Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Summary of Claims
Claims 1-30 are pending
Claims 1-18, 20-30 are amended
Response to Arguments
Specification
Applicant’s arguments regarding the objection of the abstract has been fully considered and are persuasive. The objection has been withdrawn.
Claim Objections
Applicant’s arguments regarding the objections of claims 7 and 10 has been fully considered and are persuasive. The objection has been withdrawn.
The KIM Reference
Regarding the argument that KIM does not teach the "performing a plurality of simulations of outcomes for the vehicle and other vehicles resulting from stimulating the identified animal" within claim 1, the examiner respectfully disagrees. The applicant’s original claims set did not specify the identification of the animal type, instead it required the mere ability to "identify an animal detected" which would be understood using broadest reasonable interpretation to merely require detecting an animal. Given the amended claim explicitly requires the identity of the animal to be known, KIM no longer teaches the limitation of identifying the animal. Please See 35 USC § 103 below for clarification.
The Current Amendment to the Independent Claims
Applicant’s arguments with respect to claims 1-30 have been considered but are moot in view of the new ground(s) of rejection as necessitated by applicant's amendments. Please see 35 U.S.C. §103 rejection below.
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
Claims 1-8, 10-18, 20-27, 29, and 30 are rejected under 35 U.S.C. 103 as being unpatentable over KAROL (US20210114514A1) in view of KIM (US20170286570A1) in further view of MORALES (US 20160355181 A1).
Regarding claim 1:
KAROL discloses:
(Currently Amended) A method performed by a processing system of a vehicle for stimulating animal behavior, comprising: performing a recognition process to identify an animal detected in proximity to the vehicle; (see at least KAROL, ¶ 0034, “In some examples, the sensor data can be provided to a perception component 110 configured to determine a classification 112 associated with the object(s) 106 (e.g., car, truck, pedestrian, bicycle, motorcycle, animal, etc.). In various examples, the perception component 110 may determine an object classification 112 based on one or more features associated with the object(s) 106. The features may include a size (e.g., width, height, depth, etc.), shape (e.g., geometry, symmetry, etc.), and/or other distinguishing features of the object(s) 106. For example, the perception component 110 may recognize a size and/or shape of an object 106, such as object 106(1), corresponds to a pedestrian and a size and/or shape of another object 106, such as object 106(2), corresponds to a cyclist.”; ¶ 0050, “In some examples, the probability of conflict may be determined based on a classification 112 associated with the object 106. In such examples, the classification 112 associated with the object 106 may assist in determining the likelihood that the object 106 will maintain or alter a trajectory. For example, a deer detected on a side of a roadway may be unpredictable and thus may have a high likelihood of altering a trajectory to conflict with the vehicle 104. As such, the deer may be determined to be an object 106 that may potentially conflict with (e.g., is relevant to) the vehicle 104.”)
selecting one of the plurality of different animal stimuli modes based on the plurality of simulations of outcomes for the vehicle and the other vehicles; and (see at least KAROL, ¶ 0017; ¶ 0020, “In various examples, the determination of a substantial match between the object reaction and the expected reaction may include a match of a threshold number of actions (e.g., one matching actions, two matching actions, etc.), a threshold percentage of actions (e.g., 90%, 50%, etc.), or the like. In some examples, the substantial match may be determined based on a threshold match and/or threshold difference between the object reaction and the expected reaction. The actions may include trajectory modifications (e.g., increase in speed, decrease in speed, change in direction of travel, etc.), body movements (e.g., foot placement, head rotation, shoulder movement, etc.), gestures, or the like. For example, an expected reaction to the first warning signal may include a head and/or shoulder movement and a positional adjustment to an electronic device the object holds. The object reaction may include a head movement toward the vehicle. Based on a match of at least the head movement, the vehicle computing system may determine that the object reaction and the expected reaction substantially match. For another example, the vehicle computing system may determine that an object reaction matches an expected reaction at 75%, with a threshold match at 65%. Based on a determination that the percentage of the match meets or exceeds the threshold match, the vehicle computing system may determine that the object reaction substantially matches the expected reaction.”; ¶ 0021, “In some examples, the determination of a substantial match between the object reaction and the expected reaction may include determining that a modification to an object trajectory meets or exceeds a threshold modification. In some examples, the threshold modification may include a modification that renders the object irrelevant to the vehicle (e.g., does not impede progress of the vehicle, no potential for conflict, etc.). In such examples, based at least in part on determining the modification, the vehicle computing system may cause the vehicle to proceed along a vehicle trajectory (e.g., at a planned speed, direction, etc.). In some examples, the threshold modification may include a change in speed and/or direction associated with the object trajectory (e.g., 45 degrees, 90 degrees, etc.).”)
controlling the vehicle signal devicesbased on the selected animal stimuli mode. (see at least KAROL, ¶ 0010)
EXAMINERS NOTE: While KAROL does not explicitly name a simulation, it does perform the given actions based on processing environmental factors for an anticipated "optimal signal".
EXAMINERS NOTE: While KAROL does not explicitly state it performs computations based on the result of other vehicles, it does communicate and utilize sensor data from other nearby vehicles to coordinate actions. Additionally, KAROL does anticipate the tracking of objects in relation to other vehicle paths.
KAROL does not disclose, but KIM teaches:
performing a plurality of simulations of outcomes, for the vehicle and other vehicles, resulting from (see at least KIM, ¶ 0005, “From this categorization, the automated dynamic object generation system may extract a set of random variables that characterize the erroneous behavior of the object described by the object data. The set of random variables may be used to generate a virtual dynamic object in a simulation (provided by the virtual simulation software) that behave in a similar manner as the object described by the object data did in the real world as described by the accident database. In some implementations, the automated dynamic object generation system may extract behavior data from the accident database that describes the set of random variables for the object described by the object data. This process may be repeated for multiple objects included in the accident database to create multiple virtual dynamic objects for inclusion in a simulation.”; ¶ 0026, Virtualization software may test the performance of software included in an autonomous vehicle. For example, the simulation may include one or more virtual dynamic objects that sometimes behave erroneously in the simulation. Examples of virtual dynamic objects may include one or more of the following (including any similar or related objects): a vehicle; a pedestrian; an animal or some other object in the roadway; traffic lights that may sometimes malfunction; variable roadway surface friction (e.g., the roadway surface may be slippery, icy, dry, sandy, etc.); and variable visibility conditions (e.g., there may be fog, snow, ice, darkness or some other condition that affects visibility).”; ¶ 0073, “The simulation displayed by the GUI 133 may test how the virtual vehicle responds to a dynamic virtual object 198 in various conditions or settings. For example, the vehicle design included in the simulation may be a design for an automated vehicle. The virtualization application 155 may generate the virtual vehicle that represents the automated vehicle based on a vehicle model that describes the physical hardware of the vehicle and a software model that describes the software of the vehicle. The software model includes the software that controls how the automated vehicle would respond to one or more obstacles or challenges. The virtual vehicle may respond to the virtual obstacles or challenges in the simulation in a manner that is the same or similar to how the automated vehicle would respond to real world-versions of these obstacles or challenges in the real world. For example, the simulation may include moving images that are displayed on the GUI 133. The GUI 133 may include a virtual roadway 197. A virtual vehicle representing the automated vehicle may drive on the virtual roadway 197 during the simulation. The virtual roadway 197 may include one or more dynamic virtual objects 198 (e.g., swerving vehicles, poor visibility weather conditions, pedestrians that are jay walking in the path of the virtual vehicle, animals or objects in the path of the vehicle, etc.). The virtual vehicle will respond to the one or more dynamic virtual objects 198 in the simulation in a manner that is the same or similar to how the automated vehicle would respond to real world-versions of these obstacles or challenges in the real world.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
KAROL in view of KIM does not disclose, but MORALES teaches:
determining one or more possible animal responses by the animal based on: (see at least MORALES, ¶ 0017, “In the aspect described above, the collision avoidance assistance device for a vehicle may further include an assistance processing selection unit configured to select a mode of the assistance processing for collision avoidance based on the determined type of the animal. In addition, the assistance processing performing unit may be configured to perform the assistance processing for the selected mode. As already described above, the behavior characteristics of an animal when the vehicle approaches the animal differ according to the type. Therefore, the assistance efficient for collision avoidance differs according to the animal type. For example, the generation of a warning is efficient for an animal of the type that reacts to sound or light and moves away from the vehicle. The assistance by braking or steering the vehicle for allowing the vehicle to avoid entering the presence area of the animal is efficient for an animal of the type that does not react to a warning and enters the traveling road. That is, the mode of efficient assistance processing differs according to the determined type of the animal. Therefore, if an animal is detected around the vehicle and there is a possibility that the animal will collide with the vehicle, the mode of assistance processing may also be selected according to the type of the animal. This mode allows for the provision of more suitable driving assistance for collision avoidance. This also reduces discomfort and strangeness in the surroundings or reduces those of the driver or occupants.”)
the identity of the animal; and(see at least MORALES, ¶ 0005, “In general, animals (for example, livestock such as a horse, ox, and sheep and wild animals such as a deer, wild goat, bear, kangaroo) that may enter the traveling road of a vehicle differ in the behavior pattern or the behavior characteristics according to the type. For example, the behavior of an animal when a vehicle approaches the animal depends on the type of the animal; the animal runs away (flees) from the vehicle, stands transfixed where the animal is, approaches the vehicle, or runs into the traveling road. The moving speed and the moving direction of the animal also differ among animal types. Therefore, when an animal is detected in the image of the traveling road in the traveling direction of the vehicle or in the image of its surroundings, the type of the animal must be identified; otherwise, it is difficult to estimate where the animal will move after it is detected, that is, the position where the animal will exist or the area where the animal is likely to exist in the future. In addition, it may become difficult to accurately determine the possibility of collision between the vehicle and the animal. On this point, if the object is an animal and if the type of the animal is not identified and the tendency of the behavior cannot be predicted, it is not known in which direction and at what speed the image of the animal in the captured image will move. Therefore, in predicting the animal's future presence area, it may become necessary to understand the tendency of the behavior of the animal or to make an image analysis of a relatively large area in the image for tracking the image of the animal. However, because the image information is four-dimensional information having the two-dimensional coordinate values, brightness, and time, the calculation load and the processing time are significantly increased as the analysis range of the image area becomes larger. This means that the quick implementation of collision possibility determination and collision avoidance assistance requires higher-performance calculation processing device and memory, resulting in an increase in the cost.”)
a plurality of different animal stimuli modes of one or more vehicle signal devices of the vehicle; (see at least MORALES, ¶ 0006, “In addition, when the behavior characteristics of animals differ among animal types, efficient assistance for collision avoidance also differs among animal types. When a warning by sound and light is issued to an animal detected ahead of the vehicle, the reaction differs among animal types; some animals are highly sensitive to the warning and move away from the vehicle and some other animals do not react to the warning at all and enter the traveling road with little or no change in the behavior. In particular, in the former case, collision can be avoided by issuing a warning by sound or light with no need to apply the brake or to perform a steering operation on the vehicle. In the latter case, collision can be avoided by applying the brake or by performing the steering operation on the vehicle. Conversely, when collision can be avoided only by issuing a warning, driving assistance by applying the brake or by performing the steering operation on the vehicle is not necessary. Similarly, when collision can be avoided by applying the brake or performing the steering operation on the vehicle, the generation of a warning is not necessary. Therefore, when an animal is detected as an object in the image of the traveling road in the traveling direction of the vehicle or in the image of its surroundings, it is preferable that assistance for collision avoidance be provided in a more suitable mode according to the type of the animal.”)
the one or more possible animal responses to the plurality of different animal stimuli modes; (see at least MORALES, ¶ 0006; ¶ 0017)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making with the virtual vehicle simulation abilities of KAROL in view KIM to incorporate decision making based on animal type and warning reaction efficacy within MORALES effectively yield an effective safer reaction decision system that accounts for specific animal reaction abilities.
Regarding claim 2:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL does not disclose, but KIM teaches:
the plurality of simulations of outcomes for the vehicle and other vehicles (see at least KIM, ¶ 0005, “From this categorization, the automated dynamic object generation system may extract a set of random variables that characterize the erroneous behavior of the object described by the object data. The set of random variables may be used to generate a virtual dynamic object in a simulation (provided by the virtual simulation software) that behave in a similar manner as the object described by the object data did in the real world as described by the accident database. In some implementations, the automated dynamic object generation system may extract behavior data from the accident database that describes the set of random variables for the object described by the object data. This process may be repeated for multiple objects included in the accident database to create multiple virtual dynamic objects for inclusion in a simulation.”; ¶ 0026, “Virtualization software may test the performance of software included in an autonomous vehicle. For example, the simulation may include one or more virtual dynamic objects that sometimes behave erroneously in the simulation. Examples of virtual dynamic objects may include one or more of the following (including any similar or related objects): a vehicle; a pedestrian; an animal or some other object in the roadway; traffic lights that may sometimes malfunction; variable roadway surface friction (e.g., the roadway surface may be slippery, icy, dry, sandy, etc.); and variable visibility conditions (e.g., there may be fog, snow, ice, darkness or some other condition that affects visibility).”; ¶ 0073, “The simulation displayed by the GUI 133 may test how the virtual vehicle responds to a dynamic virtual object 198 in various conditions or settings. For example, the vehicle design included in the simulation may be a design for an automated vehicle. The virtualization application 155 may generate the virtual vehicle that represents the automated vehicle based on a vehicle model that describes the physical hardware of the vehicle and a software model that describes the software of the vehicle. The software model includes the software that controls how the automated vehicle would respond to one or more obstacles or challenges. The virtual vehicle may respond to the virtual obstacles or challenges in the simulation in a manner that is the same or similar to how the automated vehicle would respond to real world-versions of these obstacles or challenges in the real world. For example, the simulation may include moving images that are displayed on the GUI 133. The GUI 133 may include a virtual roadway 197. A virtual vehicle representing the automated vehicle may drive on the virtual roadway 197 during the simulation. The virtual roadway 197 may include one or more dynamic virtual objects 198 (e.g., swerving vehicles, poor visibility weather conditions, pedestrians that are jay walking in the path of the virtual vehicle, animals or objects in the path of the vehicle, etc.). The virtual vehicle will respond to the one or more dynamic virtual objects 198 in the simulation in a manner that is the same or similar to how the automated vehicle would respond to real world-versions of these obstacles or challenges in the real world.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
KAROL in view of KIM does not disclose, but MORALES teaches:
use information regarding behaviors of the identified animal obtained from a database accessible by a processor of the vehicle. (see at least MORALES, ¶ 0030. “The collision avoidance assistance device may further include a memory, and the controller may be further configured to retrieve the behavior characteristics index values of the determined type of the animal from the memory.”; ¶ 0034, “According to another aspect of an exemplary embodiment, a vehicle comprising a collision avoidance assistance device is provided. The collision avoidance assistance device may include a camera configured to acquire an image of an area around the vehicle; and an electronic control device. The electronic control device may be configured to: detect an image of an animal in the image of the area around the vehicle, determine a type of the animal detected in the image, retrieve behavior characteristics index values representing behavior characteristics of the determined type of the animal, calculate a future presence area of the animal based on the behavior characteristics index values, determine a probability of a collision between the animal and the vehicle based on the calculated future presence area of the animal, and perform a collision avoidance assistance function based on the determined probability of the collision between the animal and the vehicle.”)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making with the virtual vehicle simulation abilities of KAROL in view KIM to incorporate decision making based on animal type and warning reaction efficacy within MORALES effectively yield an effective safer reaction decision system that accounts for specific animal reaction abilities.
Regarding claim 3:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
use information regarding behaviors of the identified animal provided as an output by a trained artificial intelligence (AI) model executed by a processor of the vehicle. (see at least KAROL, ¶ 0115, “In various examples, the reaction determination component 432 may receive the expected reaction from a machine learning component 434 or machine learning component 454 of the computing device(s) 442. In such examples, the machine learning component 434 and/or 454 may be configured to receive data associated with the object and/or the set of characteristics associated with the warning signal and output an expected reaction. The machine learning components 434 and/or 454 may include one or more models trained utilizing training data comprising a plurality of object reactions to a plurality of warning signals.”; ¶ 0116, “In various examples, the machine learning components 434 and/or 454 may be trained to determine an optimal signal for alerting an object of the presence of the vehicle. The optimal signal may be based on one or more real-time considerations present in the environment, such as environmental factors, weather conditions, object activity, and the like (as described above). The optimal signal may include a signal that has the greatest probability of being successful in alerting a particular object to the presence and/or operation of the vehicle.”; ¶ 0117, “In some examples, the machine learning components 434 and/or 454 may be trained utilizing training data including previously emitted warning signals, object reactions thereto, and/or associated real-time considerations associated therewith. In such examples, the machine learning components 434 and/or 454 may be configured to receive input comprising real-time considerations and may output an optimal warning signal (e.g., characteristics associated with an optimal warning signal) and/or an expected reaction thereto. In various examples, the training data may include the previously emitted signals and associated reactions and/or real-time considerations that were successful in causing objects to move away from and/or out of the way of the vehicle 402. In such examples, the optimal signal output by the machine learning components 434 and/or 454 to alert a particular object may include a signal that resulted in another object with similar attributes to the particular object reacting according to an expected reaction (e.g., staying out of the vehicle path, moving out of the vehicle path, acknowledging the presence of the vehicle 402, etc.).”)
KAROL does not disclose, but KIM teaches:
the plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding claim 4:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
identifying one or more road conditions, (see at least KAROL, ¶ 0012, “The vehicle computing system may be configured to emit a first warning signal to alert one or more objects in the environment of the vehicle presence and/or operation. The first warning signal may include an audio signal and/or a light signal. The first warning signal may include a first set of characteristics, such as frequency, volume, luminosity, color, shape, motion, or the like. In various examples, the first warning signal may be emitted based on a detection of an object in the environment and/or features associated with the detection. In such examples, the features associated with the detection may include a distance between the vehicle and the object, a relative speed between the vehicle and the object, and the like. For example, the vehicle computing system may detect a bicyclist on the road and may determine that the bicyclist may not hear the vehicle approaching from behind. The vehicle computing system may emit a warning signal toward the bicyclist, such as to warn the bicyclist of the vehicle's approach so that the bicyclist does not swerve or otherwise maneuver into the road.”; ¶ 0039, “In some examples, the one or more characteristics of the first set of characteristics may be determined based on weather conditions in the environment. The weather conditions may include rain, wind, sleet, hail, snow, temperature, humidity, large pressure changes, or any other weather phenomenon which may affect an auditory perception of an object 106 in the environment 100. In various examples, the one or more characteristics of the warning signal may be determined based on road conditions in the environment. The road conditions may include a smoothness of road surface (e.g., concrete, asphalt, gravel, etc.), a number of potholes, uneven terrain (e.g., rumble strips, washboards, corrugation of road, etc.), or the like. For example, objects 106 and/or vehicles 104 operating on a gravel road may generate a larger amount of noise than when operating on a smooth surface. The increase in noise generated by the objects 106 and/or vehicles 104 (e.g., impact amount of noise from travel) may result in a subsequent increase in the determined volume and/or volume range of the warning signal.”)
the identified one or more road conditions. (see at least KAROL, ¶ 0012; ¶ 0039)
KAROL does not disclose, but KIM teaches:
wherein the plurality of simulations of outcomes take into account (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding claim 5:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
identifying one or more traffic conditions, (see at least KAROL, ¶ 0012, “The vehicle computing system may be configured to emit a first warning signal to alert one or more objects in the environment of the vehicle presence and/or operation. The first warning signal may include an audio signal and/or a light signal. The first warning signal may include a first set of characteristics, such as frequency, volume, luminosity, color, shape, motion, or the like. In various examples, the first warning signal may be emitted based on a detection of an object in the environment and/or features associated with the detection. In such examples, the features associated with the detection may include a distance between the vehicle and the object, a relative speed between the vehicle and the object, and the like. For example, the vehicle computing system may detect a bicyclist on the road and may determine that the bicyclist may not hear the vehicle approaching from behind. The vehicle computing system may emit a warning signal toward the bicyclist, such as to warn the bicyclist of the vehicle's approach so that the bicyclist does not swerve or otherwise maneuver into the road.”; ¶ 0036, “In various examples, the first set of characteristics may be determined dynamically, such as based on one or more real-time conditions associated with the environment 100. The real-time conditions may include data associated with the object 106 (e.g., object attribute (e.g., classification, position (e.g., facing/moving toward the vehicle, facing/moving away from the vehicle, etc.), distance from the vehicle, trajectory, etc.), object activity (e.g., walking, running, riding a scooter, (e.g., a particular activity implied by an object trajectory, such as based on speed, etc.), reading a book, talking on a phone, viewing data on an electronic device, interacting with another vehicle, interacting with another object (e.g., talking to another person, looking into a stroller, etc.), eating, drinking, operating a sensory impairment device (e.g., cane, hearing aid, etc.), listening to headphones, etc.), environmental factors (e.g., noise level in the environment 100, amount of traffic, road conditions, etc.), weather conditions (e.g., rain, snow, hail, wind, etc.), vehicular considerations (e.g., speed, passengers in the vehicle 104, etc.), and the like. For example, the first set of characteristics associated with a first warning signal generated for a pedestrian wearing headphones may include a first frequency and a first set of characteristics associated with a first warning signal generated for a pedestrian that is looking in a direction associated with the vehicle may include a second frequency.”)
take into account the identified one or more traffic conditions. (see at least KAROL, ¶ 0012; ¶ 0036)
KAROL does not disclose, but KIM teaches:
wherein the plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding claim 6:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
identifying ambient lighting conditions, (see at least KAROL, ¶ 0112, “The vehicle computing system may be configured to emit a first warning signal to alert one or more objects in the environment of the vehicle presence and/or operation. The first warning signal may include an audio signal and/or a light signal. The first warning signal may include a first set of characteristics, such as frequency, volume, luminosity, color, shape, motion, or the like. In various examples, the first warning signal may be emitted based on a detection of an object in the environment and/or features associated with the detection. In such examples, the features associated with the detection may include a distance between the vehicle and the object, a relative speed between the vehicle and the object, and the like. For example, the vehicle computing system may detect a bicyclist on the road and may determine that the bicyclist may not hear the vehicle approaching from behind. The vehicle computing system may emit a warning signal toward the bicyclist, such as to warn the bicyclist of the vehicle's approach so that the bicyclist does not swerve or otherwise maneuver into the road.”; ¶ 0043, “In various examples, the warning signal component 114 may generate (e.g., determine the first set of characteristics) and/or cause the first warning signal to be emitted based on a location associated with the vehicle 104. The location may include a school zone, a construction zone, proximity to a playground, a business district, a downtown area, or the like. In some examples, the warning signal component 114 may generate and/or cause the first warning signal to be emitted based on a time of day, day of the week, season, date (e.g., holiday, etc.), or the like. In some examples, the warning signal component 114 may generate and/or cause the first warning signal to be emitted based on a speed associated with the vehicle 104. In such examples, based on a determination that the vehicle 104 is traveling at or below a threshold speed (e.g., 28 kilometers per hour, 22 miles per hour, 15 miles per hour, etc.), the warning signal component 114 may cause the first warning signal to be emitted.”)
take into account the identified ambient lighting conditions. (see at least KAROL, ¶ 0112; ¶ 0043)
KAROL does not disclose, but KIM teaches:
wherein the plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding claim 7:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
identifying one or more weather conditions, (see at least KAROL, ¶ 0012, “The vehicle computing system may be configured to emit a first warning signal to alert one or more objects in the environment of the vehicle presence and/or operation. The first warning signal may include an audio signal and/or a light signal. The first warning signal may include a first set of characteristics, such as frequency, volume, luminosity, color, shape, motion, or the like. In various examples, the first warning signal may be emitted based on a detection of an object in the environment and/or features associated with the detection. In such examples, the features associated with the detection may include a distance between the vehicle and the object, a relative speed between the vehicle and the object, and the like. For example, the vehicle computing system may detect a bicyclist on the road and may determine that the bicyclist may not hear the vehicle approaching from behind. The vehicle computing system may emit a warning signal toward the bicyclist, such as to warn the bicyclist of the vehicle's approach so that the bicyclist does not swerve or otherwise maneuver into the road.”; ¶ 0039, “In some examples, the one or more characteristics of the first set of characteristics may be determined based on weather conditions in the environment. The weather conditions may include rain, wind, sleet, hail, snow, temperature, humidity, large pressure changes, or any other weather phenomenon which may affect an auditory perception of an object 106 in the environment 100. In various examples, the one or more characteristics of the warning signal may be determined based on road conditions in the environment. The road conditions may include a smoothness of road surface (e.g., concrete, asphalt, gravel, etc.), a number of potholes, uneven terrain (e.g., rumble strips, washboards, corrugation of road, etc.), or the like. For example, objects 106 and/or vehicles 104 operating on a gravel road may generate a larger amount of noise than when operating on a smooth surface. The increase in noise generated by the objects 106 and/or vehicles 104 (e.g., impact amount of noise from travel) may result in a subsequent increase in the determined volume and/or volume range of the warning signal.”)
take into account the identified (see at least KAROL, ¶ 0012; ¶ 0039)
KAROL does not disclose, but KIM teaches:
wherein the plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding claim 8:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
take into account probabilities of each of a plurality of behaviors that the identified animal may perform in response to each stimulus mode. (see at least KAROL, ¶ 0048, “In various examples, the object 106 may be relevant to the vehicle 104 based on a probability of conflict (e.g., likelihood of collision) between the object 106 and the vehicle 104. The probability of conflict may be based on a determined likelihood that the object 106 will continue on the object trajectory and/or alter the object trajectory to one that conflicts with the vehicle 104. In some examples, the probability of conflict may correspond to a likelihood (e.g., probability) of conflict between the vehicle 104 and the object 106 being above a threshold level (e.g., threshold probability) of conflict.”; ¶ 0050; ¶ 0051, “In some examples, based on a determination of relevance, the warning signal component 114 of the computing system(s) 102 may generate the first warning signal to alert the relevant object(s) 106 in the environment of the vehicle 104 presence and/or operation. As discussed above, a first set of characteristics (e.g., frequency, volume, luminosity, color, shape, motion, etc.) of the first warning signal may be determined based on classifications 112 associated with the relevant object(s) 106.”)
KAROL does not disclose, but KIM teaches:
the plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding claim 10:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
comprises performing the plurality of simulations of outcomes in offline simulations to generate a training database, and applying the training database to a machine learning model to generate a trained artificial intelligence (AI) model that can be implemented in a vehicle processor; and (see at least KAROL, ¶ 0115, “In various examples, the reaction determination component 432 may receive the expected reaction from a machine learning component 434 or machine learning component 454 of the computing device(s) 442. In such examples, the machine learning component 434 and/or 454 may be configured to receive data associated with the object and/or the set of characteristics associated with the warning signal and output an expected reaction. The machine learning components 434 and/or 454 may include one or more models trained utilizing training data comprising a plurality of object reactions to a plurality of warning signals.”; ¶ 0116, “In various examples, the machine learning components 434 and/or 454 may be trained to determine an optimal signal for alerting an object of the presence of the vehicle. The optimal signal may be based on one or more real-time considerations present in the environment, such as environmental factors, weather conditions, object activity, and the like (as described above). The optimal signal may include a signal that has the greatest probability of being successful in alerting a particular object to the presence and/or operation of the vehicle.”; ¶ 0117, “In some examples, the machine learning components 434 and/or 454 may be trained utilizing training data including previously emitted warning signals, object reactions thereto, and/or associated real-time considerations associated therewith. In such examples, the machine learning components 434 and/or 454 may be configured to receive input comprising real-time considerations and may output an optimal warning signal (e.g., characteristics associated with an optimal warning signal) and/or an expected reaction thereto. In various examples, the training data may include the previously emitted signals and associated reactions and/or real-time considerations that were successful in causing objects to move away from and/or out of the way of the vehicle 402. In such examples, the optimal signal output by the machine learning components 434 and/or 454 to alert a particular object may include a signal that resulted in another object with similar attributes to the particular object reacting according to an expected reaction (e.g., staying out of the vehicle path, moving out of the vehicle path, acknowledging the presence of the vehicle 402, etc.).”)
selecting one of the different stimuli modes to be performed by vehicle signal devices to elicit a behavior of the identified animal based on the plurality of simulated outcomes for the vehicle and other vehicles comprises applying at least (see at least KAROL, ¶ 0011, “The vehicle computing system may be configured to identify objects in the environment. In some examples, the objects may be identified based on sensor data from sensors (e.g., cameras, motion detectors, lidar, radar, etc.) of the vehicle. In some examples, the objects may be identified based on sensor data received from remote sensors, such as, for example, sensors associated with another vehicle or sensors mounted in an environment that are configured to share data with a plurality of vehicles. In various examples, the vehicle computing system may be configured to determine classifications associated with the objects, such as whether the objects are pedestrians, bicyclists, animals, other vehicles, or the like.”; ¶ 0018, “In various examples, the vehicle computing system may compare the object reaction to an expected reaction (also referred to generally as an object action) associated with the first warning signal (also referred to generally as a first signal). In various examples, the vehicle computing system may be configured to determine the expected reaction based on one or more characteristics of the first warning signal (e.g., volume, frequency, luminosity, color, motion (e.g., animated motion, light sequencing, etc.), shape of the signal, etc.) and/or data associated with the object (e.g., object attribute (e.g., classification, position (e.g., facing/moving toward the vehicle, facing/moving away from the vehicle, etc.), distance from the vehicle, trajectory, etc.), object activity (e.g., walking, running, riding a scooter, (e.g., a particular activity implied by an object trajectory, such as based on speed, etc.), reading a book, talking on a phone, viewing data on an electronic device, interacting with another vehicle, interacting with another object (e.g., talking to another person, looking into a stroller, etc.), eating, drinking, operating a sensory impairment device (e.g., cane, hearing aid, etc.), listening to headphones, etc.). In some examples, the vehicle computing system may access a database of expected reactions to determine the expected reaction associated with the first warning signal. In such examples, the expected reactions in the database may be stored based at least in part on the data associated with the object and/or characteristic(s) of the first warning signal. In various examples, the vehicle computing system may determine an expected reaction utilizing machine learning techniques. In such examples, a model may be trained utilizing training data including a plurality of warning signals and detected reactions thereto.”; ¶ 0020, “In various examples, the determination of a substantial match between the object reaction and the expected reaction may include a match of a threshold number of actions (e.g., one matching actions, two matching actions, etc.), a threshold percentage of actions (e.g., 90%, 50%, etc.), or the like. In some examples, the substantial match may be determined based on a threshold match and/or threshold difference between the object reaction and the expected reaction. The actions may include trajectory modifications (e.g., increase in speed, decrease in speed, change in direction of travel, etc.), body movements (e.g., foot placement, head rotation, shoulder movement, etc.), gestures, or the like. For example, an expected reaction to the first warning signal may include a head and/or shoulder movement and a positional adjustment to an electronic device the object holds. The object reaction may include a head movement toward the vehicle. Based on a match of at least the head movement, the vehicle computing system may determine that the object reaction and the expected reaction substantially match. For another example, the vehicle computing system may determine that an object reaction matches an expected reaction at 75%, with a threshold match at 65%. Based on a determination that the percentage of the match meets or exceeds the threshold match, the vehicle computing system may determine that the object reaction substantially matches the expected reaction.”; ¶ 0032, “The techniques described herein may be implemented in a number of ways. Example implementations are provided below with reference to the following figures. Although discussed in the context of an autonomous vehicle, the methods, apparatuses, and systems described herein may be applied to a variety of systems (e.g., a sensor system or a robotic platform), and are not limited to autonomous vehicles. In another example, the techniques may be utilized in an aviation or nautical context, or in any system using machine vision (e.g., in a system using image data). Additionally, the techniques described herein may be used with real data (e.g., captured using sensor(s)), simulated data (e.g., generated by a simulator), or any combination of the two.”; ¶ 0116; ¶ 0194, “Based on a determination that the object reacts according to an expected reaction (“Yes” at operation 706), the process, at operation 710, may include determining whether an area for the object to move out of the vehicle path is identified. In some examples, the area may include a location that is not in the vehicle path, a lane associated with the vehicle, and/or an adjacent lane. In such examples, the area may include a location to which the blocking object may move to no longer block progress of the vehicle and/or other vehicles/objects traveling in the lane and/or the adjacent lane. In some examples, the area may include a size large enough for the object to move and no longer block progress of the vehicle and/or other vehicles/objects. In some examples, the area may include a location that the operator of the object may be unable to view, such as based on a viewing path being blocked by another object.”)
vehicle sensor, (see at least KAROL, ¶ 0011)
map, and (see at least KAROL, ¶ 0049, “In various examples, the vehicle computing system may determine the probability of conflict utilizing a top down representation of the environment, such as that described in the U.S. patent applications incorporated herein above. In some examples, the vehicle computing system may input the top down representation of the environment into a machine learned model configured to output a heat map indication predicting probabilities associated with future positions of the object 106 (e.g., predicting object trajectories and/or probabilities associated therewith). In such examples, the vehicle computing system may project the movement of the vehicle 104 forward in time and determine a probability of conflict between an amount of overlap between the heat map associated with the object 106 and future positions of the vehicle 104 as determined by the projection forward in time.”; ¶ 0057, “As illustrated with respect to object 106(2), the expected reaction 120(2) may include a change in trajectory associated with the object 106(2). The change in the trajectory may include a modification to the speed (e.g., speed up, slow down, change speed a threshold amount, etc.) and/or direction the object 106(2) travels. In various examples, the computing system 102 may determine an updated predicted object trajectory based on additional sensor data from the sensors at a time after emitting the first warning signal. In some examples, the updated predicted object trajectory may be determined utilizing the top-down representation of the environment and/or heat maps associated therewith, such as that described in the U.S. patent applications incorporated herein by reference above. In various examples, the computing system(s) 102 may determine a modification to the object trajectory (e.g., difference between the predicted object trajectory and the updated predicted object trajectory determined after emitting the first warning signal). In some examples, the expected reaction may be based on the modification. For example, the expected reaction may include an object slowing a forward speed or changing a direction of travel (e.g., from an intersecting trajectory to a parallel trajectory with the vehicle 104). The computing system(s) 102 may compare the modification and/or updated object trajectory to the expected reaction 120(2) to determine whether the object 106(2) reacts in accordance with the expected reaction.”)
traffic data (see at least KAROL, ¶ 0033, “FIG. 1 is an illustration of an environment 100, in which one or more computing systems 102 of an autonomous vehicle 104 (e.g., vehicle 104) may utilize a dynamic warning signal system to alert one or more objects 106 of a presence and/or operation of the vehicle 104 in the environment 100. The computing system(s) 102 may detect the object(s) 106 based on sensor data captured by one or more sensors 108 of the vehicle 104 and/or one or one or more remote sensors (e.g., sensors mounted on another vehicle 104 and/or mounted in the environment 100, such as for traffic monitoring, collision avoidance, or the like). The sensor(s) 108 may include data captured by lidar sensors, radar sensors, ultrasonic transducers, sonar sensors, location sensors (e.g., GPS, compass, etc.), inertial sensors (e.g., inertial measurement units (IMUs), accelerometers, magnetometers, gyroscopes, etc.), cameras (e.g., RGB, IR, intensity, depth, time of flight, etc.), microphones, time-of-flight sensors, environment sensors (e.g., temperature sensors, humidity sensors, light sensors, pressure sensors, etc.), and the like.”)
into the trained AI model in the vehicle processor and receiving as an output one of the different stimuli modes to be performed by vehicle signal devices. (see at least KAROL, ¶ 0059, “In various examples, the vehicle computing system may determine an expected reaction 120 utilizing machine learning techniques. As will be discussed in greater detail below with regard to FIG. 4, in some examples, the computing system(s) 102 may include a reaction training component configured to train a model utilizing machine learning techniques to determine an expected reaction 120 to a warning signal. In such examples, the model may be trained with training data including a plurality of warning signals and detected reactions thereto.”; ¶ 0120, “Responsive to a determination that the object reaction substantially matches the expected reaction, the reaction determination component 432 may determine that the object has been alerted to the vehicle 402 presence and/or operation. In various examples, based on the determination of a substantial match, the reaction determination component 432 may cause data associated with the warning signal and the object reaction to be stored in the reaction database 436 and/or the reaction database 456. In some examples, based on a determination of a substantial match, the reaction determination component 432 may provide data associated with the object reaction and the warning signal to the machine learning components 434 and/or 454, such as to train the machine learning components 434 and/or 454 to output relevant expected reactions.”)
KAROL does not disclose, but KIM teaches:
performing a plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
Regarding Claim 11:
With regards to claim 11, this claim is the system claim to method claim 1 and is therefore rejected using the same references and rationale. The reference to the processor executable instruction can be found in KAROL ¶ 0141.
Regarding Claim 12:
With regards to claim 12, this claim is substantially similar to claim 2 and is therefore rejected using the same references and rationale.
Regarding Claim 13:
With regards to claim 13, this claim is substantially similar to claim 3 and is therefore rejected using the same references and rationale.
Regarding Claim 14:
With regards to claim 14, this claim is substantially similar to claim 4 and is therefore rejected using the same references and rationale.
Regarding Claim 15:
With regards to claim 15, this claim is substantially similar to claim 5 and is therefore rejected using the same references and rationale.
Regarding Claim 16:
With regards to claim 16, this claim is substantially similar to claim 6 and is therefore rejected using the same references and rationale.
Regarding Claim 17:
With regards to claim 17, this claim is substantially similar to claim 7 and is therefore rejected using the same references and rationale.
Regarding Claim 18:
With regards to claim 18, this claim is substantially similar to claim 8 and is therefore rejected using the same references and rationale.
Regarding Claim 20:
With regards to claim 20, this claim is the means claim to method claim 1 and is therefore rejected using the same references and rationale.
Regarding Claim 21:
With regards to claim 21, this claim is substantially similar to claim 2 and is therefore rejected using the same references and rationale.
Regarding Claim 22:
With regards to claim 22, this claim is substantially similar to claim 3 and is therefore rejected using the same references and rationale.
Regarding Claim 23:
With regards to claim 23, this claim is substantially similar to claim 4 and is therefore rejected using the same references and rationale.
Regarding Claim 24:
With regards to claim 24, this claim is substantially similar to claim 5 and is therefore rejected using the same references and rationale.
Regarding Claim 25:
With regards to claim 25, this claim is substantially similar to claim 6 and is therefore rejected using the same references and rationale.
Regarding Claim 26:
With regards to claim 26, this claim is substantially similar to claim 7 and is therefore rejected using the same references and rationale.
Regarding Claim 27:
With regards to claim 27, this claim is substantially similar to claim 8 and is therefore rejected using the same references and rationale.
Regarding Claim 29:
With regards to claim 29, this claim is the non-transitory memory claim to method claim 1 and is therefore rejected using the same references and rationale. The reference to the non-transitory memory can be found in KAROL ¶ 0141.
Regarding Claim 30:
With regards to claim 30, this claim is substantially the same scope as all of the claims 2-3 combined and is therefore rejected using the same references and rationale.
Claim(s) 9, 19, 28 are rejected under 35 U.S.C. 103 as being unpatentable over KAROL (US20210114514A1) in view of KIM (US20170286570A1) in further view of MORALES (US 20160355181 A1) in further view of COMMONS (US9015093B1).
Regarding claim 9:
KAROL in view of KIM in further view of MORALES discloses the limitations within claim 1 and KAROL further discloses:
for the vehicle and other vehicles that take into account probabilities of (see at least KAROL, ¶ 0019, “Based on the comparison between the object reaction and the expected reaction, the vehicle computing system may determine whether the object reacted as expected (e.g., whether a substantial match exists between the object reaction and the expected reaction). Responsive to a determination that the object reaction substantially matches the expected reaction, the vehicle computing system may store the encounter (e.g., data associated with first warning signal and the object reaction) in the database. In some examples, the database may be used for future object reaction comparisons, such as to increase a confidence in a reaction to the first warning signal, to train the machine learned model, or the like.”; ¶ 0020, “In various examples, the determination of a substantial match between the object reaction and the expected reaction may include a match of a threshold number of actions (e.g., one matching actions, two matching actions, etc.), a threshold percentage of actions (e.g., 90%, 50%, etc.), or the like. In some examples, the substantial match may be determined based on a threshold match and/or threshold difference between the object reaction and the expected reaction. The actions may include trajectory modifications (e.g., increase in speed, decrease in speed, change in direction of travel, etc.), body movements (e.g., foot placement, head rotation, shoulder movement, etc.), gestures, or the like. For example, an expected reaction to the first warning signal may include a head and/or shoulder movement and a positional adjustment to an electronic device the object holds. The object reaction may include a head movement toward the vehicle. Based on a match of at least the head movement, the vehicle computing system may determine that the object reaction and the expected reaction substantially match. For another example, the vehicle computing system may determine that an object reaction matches an expected reaction at 75%, with a threshold match at 65%. Based on a determination that the percentage of the match meets or exceeds the threshold match, the vehicle computing system may determine that the object reaction substantially matches the expected reaction.”; ¶ 0032, “The techniques described herein may be implemented in a number of ways. Example implementations are provided below with reference to the following figures. Although discussed in the context of an autonomous vehicle, the methods, apparatuses, and systems described herein may be applied to a variety of systems (e.g., a sensor system or a robotic platform), and are not limited to autonomous vehicles. In another example, the techniques may be utilized in an aviation or nautical context, or in any system using machine vision (e.g., in a system using image data). Additionally, the techniques described herein may be used with real data (e.g., captured using sensor(s)), simulated data (e.g., generated by a simulator), or any combination of the two.”)
animal behaviors, (see at least KAROL, ¶ 0020)
vehicle behaviors, and (see at least KAROL, ¶ 0012, “The vehicle computing system may be configured to emit a first warning signal to alert one or more objects in the environment of the vehicle presence and/or operation. The first warning signal may include an audio signal and/or a light signal. The first warning signal may include a first set of characteristics, such as frequency, volume, luminosity, color, shape, motion, or the like. In various examples, the first warning signal may be emitted based on a detection of an object in the environment and/or features associated with the detection. In such examples, the features associated with the detection may include a distance between the vehicle and the object, a relative speed between the vehicle and the object, and the like. For example, the vehicle computing system may detect a bicyclist on the road and may determine that the bicyclist may not hear the vehicle approaching from behind. The vehicle computing system may emit a warning signal toward the bicyclist, such as to warn the bicyclist of the vehicle's approach so that the bicyclist does not swerve or otherwise maneuver into the road.”)
driver reactions. (see at least KAROL, ¶ 0010, “This disclosure is directed to techniques for improving vehicle warning systems. The vehicle warning systems may be configured to emit a sound and/or a light to warn objects (e.g., dynamic object) in an environment proximate the vehicle of a potential conflict with the vehicle. The vehicle may include an autonomous or semi-autonomous vehicle. The objects may include pedestrians, bicyclists, animals (e.g., dogs, cats, birds, etc.), other vehicles (e.g., cars, trucks, motorcycles, mopeds, etc.), or any other object that may potentially cause a conflict (e.g., collision) with the vehicle. A vehicle computing system may be configured to identify an object in the environment and determine that a potential conflict between the vehicle and the object may occur. The vehicle computing system may emit a first signal to warn the object of the potential conflict and, based on a determination that an object reaction did not substantially match an expected reaction, emit a second (different) signal. The vehicle computing system may continue to modify warning signals until the object reacts according to the expected reaction or the object is no longer relevant to the vehicle (e.g., potential of collision no longer exists), thereby maximizing safe operation of the vehicle.”; ¶ 0110, “In various examples, the signal emission component 430 may dynamically determine the set of characteristics associated with the warning signal, such as based on real-time conditions. The real-time conditions may include one or more environmental factors (e.g., noise level in the environment 100, amount of traffic, proximity to the object 106, etc.), weather conditions (e.g., rain, snow, hail, wind, etc.), vehicular considerations (e.g., speed, passengers in the vehicle 104, etc.), data associated with the object 106 (e.g., object attribute (e.g., classification, position (e.g., facing/moving toward the vehicle, facing/moving away from the vehicle, etc.), distance from the vehicle, trajectory, etc.), object activity (e.g., walking, running, riding a scooter, (e.g., a particular activity implied by an object trajectory, such as based on speed, etc.), reading a book, talking on a phone, viewing data on an electronic device, interacting with another vehicle, interacting with another object (e.g., talking to another person, looking into a stroller, etc.), eating, drinking, operating a sensory impairment device (e.g., cane, hearing aid, etc.), listening to headphones, etc.), and the like. In such examples, the signal emission component 430 may receive data associated with the environment, such as from the localization component 420 and/or the perception component 422, and may dynamically determine the set of characteristics associated with the warning signal.”)
KAROL does not disclose, but KIM teaches:
performing the plurality of simulations of outcomes (see at least KIM, ¶ 0005; ¶ 0026; ¶ 0073)
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the “expected reaction” decision making of KAROL to incorporate the virtual vehicle simulation abilities of KIM to effectively yield a safer reaction decision system.
KAROL in view of KIM does not disclose, but COMMONS teaches:
comprises performing Monte Carlo simulations of outcomes (see at least COMMON, Col 20 lines 16-34, "One way to quantify the noise of an information processing system is to weight the signals received by a network with an "importance" or "relevance" or other normalized criterion. The weighting may be derived empirically, or adaptively, or as a part of the basic training of a network. As those signals are being processed, their weighted utility in producing a useful output of the hierarchically superior layer is analyzed. Thus, if the absolute value of all weights applied to an input or set of related inputs are (in the aggregate) small relative to other inputs, the inputs are insignificant and may be deemed noise. Likewise, if the weights are large, but are correlated and have offsetting sign, they may be noise, though a more detailed analysis may be in order. Indeed, as part of the processing scheme, a Monte Carlo style simulation (or less comprehensive schema) may be employed to determine a sensitivity of each output to each input or combination of inputs. In similar fashion, if the neural network is implemented as an analog network, noise may be permitted or injected on each line, with the outputs analyzed for sensitivity to the inputs."; Col 25 lines 21-35, “Neural network 2116 is a feed-forward neural network that performs processing actions at stage/order 4, the Nominal stage/order, of the model described in Table 1. At the Nominal stage/order, an intelligent system can identify simple relationships between concepts and label them. Neural network 2116 has one hidden layer. The neurons in this layer receive excitatory and inhibitory input based on the centroids, dimensions, coordinates, and history of centroid positions at successive one-second time points of objects and persons that was received from neural network 2114. The neurons also receive input from other neurons within the hidden layer. The determination that "another vehicle" has a "motion vector that may lead to a collision" is signaled by excitatory input from neurons, within the hidden layer, activated by patterns for "motion vector that may lead to a collision" and that share contiguous and overlapping store coordinates with "another vehicle." When "another vehicle" has become associated with "motion vector that may lead to a collision," an output signal is triggered. Neural network 2116 then outputs to neural network 2118 an array pattern for the "motion vector that may lead to a collision" and the history of store coordinates of the "another vehicle" array at successive times. The array pattern uniquely identifies the "another vehicle" and the "motion vector that may lead to a collision" as being associated with the "another vehicle." This information can now be fed to a rule-based system that can calculate an appropriate response to avoid the collision. Persons skilled in the art will note that this rule-based system will need to take the motion vectors of the other vehicles and pedestrians, as well as the present road signs and traffic control devices, into account.")
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify, with a reasonable expectation of success, the simulation decision-based reaction generation system of KAROL in view of KIM to incorporate the machine learning training with Monte Carlo simulations of COMMONS to yield a safer decision making-processor by allowing the vehicle to more quickly determine the appropriate stimulation to warn outside individuals/animals.
EXAMINERS NOTE: While KAROL does not explicitly use Monte Carlo simulations for preparing outputs of the simulation, it does rely on probabilities of certain responses to the vehicle-generated warnings by outside objects and continuously modifies its expected “optimal signal” based on the current environment and outcome of the actuation.
EXAMINERS NOTE: While KAROL does not explicitly account for driver reactions, it does account for other vehicles as objects that need to be tracked and warned.
Regarding Claim 19:
With regards to claim 19, this claim is substantially similar to claim 9 and is therefore rejected using the same references and rationale.
Regarding Claim 28:
With regards to claim 28, this claim is substantially similar to claim 9 and is therefore rejected using the same references and rationale.
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any nonprovisional extension fee (37 CFR 1.17(a)) pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure.
COHEN (US20210005086A1)
¶ 0013, “An autonomous driver assistance system incorporates a variety of sensors (infrared, radar, lidar, ultrasonic, visible light cameras, etc.), a processor programmed with animal detection algorithms, networking capabilities, power supply, a multi-frequency ultrasonic animal repellant device, are mounted on a vehicle. The sensors collect image data of the vehicle's surroundings, then computer vision algorithms pre-programmed in the computer identify and classify animals according to their species, age, speed, location in relation to the vehicle, so that the system may estimate its hearing range, and the likelihood and severity of a collision with the vehicle. The system then autonomously triggers an ultrasonic device, on the vehicle's exterior, to emit sound waves to repel the specific animal profile. The system also alerts the driver to the presence of the animal on the road, and may also initiate a braking or honking sequence. The sensors may observe if the animal responds to the sound, by analyzing video for movement, and if not, the system triggers additional sound waves of different frequency and duration. The system transmits data from these events to an external computer for aggregation and analysis. The data is displayed on web and mobile interfaces which allows user to search, generate reports, and adapt driving behavior.”
SHAMBIK (US 20170154241 A1)
¶ 0009, “In another aspect, the present disclosure is directed to a method of detecting an animal in a vicinity of a vehicle. The method includes receiving a plurality of images of the vicinity of the vehicle from one or more image capture devices; receiving a truncated animal appearance template, wherein the truncated animal appearance template corresponds to appearance of at least a portion of a body and one or more limbs of an animal without a shape of a head of the animal; processing the plurality of images using the truncated animal appearance template to detect, in at least one image from the plurality of images, visual information that corresponds to the truncated animal appearance template; and initiating a vehicle response when visual information corresponding to the truncated animal appearance template is detected in at least two images of the plurality of images.”
¶ 0161, “According to embodiments of the presently disclosed subject matter, the kinematic modeling can include various predefined animal attributes and/or animal behavior models, which can be used to predict the animal's behavior and the collision hazard. The animal's behavior model can be sensitive to a location of the animal relative to the vehicle, a motion of the animal, the animal's position, orientation, speed, etc. and state (e.g., walking, eating, standing, in the midst of a pack, etc.), and also to various states and/or attributes of the vehicle. The animal's behavior model can also be sensitive to an animal's type, and the animal detection process can be capable of providing an indication of a type of the detected animal. Thus, for example, if an animal is detected while standing on the road on which the vehicle is travelling and as the vehicle draws near the animal starts running off the road, the kinematic modeling operation can conclude that while an animal is successfully detected and the detection is approved across a plurality of frames, the detected animal does not pose a risk to the vehicle, since there is not risk of a collision. In a reverse example, an animal may be detected on the sides of the road, and as the vehicle approaches, the animal starts to run and enters a collision course with the encroaching vehicle.”
Any inquiry concerning this communication or earlier communications from the examiner should be directed to RAFAEL VELASQUEZ VANEGAS whose telephone number is (571)272-6999. The examiner can normally be reached M-F 8 - 4.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, VIVEK KOPPIKAR can be reached at (571) 272-5109. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/RAFAEL VELASQUEZ VANEGAS/Patent Examiner, Art Unit 3667
/JOAN T GOODBODY/Examiner, Art Unit 3667
Prosecution Insights