According to one illustrative example, two values of the first visual attention metric A1(t), for different times, may be compared to respective thresholds according to the following:
- Ath1 a: 3% of the time during the last 6 minutes.
- Ath1 b: 3% of the time during the last 30 minutes.
- When A1>Ath1 a and A1>Ath1 b, it may be determined that the
driver 7 exhibits an elevated risk of expectation mismatch. - If this is the case, the method proceeds to step 304, in which the
control unit 25 of the risk evaluation andmitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. This signal may, for example, be provided to thedriving automation system 11. Otherwise, the method returns to step 301. -
FIG. 6 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 3 and observed collisions due to expectation mismatch. In the diagram ofFIG. 6 , thedrivers 7 exhibiting a current level of visual attention to the road ahead of thevehicle 1 that is sufficiently low to indicate an elevated risk of expectation mismatch are those in the bottomleft rectangle 31. - In the field tests referred to in the Summary section above, the method according to the first embodiment of the present invention achieved an accuracy of 0.778, a sensitivity of 0.571, and a specificity of 0.769.
- Here, “accuracy” is defined as (TP+TN)/Ntot, “sensitivity” is defined as TP/(TP+FN), and “specificity” is defined as TN/(TN+FN), where:
- TP (True Positive) is the number of drivers for which the method predicted a collision and a collision actually occurred.
- FP (False Positive) is the number of drivers for which the method predicted a collision and no collision occurred.
- TN (True Negative) is the number of drivers for which the method predicted that no collision would occur and no collision occurred.
- FN (False Negative) is the number of drivers for which the method predicted that no collision would occur and a collision occurred.
- Ntot is the total number of drivers.
-
FIG. 7 is a flow-chart schematically illustrating a second embodiment of a method according to the present invention. - In a
first step 701, at least one physical property indicative of the gaze direction of thedriver 7 is monitored. Referring toFIGS. 2A-B , thecontrol unit 25 of the risk evaluation andmitigation system 13 may control thegaze sensor 27 to acquire information indicative of eye and/or head orientation of thedriver 7. - In the
subsequent step 702, an alert is provided to thedriver 7. Examples of possible alerts were provided in the Summary section above. Referring toFIG. 2A , thecontrol unit 25 of the risk evaluation andmitigation system 13 may control thedriver alert interface 29 to provide a driver alert. - In the
next step 703, an alert responsiveness value R is determined. - According to one illustrative example, the alert responsiveness metric R may be defined according to the following:
- R=Mean response time from alert onset to driver compliance.
- In the
next step 704, the alert responsiveness value determined instep 703 is compared to at least a first threshold value Rth indicative of a predefined threshold level of alert responsiveness. - According to one illustrative example, the responsiveness metric R may be compared to the threshold value Rth according to the following:
- Rth: 0.9 seconds average response time
- When R>Rth, it may be determined that the
driver 7 exhibits an elevated risk of expectation mismatch. - If this is the case, the method proceeds to step 705, in which the
control unit 25 of the risk evaluation andmitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. This signal may, for example, be provided to thedriving automation system 11. Otherwise, the method returns to step 701. -
FIG. 8 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 7 and observed collisions due to expectation mismatch. In the diagram ofFIG. 8 , thedrivers 7 exhibiting a responsiveness that is sufficiently low to indicate an elevated risk of expectation mismatch are those to the right of the dashedline 33 inFIG. 8 . - In the field tests referred to in the Summary section above, the method according to the second embodiment of the present invention achieved an accuracy of 0.741, a sensitivity of 0.333, and a specificity of 0.702.
-
FIG. 9 is a flow-chart schematically illustrating a third embodiment of a method according to the present invention. - In a
first step 901, at least one physical property indicative of the gaze direction of thedriver 7 is monitored. Referring toFIGS. 2A-B , thecontrol unit 25 of the risk evaluation andmitigation system 13 may control thegaze sensor 27 to acquire information indicative of eye and/or head orientation of thedriver 7. - In the
subsequent step 902, at least a second visual attention metric A2 indicative of a level of visual attention to the traffic scene ahead of thevehicle 1 is determined by thecontrol unit 25 based on the information acquired from thegaze sensor 27. - According to one illustrative example, the second visual attention metric A2 may be defined according to the following:
- A2(t)=The fraction of time the
driver 7 looks ahead more than 92% of a moving time window having the duration T2 (for the example case of T2=60 s, this means that thedriver 7 has his eyes on the road 5 ahead during more than 55.2 s). - In the
next step 903, the second visual attention metric value determined instep 902 is compared to at least a second threshold value Ath2 indicative of a second predefined threshold level of visual attention to the road ahead of thevehicle 1. - According to one illustrative example, two values of the second visual attention metric A2(t), for different times, may be compared to respective thresholds according to the following:
- Ath2 a: 38% of the time during the last 6 minutes.
- Ath2 b: 38% of the time during the last 30 minutes.
- When A2>Ath2 a and A2>Ath2 b, it may be determined that the
driver 7 exhibits an elevated risk of expectation mismatch. - If this is the case, the method proceeds to step 904, in which the
control unit 25 of the risk evaluation andmitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. This signal may, for example, be provided to thedriving automation system 11. Otherwise, the method returns to step 901. -
FIG. 10 is a diagram illustrating a determined correlation between elevated risk of expectation mismatch determined using the method inFIG. 9 and observed collisions due to expectation mismatch. In the diagram ofFIG. 10 , thedrivers 7 exhibiting a current level of visual attention to the road ahead of thevehicle 1 that is sufficiently high to indicate an elevated risk of expectation mismatch are those in the first 35 and second 37 indicated rectangles inFIG. 10 . - In the field tests referred to in the Summary section above, the method according to the third embodiment of the present invention achieved an accuracy of 0.685, a sensitivity of 0.238, and a specificity of 0.667.
-
FIG. 11 is a flow-chart schematically illustrating a fourth embodiment of a method according to the present invention. - In a
first step 1101, at least one physical property indicative of the gaze direction of thedriver 7 is monitored. Referring toFIGS. 2A-B , thecontrol unit 25 of the risk evaluation andmitigation system 13 may control thegaze sensor 27 to acquire information indicative of eye and/or head orientation of thedriver 7. - In the
subsequent step 1102, at least a first visual attention metric value A1, a responsiveness metric value R, and a second visual attention metric value A2 are determined as described above. - In the
next step 1103, the first visual attention metric value A1 determined instep 1102 is compared to at least a first threshold value as described above in connection withFIG. 3 . - If the comparison indicates a low level of visual attention to the road ahead of the
vehicle 1, the method proceeds to step 1104, in which thecontrol unit 25 of the risk evaluation andmitigation system 13 provides a signal indicative of an elevated risk of expectation mismatch. Otherwise, the method proceeds to step 1105. - In
step 1105, the responsiveness metric value R determined instep 1102 is compared to at least a first threshold value as described above in connection withFIG. 7 . If the comparison indicates a low level of alert responsiveness, the method proceeds to step 1104. Otherwise, the method proceeds to step 1106. - In
step 1106, the second visual attention metric value A2 determined instep 1102 is compared to at least a second threshold value as described above in connection withFIG. 9 . If the comparison indicates a high level of alert responsiveness, the method proceeds to step 1104. Otherwise, the method returns to step 1101. - In this embodiment, the signal generated in
step 1104 is provided to the drivingautomation control unit 15 of thedriving automation system 11. In response to receiving this signal, thecontrol unit 15 of thedriving automation system 11 modifies at least one driving automation property of thedriving automation system 11. -
FIG. 12 is a diagram illustrating determined correlations between elevated risk of expectation mismatch determined using the methods according to the first, second, third, and fourth example embodiments described above. As is schematically indicated inFIG. 12 , a rule for identifying drivers exhibiting an elevated risk of expectation mismatch is better the higher up to the left it is in the diagram inFIG. 12 . As can be clearly seen in the diagram ofFIG. 12 , the method according to the fourth embodiment above provides the best result, followed by the method according to the first embodiment. As will be immediately obvious to one of ordinary skill in the art, there are many other combinations of the methods described herein and other variants that may provide almost as good results (or better) than that achieved using the fourth embodiment described above with reference to the flow-chart inFIG. 11 . - In the field tests referred to in the Summary section above, the method according to the fourth embodiment of the present invention achieved an accuracy of 0.907, a sensitivity of 0.952, and a specificity of 0.967.
- Finally, an example method of reducing the above-described expectation mismatch will be described with reference to
FIG. 13 .FIG. 13 schematically shows thevehicle 1, equipped with adriving automation system 11, in alane 39 of theroad 3. Thesolid line 41 in thelane 39 indicates the path of thevehicle 1 under the control of thedriving automation system 11. During the first portion of the travel indicated inFIG. 13 , the drivingautomation control unit 15 of thedriving automation system 11 controls thesteering system 19 of thevehicle 1 towards keeping thevehicle 1 within afirst regulation corridor 43 in thelane 39. Thefirst regulation corridor 43 has as first width w1. - At a time t1, indicated by a first arrow in
FIG. 13 , the risk evaluation andmitigation system 13 detects an elevated risk of expectation mismatch, in a manner described above, and thecontrol unit 25 of the risk evaluation andmitigation system 13 provides a signal indicative thereof to thedriving automation system 11. - In response to this signal, the driving
automation control unit 15 of thedriving automation system 11 controls thesteering system 19 of thevehicle 1 towards keeping thevehicle 1 within asecond regulation corridor 45 in thelane 39. Thesecond regulation corridor 45 has as second width w2, greater than the first width w1 of thefirst regulation corridor 43. - Due to the increased width of the regulation corridor, the
driving automation system 11 will control thevehicle 1 to move more from side to side in thelane 39. This will result in thedriver 7 perceiving a reduced capability of thedriving automation system 11 of thevehicle 1, which will in turn result in a reduced or eliminated expectation mismatch. - At a time t2, indicated by a second arrow in
FIG. 13 , the risk evaluation andmitigation system 13 may have determined that the risk of expectation mismatch has become sufficiently low to allow thedriving automation system 11 to again apply thefirst regulation corridor 43. - As described further above in the Summary section, the switch between the
first regulation corridor 43 and thesecond regulation corridor 45 may take place at irregular times, and without a prior indication of an elevated risk of expectation mismatch. In such aspects, the alternation between the two or more regulation corridors may be used to reduce the risk that expectation mismatch occurs. - The person skilled in the art realizes that the present invention by no means is limited to the preferred embodiments described above. On the contrary, many modifications and variations are possible within the scope of the appended claims. For example, many other metrics and combinations of metrics may be used to detect an elevated risk of expectation mismatch.
- In the claims, the word “comprising” does not exclude other elements or steps, and the indefinite article “a” or “an” does not exclude a plurality. A single processor or other unit may fulfill the functions of several items recited in the claims. The mere fact that certain measures are recited in mutually different dependent claims does not indicate that a combination of these measures cannot be used to advantage. Any reference signs in the claims should not be construed as limiting the scope.
Claims (1)
1. A driving automation method for a vehicle, said method comprising the steps of:
identifying a lane of a road traveled by the vehicle;
controlling a steering of the vehicle towards keeping the vehicle within a first regulation corridor in said lane, said first regulation corridor having a first width; and
intermittently controlling the steering of the vehicle towards keeping the vehicle within a second regulation corridor in said lane, said second regulation corridor having a second width greater than said first width.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
US17/379,099 US20210339764A1 (en) | 2018-10-17 | 2021-07-19 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
Applications Claiming Priority (4)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
EP18200909.2 | 2018-10-17 | ||
EP18200909.2A EP3640109A1 (en) | 2018-10-17 | 2018-10-17 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
US16/601,682 US11097746B2 (en) | 2018-10-17 | 2019-10-15 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
US17/379,099 US20210339764A1 (en) | 2018-10-17 | 2021-07-19 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
Related Parent Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/601,682 Division US11097746B2 (en) | 2018-10-17 | 2019-10-15 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
Publications (1)
Publication Number | Publication Date |
---|---|
US20210339764A1 true US20210339764A1 (en) | 2021-11-04 |
Family
ID=64017277
Family Applications (2)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/601,682 Active US11097746B2 (en) | 2018-10-17 | 2019-10-15 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
US17/379,099 Abandoned US20210339764A1 (en) | 2018-10-17 | 2021-07-19 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
Family Applications Before (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
US16/601,682 Active US11097746B2 (en) | 2018-10-17 | 2019-10-15 | System and method for detecting and/or preventing automation expectation mismatch in vehicle |
Country Status (2)
Country | Link |
---|---|
US (2) | US11097746B2 (en) |
EP (1) | EP3640109A1 (en) |
Families Citing this family (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP6520893B2 (en) * | 2016-04-01 | 2019-05-29 | 株式会社デンソー | Driving support device and driving support program |
DE102021103242A1 (en) | 2021-02-11 | 2022-08-11 | Bayerische Motoren Werke Aktiengesellschaft | AUTOMATED MOTOR VEHICLE AND METHOD OF CONTROLLING THE AUTOMATED MOTOR VEHICLE |
JP2022152869A (en) * | 2021-03-29 | 2022-10-12 | 本田技研工業株式会社 | Vehicle control device, vehicle control method and program |
US11912313B2 (en) | 2021-10-04 | 2024-02-27 | Arriver Software Llc | Human machine interaction monitor |
Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030156015A1 (en) * | 2001-04-12 | 2003-08-21 | Hermann Winner | Method for recognising a change in lane of a vehicle |
US20150149036A1 (en) * | 2013-11-26 | 2015-05-28 | Hyundai Mobis Co., Ltd. | Apparatus and method for controlling lane keeping of vehicle |
Family Cites Families (12)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP1638801A1 (en) * | 2003-06-06 | 2006-03-29 | Volvo Technology Corporation | Method and arrangement for controlling vehicular subsystems based on interpreted driver activity |
US7835834B2 (en) * | 2005-05-16 | 2010-11-16 | Delphi Technologies, Inc. | Method of mitigating driver distraction |
US20100045451A1 (en) * | 2008-08-25 | 2010-02-25 | Neeraj Periwal | Speed reduction, alerting, and logging system |
EP2356640A4 (en) * | 2008-11-13 | 2012-11-14 | Aser Rich Ltd | System and method for improved vehicle safety through enhanced situation awareness of a driver of a vehicle |
DE102011011714A1 (en) * | 2011-02-18 | 2012-08-23 | MAN Truck & Bus Aktiengesellschaft | Method for supporting a driver of a vehicle, in particular a motor vehicle or utility vehicle |
JP6232759B2 (en) * | 2013-06-07 | 2017-11-22 | ソニー株式会社 | Information processing apparatus, approaching object notification method, and program |
DE102013224962A1 (en) * | 2013-12-05 | 2015-06-11 | Robert Bosch Gmbh | Arrangement for creating an image of a scene |
DE102014201036A1 (en) * | 2014-01-21 | 2015-07-23 | Bayerische Motoren Werke Aktiengesellschaft | Image-based classification of driver status and / or driver behavior |
EP2949548B1 (en) * | 2014-05-27 | 2018-07-11 | Volvo Car Corporation | Lane keeping suppressing system and method |
GB2532457B (en) * | 2014-11-19 | 2018-04-18 | Jaguar Land Rover Ltd | Dynamic control apparatus and related method |
WO2017028895A1 (en) * | 2015-08-17 | 2017-02-23 | Polar Electro Oy | Enhancing vehicle system control |
US20180229768A1 (en) * | 2017-02-13 | 2018-08-16 | Delphi Technologies, Inc. | Enhanced lane-keeping system for automated vehicles |
-
2018
- 2018-10-17 EP EP18200909.2A patent/EP3640109A1/en not_active Withdrawn
-
2019
- 2019-10-15 US US16/601,682 patent/US11097746B2/en active Active
-
2021
- 2021-07-19 US US17/379,099 patent/US20210339764A1/en not_active Abandoned
Patent Citations (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20030156015A1 (en) * | 2001-04-12 | 2003-08-21 | Hermann Winner | Method for recognising a change in lane of a vehicle |
US20150149036A1 (en) * | 2013-11-26 | 2015-05-28 | Hyundai Mobis Co., Ltd. | Apparatus and method for controlling lane keeping of vehicle |
Also Published As
Publication number | Publication date |
---|---|
US20200122745A1 (en) | 2020-04-23 |
US11097746B2 (en) | 2021-08-24 |
EP3640109A1 (en) | 2020-04-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
US20210339764A1 (en) | System and method for detecting and/or preventing automation expectation mismatch in vehicle | |
US11254333B2 (en) | Electronic control device, vehicle control method, and vehicle control program product | |
US11713041B2 (en) | Control system and control method for driving a motor vehicle | |
US9619721B2 (en) | Monitoring a degree of attention of a driver of a vehicle | |
US10656641B2 (en) | Method and system for controlling a driving function of a vehicle | |
US8952799B2 (en) | Method and system for warning a driver of a vehicle about potential obstacles behind the vehicle | |
KR101690352B1 (en) | Collision monitor for a motor vehicle | |
JP2011086304A (en) | Detection of unintended lane departure | |
JP2001010368A (en) | Dozing drive determining method for dozing drive alarming system | |
US20200062246A1 (en) | Emergency braking device for vehicle | |
KR20160066053A (en) | Method and control unit for monitoring traffic | |
CN107139921B (en) | A kind of steering collision-proof method and system for vehicle | |
GB2529578A (en) | Method for assisting a driver of a motor vehicle and assisting device | |
US9266500B2 (en) | Method and evaluation system for supervising correct belt utilization | |
CN111731264A (en) | Continuous lane change driving behavior monitoring control method and system | |
US20230137063A1 (en) | Driver assistance device | |
WO2009060172A1 (en) | Detecting driver impairment | |
KR101462067B1 (en) | Apparatus and method for detecting drowsy driving using vehicle information | |
CN113753067B (en) | Lane departure intervention control method and device | |
KR20150051678A (en) | Apparatus and method for preventing accident of vehicle using lane keeping assist system and camera | |
US20220055664A1 (en) | Human-Supervised Autonomous Systems Performance and Safety Monitoring Methods and Apparatus | |
KR200489951Y1 (en) | Safety distance warning device for a car | |
KR20200024076A (en) | Emergency braking device for vehicle | |
US20230159010A1 (en) | Driver assistance device | |
KR20140076910A (en) | System and method for monitoring driver condition and driving status for motor vehicle |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
AS | Assignment |
Owner name: VOLVO CAR CORPORATION, SWEDEN Free format text: ASSIGNMENT OF ASSIGNORS INTEREST;ASSIGNORS:TIVESTEN, EMMA;LJUNG AUST, MIKAEL;VICTOR, TRENT;SIGNING DATES FROM 20191010 TO 20210518;REEL/FRAME:056901/0348 |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: DOCKETED NEW CASE - READY FOR EXAMINATION |
|
STPP | Information on status: patent application and granting procedure in general |
Free format text: NON FINAL ACTION MAILED |
|
STCB | Information on status: application discontinuation |
Free format text: ABANDONED -- FAILURE TO RESPOND TO AN OFFICE ACTION |