DETAILED ACTION
Notice of Pre-AIA or AIA Status
1. The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
2. This communication is a first office action, non-final rejection on the merits. Claims 1-12 and 14-20, filed as preliminary amendment, are currently pending and have been considered below.
Claim Rejections - 35 USC § 103
3. 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.
4. Claims 4, 2-3, 6,9,12,14-16, 18 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Nishibeppu et al. ( USP 2025/0013245) in view of LI (DE-102004-037730).
As Per Claim 4, Nishibeppu et al. (Nishibeppu) discloses, an autonomous vehicle ( the work vehicle 10 being a robot tactor performing an autonomous travel in the field F ([0032], Figs. 1-3) comprising: a camera system: ( camera 53, Fig.1) [0051]) a controller (vehicle control device 11, Fig.1); and an obstacle detection system (obstacle detection device 15, Fig.1) in communication with the camera system, ([0048]) wherein the obstacle detection system is configured to: receive visual data from the camera system; (“the obstacle detection device 15 determines the type of the detection target (measurement target) based on the capture images acquired from the camera 53”, [0131]), and calculate a probability of an obstacle being present based on the visual data; (“In step S4, the obstacle detection device 15 calculates the likelihood of the detection target that has been determined. For example, when it has been determined based on the capture images that the detection target is a person, the obstacle detection device 15 calculates the likelihood (probability) that indicates the possibility (certainty) of a person based on the distance to the detection target”, [0132], fig.12); and wherein the controller is configured to: determine the presence of an obstacle if a calculated probability in the obstacle detection system is above a probability threshold; (“Next, in step S5, the vehicle control device 11 determines whether the likelihood of the detection target that has been calculated by the obstacle detection device 15 exceeds the likelihood threshold. When the vehicle control device 11 is determined that the likelihood of the detection target exceeds the likelihood threshold (S5:Yes), the vehicle control device 11 shifts the processing to step S6”, [0133], fig.12); and send an inhibit signal to stop or inhibit movement of the autonomous vehicle; (“In step S6, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing. Specifically, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target”, [0134], Fig.12).
However, Nishibeppu does not explicitly teach, wherein the controller is configured to: receive speed data from the vehicle speed sensor, and, determining if the speed of the autonomous vehicle is below a speed threshold based on the speed data, and if the speed is determined to be below the speed threshold, activate the obstacle detection system.
In an analogous art, LI discloses a self-adaptive vehicle speed detection device being equipped with microprocessor 10, memory 30, vehicle speed sensor VSS obstacle detection sensor 40, wherein the controller (microprocessor 10, Fig.1) is configured to: receive speed data from the vehicle speed sensor (VSS, Fig.1), and, determining if the speed of the autonomous vehicle is below a speed threshold based on the speed data, and if the speed is determined to be below the speed threshold, activate the obstacle detection system (“If the vehicle speed is less than the threshold, the microprocessor generates ( 10 ), therefore, a control command to activate the obstacle detection sensor”, Page 4, 4th para., See Abstract, background, also see Page 2, 2nd para.; Page 3 1st para -Page 4, 4th para, Claims 1-2, Figs. 1-2)
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu and LI before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings ( a self-adaptive vehicle speed detection device) of LI and configure with the system of Nishibeppu in order to microprocessor receiving current vehicle speed from VSS and comparing with the threshold speed , when the vehicle speed is less than the threshold value, the microprocessor is generating a command to activate the obstacle detection sensor. Motivation to combine the two teachings is, to cause the vehicle execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target (i.e., collision avoidance, an added feature to enhance safety of the vehicle).
As per Claim 2, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI teaches, wherein the controller is configured to activate the obstacle detection system at start-up of the autonomous vehicle (Nishibeppu : [0070]).
As per Claim 3, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI teaches, wherein the controller is configured to keep the obstacle detection system active at all times during autonomous operation (Nishibeppu : [0130]-[0131]).
As per Claim 6, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI teaches, wherein the camera system comprises a front-facing camera to provide visual data of the front and/or front sides of the autonomous vehicle.( ( Nishibeppu : [0052], Fig.2).
As per Claim 9, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI teaches, wherein the camera system comprises a rear-facing camera, and wherein the controller is configured to activate the obstacle detection system when the vehicle is reversing.
( Nishibeppu : [0067][0052], Fig.2).
As per Claim 12, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI teaches, wherein the autonomous vehicle is a mower, a yard truck, a loader, a wheel loader, a track loader, a dump truck, a digger, a backhoe, a forklift, a harvester, a tractor, a land leveler, a scraper, a dozer, a trencher, a grader, a seeder, a fertilizer, or a harrow. (Nishibeppu : the vehicle 10 being a robot tractor , [0032]), Fig.2).
As per Claim 14, Nishibeppu as modified by LI teaches the limitation of Claim 16. However, Nishibeppu in view of LI teaches, determining whether the autonomous vehicle is at start-up, and activating the obstacle detection system if it is determined to be at start-up. (Nishibeppu : [0070], Fig.4).
As per Claim 15, Nishibeppu as modified by LI teaches the limitation of Claim 16. However, Nishibeppu in view of LI teaches, determining whether the autonomous vehicle is operating autonomously, and keeping the obstacle detection system active at all times during autonomous operation. (Nishibeppu : [0130], Fig.3).
As Per Claim 16, Nishibeppu et al. ( Nishibeppu) discloses, a method of controlling an autonomous vehicle, (“The work vehicle 10 is a so-called robot tractor that is configured to be capable of performing autonomous travel in a field F (see FIG. 3) according to a preset target route R”, [0032]), the method comprising: activating an obstacle detection algorithm including: (“Specifically, as shown in FIG. 1, the detection control unit 51 includes various processing units such as an acquisition processing unit 511, a determination processing unit 512, and an output processing unit 513. Note that the obstacle detection device 15 functions as the various processing units by causing the CPU to execute various types of processing according to the obstacle detection program”, [0069]); receiving visual data relating to data from a camera system on the autonomous vehicle; (“The acquisition processing unit 511 acquires capture images from the camera 53, and acquires measurement information from the obstacle sensor 54.”, [0070]; “The camera 53 is a digital camera that captures an image of a subject included in a predetermined imaging range, and outputs the image as digital image data. The camera 53 continuously captures images of a subject at a predetermined frame rate, generates frame images (capture images) at a predetermined resolution, and sequentially transmits the frame images to the detection control unit 51”, [0051]); calculating a probability of an obstacle being present based on the visual data: (“In step S4, the obstacle detection device 15 calculates the likelihood of the detection target that has been determined. For example, when it has been determined based on the capture images that the detection target is a person, the obstacle detection device 15 calculates the likelihood (probability) that indicates the possibility (certainty) of a person based on the distance to the detection target.”, [0132]);
if the probability is above a probability threshold: (“ in step S5, the vehicle control device 11 determines whether the likelihood of the detection target that has been calculated by the obstacle detection device 15 exceeds the likelihood threshold. When the vehicle control device 11 is determined that the likelihood of the detection target exceeds the likelihood threshold (S5:Yes), the vehicle control device 11 shifts the processing to step S6”, [0133]); determining the presence of an obstacle; (“Next, in step S5, the vehicle control device 11 determines whether the likelihood of the detection target that has been calculated by the obstacle detection device 15 exceeds the likelihood threshold. When the vehicle control device 11 is determined that the likelihood of the detection target exceeds the likelihood threshold (S5:Yes), the vehicle control device 11 shifts the processing to step S6”, [0133]); sending an inhibit signal to stop or inhibit movement of the autonomous vehicle; (“In step S6, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing. Specifically, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target”, [0134]).
However, Nishibeppu does not explicitly teach, receiving speed data relating to speed of the autonomous vehicle; determining if the speed of the autonomous vehicle is below a speed threshold based on the speed data; if the speed is determined to be below the speed threshold, activating the obstacle detection system.
In an analogous art, LI discloses a self-adaptive vehicle speed detection device being equipped with microprocessor 10, memory 30, vehicle speed sensor VSS obstacle detection sensor 40, receiving speed data relating to speed of the autonomous vehicle; (via microprocessor 10, receiving speed data from Vehicle speed sensor VSS, Fig.1) determining if the speed of the autonomous vehicle is below a speed threshold based on the speed data; if the speed is determined to be below the speed threshold, activating the obstacle detection system. (“If the vehicle speed is less than the threshold, the microprocessor generates ( 10 ), therefore, a control command to activate the obstacle detection sensor”, Page 4, 4th para., See Abstract, background, Page 2, 2nd para.; Page 3 1st para -Page 4, 4th para, Claims 1-2, Figs. 1-2)
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu and LI before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings ( a self-adaptive vehicle speed detection device) of LI and configure with the system of Nishibeppu in order to microprocessor receiving current vehicle speed from VSS and comparing with the threshold speed, when the vehicle speed is less than the threshold value, the microprocessor is generating a command to activate the obstacle detection sensor. Motivation to combine the two teachings is, to cause the vehicle execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target (i.e., collision avoidance, an added feature to enhance safety of the vehicle).
As per Claim 18, Nishibeppu as modified by LI teaches the limitation of Claim 16. However, Nishibeppu in view of LI teaches, wherein the camera system comprises a rear-facing camera, and wherein the method comprises: determining whether the vehicle is being controlled to reverse, and if the vehicle is being controlled to reverse, activating the obstacle detection system (“An example of a case where a detection target in a front direction is detected when the work vehicle 10 is performing forward travel will be described below. An example of a case where a detection target in a rear direction is detected when the work vehicle 10 is performing reverse travel will be omitted”, [0067]), .. “Furthermore, the camera 53 includes a front camera 53f that is capable of imaging an imaging range at the front when viewed from the work vehicle 10, and a rear camera 53r that is capable of imaging an imaging range at the rear when viewed from the work vehicle 10. As shown in FIG. 2, the front camera 53f is arranged on the upper front side of the cabin 138, and the rear camera 53r is arranged on the upper rear side of the cabin 138”, [0052]).
As per Claim 20, Nishibeppu as modified by LI teaches the limitation of Claim 16. However, Nishibeppu in view of LI teaches, wherein the autonomous vehicle is a mower, a yard truck, a loader, a wheel loader, a track loader, a dump truck, a digger, a backhoe, a forklift, a harvester, a tractor, a land leveler, a scraper, a dozer, a trencher, a grader, a seeder, a fertilizer, or a harrow. (Nishibeppu : the vehicle 10 being a robot tractor , [0032]), Fig.2).
5. Claims 5 and 17 are rejected under 35 U.S.C. 103 as being unpatentable over Nishibeppu et al. ( USP 2025/0013245) in view of Sonehara et al. ( CN-118119989).
As Per Claim 5, Nishibeppu et al. ( Nishibeppu) discloses, an autonomous vehicle ( the work vehicle 10 being a robot tactor performing an autonomous travel in the field F ([0032], Figs. 1-3) comprising: a camera system: ( camera 53, Fig.1) [0051]) a controller; ( vehicle control device 11, Fig.1) and an obstacle detection system ( obstacle detection device 15, Fig.1)[0053]); in communication with the camera system, ([0048]) wherein the obstacle detection system is configured to: receive visual data from the camera system; (“the obstacle detection device 15 determines the type of the detection target (measurement target) based on the capture images acquired from the camera 53”, [0131]); and calculate a probability of an obstacle being present based on the visual data; (“In step S4, the obstacle detection device 15 calculates the likelihood of the detection target that has been determined. For example, when it has been determined based on the capture images that the detection target is a person, the obstacle detection device 15 calculates the likelihood (probability) that indicates the possibility (certainty) of a person based on the distance to the detection target”, [0132], fig.12); and wherein the controller is configured to: determine the presence of an obstacle if a calculated probability in the obstacle detection system is above a probability threshold; (“ in step S5, the vehicle control device 11 determines whether the likelihood of the detection target that has been calculated by the obstacle detection device 15 exceeds the likelihood threshold. When the vehicle control device 11 is determined that the likelihood of the detection target exceeds the likelihood threshold (S5:Yes), the vehicle control device 11 shifts the processing to step S6”, [0133], fig.12); and send an inhibit signal to stop or inhibit movement of the autonomous vehicle; (“In step S6, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing. Specifically, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target”, [0134], Fig.12).
However, Nishibeppu does not explicitly teach, a vehicle speed sensor configured to determine the speed of the autonomous vehicle; wherein the controller is configured to: receive speed data from the vehicle speed sensor, and, determine if the speed of the autonomous vehicle is above a speed threshold based on the speed data; and if the speed is above a speed threshold, activate the obstacle detection system.
In an analogous art, Sonehara et al. ( Sonehara) discloses, obstacle detecting device of connecting vehicle, wherein, a vehicle speed sensor configured to determine the speed of the autonomous vehicle; ( “the automatic driving system 1A has an obstacle detecting device 40 and a driving control part 50… The obstacle sensor 30 is connected to the obstacle detecting device 40. In addition, an angle sensor 10 and a vehicle speed sensor 20 can also be connected to the obstacle detecting device 40”, Page 8, 4th para, Fig.1-2)); wherein the controller is configured to:
receive speed data from the vehicle speed sensor, and, determine if the speed of the autonomous vehicle is above a speed threshold based on the speed data; and if the speed is above a speed threshold, activate the obstacle detection system. ( “If the vehicle speed sensor 20 detects a vehicle speed above a first threshold value and the angle sensor 10 detects a connection angle above a second threshold value ("Yes" in step S11) Then the obstacle detecting device 40 executes the calculation processing of the first monitoring area and the second monitoring area (step S12), Page 16, 4th para, also see Page 6, 3rd para; Page 8, 4th para;Page9 4th para, Page 10, 3rd-4th para; Page 16, 3rd para., Figs. 1-4).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu and Sonehara before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (obstacle detecting device and speed sensor etc.) of Sonehara and configure with the system of Nishibeppu in order to when control unit receiving speed sensor data higher than the first threshold value then the obstacle detection device performing a calculation process for monitoring the presence or absence of the obstacle. Motivation to combine the two teachings is, to cause the vehicle execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target (i.e., collision avoidance, an added feature to enhance safety of the vehicle).
As Per Claim 17, Nishibeppu et al. ( Nishibeppu) discloses, a method of controlling an autonomous vehicle, (“The work vehicle 10 is a so-called robot tractor that is configured to be capable of performing autonomous travel in a field F (see FIG. 3) according to a preset target route R”, [0032])
the method comprising: activating an obstacle detection algorithm including:(“Specifically, as shown in FIG. 1, the detection control unit 51 includes various processing units such as an acquisition processing unit 511, a determination processing unit 512, and an output processing unit 513. Note that the obstacle detection device 15 functions as the various processing units by causing the CPU to execute various types of processing according to the obstacle detection program”, [0069]); receiving visual data relating to data from a camera system on the autonomous vehicle; (“The acquisition processing unit 511 acquires capture images from the camera 53, and acquires measurement information from the obstacle sensor 54.”, [0070]; “The camera 53 is a digital camera that captures an image of a subject included in a predetermined imaging range, and outputs the image as digital image data. The camera 53 continuously captures images of a subject at a predetermined frame rate, generates frame images (capture images) at a predetermined resolution, and sequentially transmits the frame images to the detection control unit 51”, [0051]); calculating a probability of an obstacle being present based on the visual data;
(“In step S4, the obstacle detection device 15 calculates the likelihood of the detection target that has been determined. For example, when it has been determined based on the capture images that the detection target is a person, the obstacle detection device 15 calculates the likelihood (probability) that indicates the possibility (certainty) of a person based on the distance to the detection target.”, [0132]); if the probability is above a probability threshold: (“Next, in step S5, the vehicle control device 11 determines whether the likelihood of the detection target that has been calculated by the obstacle detection device 15 exceeds the likelihood threshold. When the vehicle control device 11 is determined that the likelihood of the detection target exceeds the likelihood threshold (S5:Yes), the vehicle control device 11 shifts the processing to step S6”, [0133]); determining the presence of an obstacle; (“in step S5, the vehicle control device 11 determines whether the likelihood of the detection target that has been calculated by the obstacle detection device 15 exceeds the likelihood threshold. When the vehicle control device 11 is determined that the likelihood of the detection target exceeds the likelihood threshold (S5:Yes), the vehicle control device 11 shifts the processing to step S6”, [0133]); sending an inhibit signal to stop or inhibit movement of the autonomous vehicle; (“In step S6, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing. Specifically, the vehicle control device 11 causes the work vehicle 10 to execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target”, [0134]).
However, Nishibeppu does not explicitly teach, receiving speed data relating to speed of the autonomous vehicle; determining if the speed of the autonomous vehicle is above a speed threshold based on the speed data; if the speed is determined to be above the speed threshold, activating the obstacle detection system.
In an analogous art, Sonehara et al. ( Sonehara) discloses, obstacle detecting device of connecting vehicle, wherein, receiving speed data relating to speed of the autonomous vehicle; ( “the automatic driving system 1A has an obstacle detecting device 40 and a driving control part 50… The obstacle sensor 30 is connected to the obstacle detecting device 40. In addition, an angle sensor 10 and a vehicle speed sensor 20 can also be connected to the obstacle detecting device 40”, Page 8, 4th para, Fig.1-2)); determining if the speed of the autonomous vehicle is above a speed threshold based on the speed data; if the speed is determined to be above the speed threshold, activating the obstacle detection system ( “If the vehicle speed sensor 20 detects a vehicle speed above a first threshold value and the angle sensor 10 detects a connection angle above a second threshold value ("Yes" in step S11) Then the obstacle detecting device 40 executes the calculation processing of the first monitoring area and the second monitoring area (step S12), Page 16, 4th para, also see Page 6, 3rd para; Page 8, 4th para;Page9 4th para, Page 10, 3rd-4th para; Page 16, 3rd para., Figs. 1-4).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu and Sonehara before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (obstacle detecting device and speed sensor etc. ) of Sonehara and configure with the system of Nishibeppu in order to when control unit receiving speed sensor data higher than the first threshold value then the obstacle detection device performing a calculation process for monitoring the presence or absence of the obstacle. Motivation to combine the two teachings is, to cause the vehicle execute the countermeasure processing (stopping processing, deceleration processing, or notification processing) according to the position of the detection target (i.e., collision avoidance, an added feature to enhance safety of the vehicle).
6. Claims 7-8, 10 -11 and 19 are rejected under 35 U.S.C. 103 as being unpatentable over Nishibeppu et al. ( USP 2025/0013245) in view of LI (DE-102004-037730) in view of Popov et al. (USP 2021/0156960).
As per Claim 7, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI does not explicitly teach, wherein the camera system comprises a camera facing an operator seat on the autonomous vehicle.
In an analogous art, Popov et al. ( Popov) discloses, deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications,
wherein the camera system comprises a camera facing an operator seat on the autonomous vehicle. ( via “ autonomous machines using deep neural networks (DNNs)” [0027] using “In-cabin monitoring camera sensor is preferably monitored by a neural network running on another instance of the Advanced SoC, configured to identify in cabin events and respond accordingly. An in-cabin system may perform lip reading to activate cellular service and place a phone call, dictate emails, change the vehicle's destination, activate or change the vehicle's infotainment system and settings, or provide voice-activated web surfing”. [0171]).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu, Li and Popov before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (software and in-cabin cameras) of Popov and configure with the system of Nishibeppu in order to in-cabin cameras detecting the facial expression the driver and providing the driver an additional functions (e.g., placing phone calls, dictating an email etc.) when the vehicle is operating in an autonomous mode. Motivation to combine the two teachings is, ease of communication.
As per Claim 8, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI does not explicitly teach, wherein the camera system comprises a camera selected from the group consisting of a camera with a fish-eye lens, an electro-optical camera, a stereo camera, a depth camera, an infrared camera, a neuromorphic camera, and a hyperspectral camera.
In an analogous art, Popov et al. ( Popov) discloses, deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications,
wherein the camera system comprises a camera selected from the group consisting of a camera with a fish-eye lens, an electro-optical camera, a stereo camera, a depth camera, an infrared camera, a neuromorphic camera, and a hyperspectral camera.
( via “Cameras with a field of view that include portions of the environment to the side of the vehicle 1300 (e.g., side-view cameras) may be used for surround view, providing information used to create and update the occupancy grid, as well as to generate side impact collision warnings. For example, surround camera(s) 1374 (e.g., four surround cameras 1374 as illustrated in FIG. 13B) may be positioned to on the vehicle 1300. The surround camera(s) 1374 may include wide-view camera(s) 1370, fisheye camera(s), 360 degree camera(s), and/or the like. Four example, four fisheye cameras may be positioned on the vehicle's front, rear, and sides”, [0133]), [0134], Fig.13B-13C).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu, Li and Popov before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (software and in-cabin cameras) of Popov and configure with the system of Nishibeppu in order to fisheye cameras having improved field of view as compared to standard cameras. Motivation to combine the two teachings is, improved surrounding monitoring (i.e., collision avoidance).
As per Claim 10, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI does not explicitly teach, wherein calculated probabilities are filtered based on a Bayes filter, a hidden Markov model, or a moving average filter.
In an analogous art, Popov et al. ( Popov) discloses, deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications,
wherein calculated probabilities are filtered based on a Bayes filter, a hidden Markov model, or a moving average filter(“In some embodiments, machine learning model(s) 108 may be implemented using a DNN, such as a convolutional neural network (CNN). Although certain embodiments are described with machine learning model(s) 108 being implemented using neural network(s), and specifically CNN(s), this is not intended to be limiting. For example, and without limitation, machine learning model(s) 108 may include any type of machine learning model, such as a machine learning model(s) using linear regression, logistic regression, decision trees, support vector machines (SVM), Naïve Bayes”.[0047]).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu, Li and Popov before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (software and in-cabin cameras) of Popov and configure with the system of Nishibeppu in order to machine learning models allowing for prediction of classification/objects which can increase the accuracy of the object detection. Motivation to combine the two teachings is, precision in object detection (i.e., collision avoidance).
As per Claim 11, Nishibeppu as modified by LI teaches the limitation of Claim 4. However, Nishibeppu in view of LI does not explicitly teach, wherein the obstacle detection system comprises a cascade classifier or deep learning algorithm.
In an analogous art, Popov et al. ( Popov) discloses, deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications, wherein the obstacle detection system comprises a cascade classifier or deep learning algorithm (“the system of the present disclosure may implement a deep learning solution (e.g., using a deep neural network (DNN), such as a convolutional neural network (CNN)) for autonomous vehicles to detect moving and stationary obstacles and other objects from RADAR data.”, [0006], also see [0027], [0046]).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu, Li and Popov before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (software and in-cabin cameras) of Popov and configure with the system of Nishibeppu in order to machine learning models allowing for prediction of classification/objects which can increase the accuracy of the object detection. Motivation to combine the two teachings is, precision in object detection (i.e., collision avoidance).
As per Claim 19, Nishibeppu as modified by LI teaches the limitation of Claim 16. However, Nishibeppu in view of LI does not explicitly teach, filtering, based on a Bayes filter, a hidden Markov model, or a moving average filter, calculated probabilities.
In an analogous art, Popov et al. ( Popov) discloses, deep neural network for detecting obstacle instances using radar sensors in autonomous machine applications,
filtering, based on a Bayes filter, a hidden Markov model, or a moving average filter, calculated probabilities (“Turning now to FIG. 3, FIG. 3 is an illustration of an example implementation of machine learning model(s) 108, in accordance with some embodiments of the present disclosure. At a high level, machine learning model(s) 108, in accordance with some embodiments of the present disclosure… “In order to detect objects from the input, machine learning model(s) 108 may predict classification data (e.g., class confidence tensor 110) and/or object instance data such as location, size, and/or orientation data for each class (e.g., instance regression tensor 112”).[0046]…
“In some embodiments, machine learning model(s) 108 may be implemented using a DNN, such as a convolutional neural network (CNN). Although certain embodiments are described with machine learning model(s) 108 being implemented using neural network(s), and specifically CNN(s), this is not intended to be limiting. For example, and without limitation, machine learning model(s) 108 may include any type of machine learning model, such as a machine learning model(s) using linear regression, logistic regression, decision trees, support vector machines (SVM), Naïve Bayes”, [0047]).
It would have been obvious to one of ordinary skill in the art, having the teachings of Nishibeppu, Li and Popov before him before the effective filing date of the claimed invention to modify the systems of Nishibeppu to include the teachings (software and in-cabin cameras) of Popov and configure with the system of Nishibeppu in order to machine learning models allowing for prediction of classification/objects which can increase the accuracy of the object detection. Motivation to combine the two teachings is, precision in object detection (i.e., collision avoidance).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to MUHAMMAD SHAFI whose telephone number is (571)270-5741. The examiner can normally be reached M-F 8:30 am -5:00 pm.
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, Scott Browne can be reached at 571-270-0151. 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.
/MUHAMMAD SHAFI/Primary Examiner, Art Unit 3666C
