DETAILED ACTION
This is the first office action regarding application number 19/233,145, filed June 10, 2025. This is a Non-Final Office Action on the merits, Claims 1-22 are currently pending and are addressed below.
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 .
Priority
Acknowledgement is made of applicants claim for domestic priority based on an provisional application filed on June 13, 2024.
Drawings
The drawings are objected to as failing to comply with 37 CFR 1.84(p)(5) because they do not include the following reference sign(s) mentioned in the description: Paragraph [0192] item 1510. Corrected drawing sheets in compliance with 37 CFR 1.121(d) are required in reply to the Office action to avoid abandonment of the application. Any amended replacement drawing sheet should include all of the figures appearing on the immediate prior version of the sheet, even if only one figure is being amended. Each drawing sheet submitted after the filing date of an application must be labeled in the top margin as either “Replacement Sheet” or “New Sheet” pursuant to 37 CFR 1.121(d). If the changes are not accepted by the examiner, the applicant will be notified and informed of any required corrective action in the next Office action. The objection to the drawings will not be held in abeyance.
Specification
The lengthy specification has not been checked to the extent necessary to determine the presence of all possible minor errors. Applicant’s cooperation is requested in correcting any errors of which applicant may become aware in the specification.
Applicant is reminded of the proper content of an abstract of the disclosure.
A patent abstract is a concise statement of the technical disclosure of the patent and should include that which is new in the art to which the invention pertains. The abstract should not refer to purported merits or speculative applications of the invention and should not compare the invention with the prior art.
If the patent is of a basic nature, the entire technical disclosure may be new in the art, and the abstract should be directed to the entire disclosure. If the patent is in the nature of an improvement in an old apparatus, process, product, or composition, the abstract should include the technical disclosure of the improvement. The abstract should also mention by way of example any preferred modifications or alternatives.
Where applicable, the abstract should include the following: (1) if a machine or apparatus, its organization and operation; (2) if an article, its method of making; (3) if a chemical compound, its identity and use; (4) if a mixture, its ingredients; (5) if a process, the steps.
Extensive mechanical and design details of an apparatus should not be included in the abstract. The abstract should be in narrative form and generally limited to a single paragraph within the range of 50 to 150 words in length.
See MPEP § 608.01(b) for guidelines for the preparation of patent abstracts.
The abstract of the disclosure is objected to because it exceeds the range of 50 to 150 words in length. A corrected abstract of the disclosure is required and must be presented on a separate sheet, apart from any other text. See MPEP § 608.01(b).
The use of at least the terms Wi-Fi, Bluetooth, VMP, and NVIDIA, among others, which are trade names or marks used in commerce, has been noted in this application. The term should be accompanied by the generic terminology; furthermore the term should be capitalized wherever it appears or, where appropriate, include a proper symbol indicating use in commerce such as ™, SM , or ® following the term.
Although the use of trade names and marks used in commerce (i.e., trademarks, service marks, certification marks, and collective marks) are permissible in patent applications, the proprietary nature of the marks should be respected and every effort made to prevent their use in any manner which might adversely affect their validity as commercial marks.
Here while many terms are already correctly notated, due to the lengthy nature of the specification the Applicant’s cooperation is requested in correcting any errors of which applicant may become aware in the specification with regards to additional trade names or marks used in commerce.
Claim Rejections - 35 USC § 102
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 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 the appropriate paragraphs of 35 U.S.C. 102 that form the basis for the rejections under this section made in this Office action:
A person shall be entitled to a patent unless –
(a)(1) the claimed invention was patented, described in a printed publication, or in public use, on sale, or otherwise available to the public before the effective filing date of the claimed invention.
(a)(2) the claimed invention was described in a patent issued under section 151, or in an application for patent published or deemed published under section 122(b), in which the patent or application, as the case may be, names another inventor and was effectively filed before the effective filing date of the claimed invention.
Claim(s) 1-8, 12-18, and 22 is/are rejected under 35 U.S.C. 102(a)(1) and (a)(2) as being anticipated by Robinson (US-20220227379).
Regarding claim 1, Robinson teaches a system for navigating a host vehicle relative to a road segment, the system comprising (Paragraph [0015], "Accordingly, where an autonomous vehicle control system is being implemented, the vehicle control system takes the ultimate decision as to whether to perform the suggested actions. Alternatively, the alert may be an instruction or command to perform action.")
at least one processor comprising circuitry and a memory, wherein the memory includes instructions that when executed by the circuitry cause the at least one processor to (Paragraph [0238], "FIG. 9 shows a computing system for performing the methods described herein. The system 500 comprises a controller 510, memory 520 and an interface 530. The controller is configured to perform the methods described herein based on executable code stored in the memory 520.")
receive a captured image acquired by a camera onboard the host vehicle (Paragraph [0081], "The systems described herein are configured to sit between the sensors (e.g. a camera or LiDAR) and a machine learning system (such as a control system for an automated vehicle).") (Paragraph [0089], "The first 10 and second 20 sensor nodes are implemented in processors connected directly to a corresponding sensor. Accordingly, the first sensor node 10 receives first sensor data S.sub.1 from a first sensor and the second sensor node 20 receives second sensor data S.sub.2 from a second sensor,” here the system uses sensors to capture data, those sensors can include a camera or Lidar for capturing image data)
generate a representation in embedding space of at least a portion of the captured image (Paragraph [0112], "Each sensor node 120 receives at least one corresponding sensor input 110; however, multiple sensor inputs may be received by a single sensor node and combined in a manner similar to that described with regard to the fusion node 30 of FIG. 2 (embedding the sensor inputs into a single latent space). An example of this is shown in FIG. 2 at node N.sub.n-1.sup.1. In this case, there is no need to independently encode the sensor inputs before combining them at the sensor node, but instead the sensor inputs can be mapped directly onto the embedding space.") (Paragraph [0107], "In light of the above, data fusion can be obtained through the mapping of at least two representations of separate sensor data (in this case, the encoded sensor data E.sub.1, E.sub.2) into a combined representation C.sub.1 in a corresponding latent space,” here the system receives sensor data and combines that data and maps the representation into an embedding space)
determine whether the representation in embedding space of the at least a portion of the captured image falls outside of a predetermined embedding space region (Paragraph [0211-0212], "The threshold may be predefined and may be either constant or be adapted based on system performance (e.g. to output a set percentage or proportion of events as edge cases). If the prediction error is greater than the threshold, then the event is deemed to be an edge case and information relating to the edge case is output 412," here the system is applying a threshold to the representation and if the threshold is exceeded the representation is determine to fall outside the predetermined region) (Paragraph [0228], “For instance, in response to the prediction error of the system exceeding a threshold, the system (the neural network 420) may output an alert to the autonomous vehicle control system 324. This alert may simply be an indication that an edge case has been detected, or may include additional information, such as the nature of the edge case and/or features of the environment that may have caused the edge case. For instance, where the neural network 420 is making multiple predictions, the neural network 420 may identify a specific prediction and an associated feature that caused the prediction error to exceed the threshold.”)
wherein the predetermined embedding space region is defined as a non-anomalous embedding space region (Paragraph [0181], "An edge case is indicative of a situation in which a driver (or other type of vehicle controller) or a vehicle control system (such as an autonomous vehicle control system) might have difficulties. By alerting a vehicle control system of the presence of an edge case, the vehicle control system can be put on alert and can use this information to decide to take remedial action to mitigate any risk," here the system is defining a normal region and edge cases that fall outside the normal region)
determine a navigational action for the host vehicle based on a determination that the representation in embedding space of the at least a portion of the captured image falls outside of the predetermined embedding space region (Paragraph [0181], "By alerting a vehicle control system of the presence of an edge case, the vehicle control system can be put on alert and can use this information to decide to take remedial action to mitigate any risk. Remedial action may include priming brakes or steering for emergency use or actively issuing driving controls, such as braking and steering, to avoid danger.")
and cause at least one system associated with the host vehicle to implement the navigational action (Paragraph [0196], "This might include priming, activating, or adjusting the settings for various vehicle control subsystems. For instance, the edge case module 326 may prime a braking system (e.g. by activating an antilock braking system or increasing brake sensitivity) to allow the driver to brake more effectively. Alternatively, or in addition, other subsystems may be adjusted or primed, including pre-emptively activating lights or indicators (such as brake lights, emergency indicators, turning indicators, etc.), adjusting (increasing or decreasing) driving light brightness, adjusting suspension (e.g. increasing or decreasing stiffness, adjusting balance, etc.), charging capacitors or changing sensitivity of the brake(s) or steering,").
Regarding claim 2, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the representation in embedding space of the at least a portion of the captured image is performed by a trained model (Paragraph [0090], "The first 10 and second 20 sensor nodes compress the sensor data through mapping the sensor data onto a corresponding latent space via a machine learning model such as a neural network.").
Regarding claim 3, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the trained model is a variational encoder (Paragraph [0097], "One or more of the autoencoders may be variational autoencoders (VARs). These encode data as a distribution (e.g. a Gaussian distribution represented by a mean and standard deviation). When decoded, the encoded distribution may be sampled to produce a latent vector that is then passed through the decoder to produce an output.")
Regarding claim 4, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the trained model is further configured to output an indicator of whether the representation in embedding space of the at least a portion of the captured image falls outside of the predetermined embedding space region, and wherein the determination of the navigational action for the host vehicle is based the output of the trained model (Paragraph [0005], "and, in response to the prediction error exceeding a threshold, outputting an alert indicating detection of an edge case") (Paragraph [0181], "An edge case is indicative of a situation in which a driver (or other type of vehicle controller) or a vehicle control system (such as an autonomous vehicle control system) might have difficulties. By alerting a vehicle control system of the presence of an edge case, the vehicle control system can be put on alert and can use this information to decide to take remedial action to mitigate any risk," here the system is outputting an alert/indicator to the autonomous vehicle system that the sensor data falls outside the embedding space region/indicates an edge case, this output is then used to determine a navigational action).
Regarding claim 5, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein generation of the representation in embedding space is performed by a trained model configured to map the at least a portion of the captured image to a probability distribution over latent variables associated with the embedding space (Paragraph [0090], "The first 10 and second 20 sensor nodes compress the sensor data through mapping the sensor data onto a corresponding latent space via a machine learning model such as a neural network.") (Paragraph [0097], "One or more of the autoencoders may be variational autoencoders (VARs). These encode data as a distribution (e.g. a Gaussian distribution represented by a mean and standard deviation). When decoded, the encoded distribution may be sampled to produce a latent vector that is then passed through the decoder to produce an output.") (Paragraph [0211-0212], "The threshold may be predefined and may be either constant or be adapted based on system performance (e.g. to output a set percentage or proportion of events as edge cases). If the prediction error is greater than the threshold, then the event is deemed to be an edge case and information relating to the edge case is output 412," here the system is mapping the sensor data using a machine learned model, this process is accomplished using encoders which encode data as a distribution).
Regarding claim 6, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the predetermined embedding space region corresponds to a predetermined sub-region of a probabilistic distribution (Paragraph [0097], "One or more of the autoencoders may be variational autoencoders (VARs). These encode data as a distribution (e.g. a Gaussian distribution represented by a mean and standard deviation). When decoded, the encoded distribution may be sampled to produce a latent vector that is then passed through the decoder to produce an output.") (Paragraph [0211-0212], "The threshold may be predefined and may be either constant or be adapted based on system performance (e.g. to output a set percentage or proportion of events as edge cases). If the prediction error is greater than the threshold, then the event is deemed to be an edge case and information relating to the edge case is output 412.").
Regarding claim 7, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the probabilistic distribution is a gaussian distribution (Paragraph [0097], "One or more of the autoencoders may be variational autoencoders (VARs). These encode data as a distribution (e.g. a Gaussian distribution represented by a mean and standard deviation). When decoded, the encoded distribution may be sampled to produce a latent vector that is then passed through the decoder to produce an output.").
Regarding claim 8, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the predetermined sub-region is defined by at least one user-selectable parameter value (Paragraph [0051], "The machine learning agent may be biased to select actions that focus on predefined features of interest (e.g. user defined features)").
Regarding claim 12, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the representation in embedding space includes at least one feature vector (Paragraph [0097], "When decoded, the encoded distribution may be sampled to produce a latent vector that is then passed through the decoder to produce an output").
Regarding claim 13, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the at least a portion of the captured image includes a representation of a road sign (Paragraph [0142], "whilst an example of a feature of importance might be a pedestrian, another vehicle or a stop-sign")
Regarding claim 14, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the at least a portion of the captured image includes a representation of a target vehicle (Paragraph [0142], "whilst an example of a feature of importance might be a pedestrian, another vehicle or a stop-sign")
Regarding claim 15, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the navigational action includes generating a visual or audible alert (Paragraph [0189], "This may include actions for autonomously driving the vehicle or for assisting the driver in driving the vehicle (for instance, alerting the driver to obstacles or adjusting responsiveness of various control subsystems, such as breaking, acceleration or steering in preparation for driver action)," here the system may generate an alert for a driver which would be visual or audible).
Regarding claim 16, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the navigational action includes changing a heading direction of the host vehicle (Paragraph [0228], "This can then be utilised by the autonomous vehicle control system 324 to take remedial action, for instance, brake or turn to avoid an object in the environment that has been identified as dangerous.").
Regarding claim 17, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the navigational action includes slowing the host vehicle (Paragraph [0228], "This can then be utilised by the autonomous vehicle control system 324 to take remedial action, for instance, brake or turn to avoid an object in the environment that has been identified as dangerous.")
Regarding claim 18, Robinson teaches the system as discussed above in claim 1, Robinson further teaches wherein the navigational action includes maintaining a speed and heading direction for the host vehicle (Paragraph [0230], “Any alerts or instructions can be biased towards anticipating driver actions (e.g. priming systems to more effectively operate in anticipation of specific driver actions, such as adjusting brake sensitivity in anticipation of the driver braking”) (Paragraph [0181], "Remedial action may include priming brakes or steering for emergency use or actively issuing driving controls, such as braking and steering, to avoid danger,” here the system can take any number of actions in response to a determined edge case including simply priming the brakes or steering system without actively issuing driving controls, therefore maintaining the speed and heading of the vehicle).
Regarding claim 22, Robinson teaches a method for navigating a host vehicle relative to a road segment, comprising: (Paragraph [0015], "Accordingly, where an autonomous vehicle control system is being implemented, the vehicle control system takes the ultimate decision as to whether to perform the suggested actions. Alternatively, the alert may be an instruction or command to perform action.")
receive a captured image acquired by a camera onboard the host vehicle (Paragraph [0081], "The systems described herein are configured to sit between the sensors (e.g. a camera or LiDAR) and a machine learning system (such as a control system for an automated vehicle).") (Paragraph [0089], "The first 10 and second 20 sensor nodes are implemented in processors connected directly to a corresponding sensor. Accordingly, the first sensor node 10 receives first sensor data S.sub.1 from a first sensor and the second sensor node 20 receives second sensor data S.sub.2 from a second sensor,” here the system uses sensors to capture data, those sensors can include a camera or Lidar for capturing image data)
generate a representation in embedding space of at least a portion of the captured image (Paragraph [0112], "Each sensor node 120 receives at least one corresponding sensor input 110; however, multiple sensor inputs may be received by a single sensor node and combined in a manner similar to that described with regard to the fusion node 30 of FIG. 2 (embedding the sensor inputs into a single latent space). An example of this is shown in FIG. 2 at node N.sub.n-1.sup.1. In this case, there is no need to independently encode the sensor inputs before combining them at the sensor node, but instead the sensor inputs can be mapped directly onto the embedding space.") (Paragraph [0107], "In light of the above, data fusion can be obtained through the mapping of at least two representations of separate sensor data (in this case, the encoded sensor data E.sub.1, E.sub.2) into a combined representation C.sub.1 in a corresponding latent space,” here the system receives sensor data and combines that data and maps the representation into an embedding space)
determine whether the representation in embedding space of the at least a portion of the captured image falls outside of a predetermined embedding space region (Paragraph [0211-0212], "The threshold may be predefined and may be either constant or be adapted based on system performance (e.g. to output a set percentage or proportion of events as edge cases). If the prediction error is greater than the threshold, then the event is deemed to be an edge case and information relating to the edge case is output 412," here the system is applying a threshold to the representation and if the threshold is exceeded the representation is determine to fall outside the predetermined region) (Paragraph [0228], “For instance, in response to the prediction error of the system exceeding a threshold, the system (the neural network 420) may output an alert to the autonomous vehicle control system 324. This alert may simply be an indication that an edge case has been detected, or may include additional information, such as the nature of the edge case and/or features of the environment that may have caused the edge case. For instance, where the neural network 420 is making multiple predictions, the neural network 420 may identify a specific prediction and an associated feature that caused the prediction error to exceed the threshold.”)
wherein the predetermined embedding space region is defined as a non-anomalous embedding space region (Paragraph [0181], "An edge case is indicative of a situation in which a driver (or other type of vehicle controller) or a vehicle control system (such as an autonomous vehicle control system) might have difficulties. By alerting a vehicle control system of the presence of an edge case, the vehicle control system can be put on alert and can use this information to decide to take remedial action to mitigate any risk," here the system is defining a normal region and edge cases that fall outside the normal region)
determine a navigational action for the host vehicle based on a determination that the representation in embedding space of the at least a portion of the captured image falls outside of the predetermined embedding space region (Paragraph [0181], "By alerting a vehicle control system of the presence of an edge case, the vehicle control system can be put on alert and can use this information to decide to take remedial action to mitigate any risk. Remedial action may include priming brakes or steering for emergency use or actively issuing driving controls, such as braking and steering, to avoid danger.")
and cause at least one system associated with the host vehicle to implement the navigational action (Paragraph [0196], "This might include priming, activating, or adjusting the settings for various vehicle control subsystems. For instance, the edge case module 326 may prime a braking system (e.g. by activating an antilock braking system or increasing brake sensitivity) to allow the driver to brake more effectively. Alternatively, or in addition, other subsystems may be adjusted or primed, including pre-emptively activating lights or indicators (such as brake lights, emergency indicators, turning indicators, etc.), adjusting (increasing or decreasing) driving light brightness, adjusting suspension (e.g. increasing or decreasing stiffness, adjusting balance, etc.), charging capacitors or changing sensitivity of the brake(s) or steering,").
Claim Rejections - 35 USC § 103
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.
Claim 9 is/are rejected under 35 U.S.C. 103 as being unpatentable over Robinson (US-20220227379) in view of Wilson (US-20240419724)
Regarding claim 9, Robinson teaches the system as discussed above in claim 1, Robinson further teaches a percentage value associated with the probabilistic distribution (Paragraph [0211], “The method then determines whether the prediction error is greater than a threshold 410. The threshold may be predefined and may be either constant or be adapted based on system performance (e.g. to output a set percentage or proportion of events as edge cases).”).
However Robinson does not explicitly teach wherein the at least one user selectable parameter value includes a percentage value associated with the probabilistic distribution.
Wilson teaches systems and methods are described herein to manage and search data generated during operation of a vehicle such as camera data including
wherein the at least one user selectable parameter value includes a percentage value associated with the probabilistic distribution (Paragraph [0112], “Additionally, or alternatively, the network service provider can compare the cosine similarities to a similarity threshold. In some embodiments, the similarity threshold can be a threshold that is set (e.g., by a party operating a computing device to generate queries as described herein). In these examples, where the cosine similarity satisfies the similarity threshold, the network service provider can select the predetermined embeddings,” here the system is specifying that a user can adjust similarity thresholds for the embedded space, while Wilson is not explicitly using the percentage language, Robinson teaches percentage based thresholds for the probabilistic distribution, and the method of selectable parameter values of Wilson can reasonably be combined with the percentage value of Robinson).
Robinson and Wilson are analogous art as they are both generally related to systems and methods for processing sensor data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to include wherein the at least one user selectable parameter value includes a percentage value associated with the probabilistic distribution of Wilson in the system and method navigating a vehicle using representations of captured image data of Robinson with a reasonable expectation of success in order to improve the exchange of vehicle data and provide selected customization of data in an efficient manner (Paragraph [0038], “Further, to facilitate the exchange of vehicle data and to provide for selected customization of data transmissions in an efficient manner, one or more aspects of the present application further correspond to example data structure/organization in which vehicle information is transmitted in accordance with example communication protocols.”).
Claim 10-11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Robinson (US-20220227379) in view of Ferroni (US-20240257536).
Regarding claim 10, Robinson teaches the system as discussed above in claim 1, however Robinson does not explicitly teach wherein the predetermined embedding space region is defined by an embedding space distance relative to an embedding space reference.
Ferroni teaches a roadway dataset includes an image logged by an autonomous vehicle (AV) in a roadway, generating based on a text-image model, an embedding dataset including
wherein the predetermined embedding space region is defined by an embedding space distance relative to an embedding space reference (Paragraph [0144], “For example, remote computing device 120 calculates the distance between a query input text embedding and each of the image embeddings to create a distance distribution (e.g., distance function, etc.). In such an example, images that closely resemble the query will reside a short distance from the input query text in the high dimensional space, while images that are very different may have a large distance between them.”).
Robinson and Ferroni are analogous art as they are both generally related to systems and methods for processing sensor data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to include wherein the predetermined embedding space region is defined by an embedding space distance relative to an embedding space reference of Ferroni in the system and method navigating a vehicle using representations of captured image data of Robinson with a reasonable expectation of success in order to more efficiency and accurately identify image data to determine roadway features (Paragraph [0005], “The amount of time and resources for label review and comparison of onboard data (e.g., raw images, high quality images, etc.) may also restrain such labeling. Most importantly, given the significant amounts of unlabeled data to determine roadway features, the significant amounts of ongoing collection of data, and the significant improvements in autonomous sensor data, techniques are needed to more accurately, efficiently, and expeditiously search, and identify image data.”).
Regarding claim 11, the combination of Robinson and Ferrano teaches the system as discussed above in claim 1, however Robinson does not explicitly teach wherein the embedding space reference corresponds to an embedding space origin.
Ferroni further teaches wherein the embedding space reference corresponds to an embedding space origin (Paragraph [0144-0145], “images that closely resemble the query will reside a short distance from the input query text in the high dimensional space, while images that are very different may have a large distance between them. A distance distribution is a measure for the difference (or distinction) between two different objects from the same dataset (e.g., a distance between each image embedding and an input query text, a distance to a parametric description of the image in a high probability field, and/or the like). The larger the distance, the more different the two objects are. A similarity function may be used to measure the resemblance between two different objects from the same data set. The larger the similarity, the more alike the two objects are. For instance, given two points in Cartesian coordinates, the distance between them can be measured using the Euclidean distance, while the similarity can be measured using the dot-product operation,” here the system is determining a distance that is defined by an initial query, which serves as the origin).
Robinson and Ferroni are analogous art as they are both generally related to systems and methods for processing sensor data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to include wherein the embedding space reference corresponds to an embedding space origin of Ferroni in the system and method navigating a vehicle using representations of captured image data of Robinson with a reasonable expectation of success in order to more efficiency and accurately identify image data to determine roadway features (Paragraph [0005], “The amount of time and resources for label review and comparison of onboard data (e.g., raw images, high quality images, etc.) may also restrain such labeling. Most importantly, given the significant amounts of unlabeled data to determine roadway features, the significant amounts of ongoing collection of data, and the significant improvements in autonomous sensor data, techniques are needed to more accurately, efficiently, and expeditiously search, and identify image data.”).
Claim 19 and 21 is/are rejected under 35 U.S.C. 103 as being unpatentable over Robinson (US-20220227379) in view of Shambik (US-20220027642).
Regarding claim 19, the combination of Robinson and Ferrano teaches the system as discussed above in claim 1, Robinson further teaches wherein the determined navigational action includes maintained a speed and heading for the host vehicle (Paragraph [0230], “Any alerts or instructions can be biased towards anticipating driver actions (e.g. priming systems to more effectively operate in anticipation of specific driver actions, such as adjusting brake sensitivity in anticipation of the driver braking”) (Paragraph [0181], "Remedial action may include priming brakes or steering for emergency use or actively issuing driving controls, such as braking and steering, to avoid danger,” here the system can take any number of actions in response to a determined edge case including simply priming the brakes or steering system without actively issuing driving controls, therefore maintaining the speed and heading of the vehicle).
However Robinson does not explicitly teach wherein the at least a portion of the captured image includes a representation of a first target vehicle being carried as cargo by a second target vehicle, wherein the first target vehicle and the second target vehicle are facing the opposite direction, and wherein the determined navigational action includes maintained a speed and heading for the host vehicle.
Shambik teaches systems and methods for vehicle navigation using captured image data from a camera on a host vehicle including
wherein the at least a portion of the captured image includes a representation of a first target vehicle being carried as cargo by a second target vehicle, wherein the first target vehicle and the second target vehicle are facing the opposite direction (See Figures 29 and 30B showing vehicles being carried as cargo) (Paragraph [0008], “The processor may be programmed to receive, from a camera of the host vehicle, at least one captured image representative of an environment of the host vehicle; and analyze two or more pixels of the at least one captured image to determine whether the two or more pixels represent at least a portion of a first target vehicle and at least a portion of a second target vehicle. The processor may be programmed to determine that the second target vehicle is carried or towed by the first target vehicle.”) (Paragraph [0369], “Using the techniques described above, each of the pixels in the image may be analyzed to identify a boundary of the vehicles. For example, pixels associated with carrier vehicle 2910 may be analyzed to determine a boundary of carrier vehicle 2910, as described above. The system may also analyze pixels associated with vehicles 2920 and 2930. Based on the analysis of the pixels, the system may determine that vehicles 2920 and 2930 are not target vehicles and thus should not be associated with a bounding box. This analysis may be performed in a variety of ways. For example, the trained neural network described above may be trained using a set of training data including images of carried vehicles. Pixels associated with the carried vehicles in the image may be designated as carried vehicles or non-target vehicles. Accordingly, the trained neural network model may determine based on pixels in image 2900 that vehicles 2920 and 2930 are being transported on carrier vehicle 2910,” here while Shambik is not explicitly reciting a towed vehicle facing rearward, it would be obvious to a person of ordinary skill in the art that the methodology of determining a vehicle is acting as cargo instead of an additional cargo vehicle to reasonably be applied to vehicles in other orientations).
Robinson and Shambik are analogous art as they are both generally related to systems and methods for processing sensor data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to include wherein the at least a portion of the captured image includes a representation of a first target vehicle being carried as cargo by a second target vehicle, wherein the first target vehicle and the second target vehicle are facing the opposite direction of Shambik in the system and method navigating a vehicle using representations of captured image data of Robinson with a reasonable expectation of success in order to accurately determine the status of other road users and improve the ability of the system to determine appropriate navigational actions (Paragraph [0365], “The improved accuracy of the orientation of the bounding box may improve the ability of the system to determine appropriate navigation action responses.”).
Regarding claim 21, the combination of Robinson and Ferrano teaches the system as discussed above in claim 1, Robinson further teaches wherein the determined navigational action includes changing a heading direction of the host vehicle or slowing of the host vehicle (Paragraph [0228], "This can then be utilised by the autonomous vehicle control system 324 to take remedial action, for instance, brake or turn to avoid an object in the environment that has been identified as dangerous.").
However Robinson does not explicitly teach wherein the at least a portion of the captured image includes a representation of cargo attached to a top of a target vehicle.
Shambik teaches systems and methods for vehicle navigation using captured image data from a camera on a host vehicle including
wherein the at least a portion of the captured image includes a representation of cargo attached to a top of a target vehicle, and wherein the determined navigational action includes changing a heading direction of the host vehicle or slowing of the host vehicle (See Figures 29 and 30B showing vehicles being carried as cargo, specifically figure 30B shows a representation of cargo on top of a vehicle bed) (Paragraph [0008], “The processor may be programmed to receive, from a camera of the host vehicle, at least one captured image representative of an environment of the host vehicle; and analyze two or more pixels of the at least one captured image to determine whether the two or more pixels represent at least a portion of a first target vehicle and at least a portion of a second target vehicle. The processor may be programmed to determine that the second target vehicle is carried or towed by the first target vehicle.”) (Paragraph [0369], “Using the techniques described above, each of the pixels in the image may be analyzed to identify a boundary of the vehicles. For example, pixels associated with carrier vehicle 2910 may be analyzed to determine a boundary of carrier vehicle 2910, as described above. The system may also analyze pixels associated with vehicles 2920 and 2930. Based on the analysis of the pixels, the system may determine that vehicles 2920 and 2930 are not target vehicles and thus should not be associated with a bounding box. This analysis may be performed in a variety of ways. For example, the trained neural network described above may be trained using a set of training data including images of carried vehicles. Pixels associated with the carried vehicles in the image may be designated as carried vehicles or non-target vehicles. Accordingly, the trained neural network model may determine based on pixels in image 2900 that vehicles 2920 and 2930 are being transported on carrier vehicle 2910,”).
Robinson and Shambik are analogous art as they are both generally related to systems and methods for processing sensor data.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the instant application to include wherein the at least a portion of the captured image includes a representation of cargo attached to a top of a target vehicle, and wherein the determined navigational action includes changing a heading direction of the host vehicle or slowing of the host vehicle of Shambik in the system and method navigating a vehicle using representations of captured image data of Robinson with a reasonable expectation of success in order to accurately determine the status of other road users and improve the ability of the system to determine appropriate navigational actions (Paragraph [0365], “The improved accuracy of the orientation of the bounding box may improve the ability of the system to determine appropriate navigation action responses.”).
Allowable Subject Matter
Claims 20 is objected to as being dependent upon a rejected base claim, but would be allowable if rewritten in independent form including all of the limitations of the base claim and any intervening claims.
The following is an examiners statement for reasons for the indication of allowable subject matter:
Prior art fails to disclose or render obvious claims 20 disclosing systems and methods for specifically recognizing a captured image that includes a person standing on top of a target vehicle. Specifically the closest prior art Robinson, fail to teach “wherein the at least a portion of the captured image includes a representation of a pedestrian standing on top of a target vehicle, and wherein the determined navigational action includes changing a heading and direction of the host vehicle or slowing of the host vehicle” as disclosed in claims 20.
The prior art made of record below fails to disclose “wherein the at least a portion of the captured image includes a representation of a pedestrian standing on top of a target vehicle, and wherein the determined navigational action includes changing a heading and direction of the host vehicle or slowing of the host vehicle”.
Some of the similar prior art that does not disclose the applicants invention:
Omari (US-12617390) teaches methods and systems for semantic behavior filtering for prediction improvement including recognizing images of pedestrians near a roadway and determining predicted actions. However Omari does not explicitly teach recognizing an image including a pedestrian standing on top of a vehicle.
Jiang (US-20240025445) teaches a system perceives an environment of an autonomous driving vehicle (ADV) based on a plurality of sensors and map data including detecting pedestrians and determining anomalous behaviors. However Jiang does not explicitly teach recognizing an image including a pedestrian standing on top of a vehicle.
Raichelgauz (US-20220041184) teaches a method for detecting obstacles, the method may include receiving, from a plurality of vehicles, and by an I/O module of a computerized system, visual information acquired during executions of vehicle maneuvers including specific events involving pedestrians such as groups near a roadway or a bus letting off passengers. However Raichelgauz does not explicitly teach recognizing an image including a pedestrian standing on top of a vehicle.
Therefore Robinson nor any of the other prior art of record teaches or suggests the combination of limitations in claims 20. The combination of claimed limitations are novel and found to be allowable over the prior art.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to CHRISTOPHER FEES whose telephone number is (303)297-4343. The examiner can normally be reached Monday-Thursday 7:30 - 5:30 MT.
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, Aniss Chad can be reached at (571) 270-3832. 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.
/CHRISTOPHER GEORGE FEES/Primary Examiner, Art Unit 3662
Prosecution Insights