DETAILED ACTION
Status of Claims
The status of the claims is as follows:
(a) Claims 1-3, 5-14, and 16-23 remain pending.
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 .
Continued Examination Under 37 CFR 1.114
A request for Continued Examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after a Final Rejection. Since this application is eligible for Continued Examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office Action has been withdrawn pursuant to 37 CFR 1.114. The Applicant's submission filed on 02/27/2026 has been entered.
Response to Amendments
The Examiner accepts the amendments received on 11/03/2025.
Response to Arguments
Applicant argues that the rejection of claim 1 fails to consider all limitations of the claim, particularly the limitation “in response to the comparison being indicative of the malfunction,” and therefore fails to establish a prima facie case of obviousness.
The Examiner respectfully disagrees. As set forth in the rejection below, Broggi describes comparing first object data from a first sensor with second object data from a second sensor. Zhu further describes cross-validating information generated by different vehicle sensors and determining, based on deviations between the sensor information, that a sensor is experiencing a problem or operational failure (Zhu, Col. 18 Lines 22-44 and Col. 18 Line 49 to Col. 20 Line 17 and Claim 9). Thus, the Examiner finds Zhu teaches that the comparison and resulting non-correspondence are indicative of a malfunction of one of the sensors.
Coelingh further describes stopping an autonomous vehicle when sensor performance has degraded such that continued autonomous operation is inappropriate (Coelingh, Paragraphs 0005-0006). Therefore, when the teachings of the cited references are considered together, the Examiner continues to find that the vehicle is stopped in response to the sensor comparison indicating a malfunction and the sensor data being determined not to correspond. The rejection of claim 1 under 35 U.S.C. 103 is therefore maintained.
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 1-3, 5-7, and 23 are rejected under 35 U.S.C. 103 as being unpatentable over Broggi et al. U.S. P.G. Publication 2012/0143430A1 (hereinafter, Broggi), in view of Zhu et al. U.S. Patent 9,555,740 (hereinafter, Zhu), in further view of Coelingh et al. U.S. P.G. Publication 2015/0266490A1 (hereinafter, Coelingh).
Regarding Claim 1, Broggi describes a system comprising:
-a central processing device configured to receive object data provided by sensors of a vehicle (a processor receives and processes data from lidar and vision sensors of an autonomous vehicle, Broggi, Paragraphs 0029 and 0054 and Figure 1); and
-memory storing instructions configured to instruct the central processing device (software instructions stored in memory for operation of the processing system, Broggi, Paragraph 0054 and Figure 9) to:
-receive first object data based on a first object detection by a first sensor of the vehicle (receiving object data from a first lidar sensor, Broggi, Paragraphs 0038 and 0054-0055 and Figures 2-3);
-receive second object data based on a second object detection by a second sensor of the vehicle (receiving object data from another sensor including a camera system, Broggi, Paragraphs 0038, 0046, and 0054-0055 and Figures 2-3);
-make a comparison of the first object data to the second object data, the comparison comprising performing a correlation of the first object data to the second object data (comparing lidar object data with camera object data, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2);
-determine, based on the comparison of the first object data to the second object data (comparing the object data from the lidar and camera systems to determine whether the data correspond, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2); …
Broggi does not specifically describe the system to include that the first object data does not correspond to the second object data such that the comparison is indicative of a malfunction of one of the first sensor or the second sensor.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes cross-validating object information obtained from different vehicle sensors and determining deviations between the information (Zhu, Col. 18 Lines 22-44 and Col. 18 Line 49 to Col. 20 Line 17). Zhu further describes determining from the deviations that a sensor being cross-validated is experiencing a problem or operational failure (Zhu, Col. 19 Lines 1-32 and Claim 9).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include that the first object data does not correspond to the second object data such that the comparison is indicative of a malfunction of one of the first sensor or the second sensor.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because cross-validating sensor information provides a mechanism for readily identifying potential failures or problems in vehicle sensors (Zhu, Col. 19 Lines 43-62).
Broggi, as modified, does not specifically describe the system to include in response to the comparison being indicative of the malfunction and determining that the first object data does not correspond to the second object data, automatically stop the vehicle.
Coelingh discloses, teaches, or at least suggests the missing limitation. Coelingh describes monitoring vehicle sensor performance and, when the sensor performance has degraded such that continued autonomous operation is inappropriate, stopping the vehicle (Coelingh, Paragraphs 0005-0006).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include in response to the comparison being indicative of the malfunction and determining that the first object data does not correspond to the second object data, automatically stop the vehicle.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because stopping the vehicle when sensor performance is insufficient prevents continued autonomous operation using unreliable sensor information (Coelingh, Paragraphs 0005-0006).
Regarding Claim 2, Broggi, as modified, describes the system of claim 1.
Broggi does not specifically describe the system to include in response to determining that the first object data does not correspond to the second object data, change a configuration of at least one of the first sensor or the second sensor and perform a diagnostic test of at least one of the first sensor or the second sensor; wherein the configuration of the first sensor or the second sensor is changed based on the diagnostic test.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes cross-validating information obtained from different sensors to determine whether a sensor is operating properly and determining from deviations between the sensor information whether the sensor is experiencing a problem (Zhu, Col. 18 Lines 22-44 and Col. 18 Line 49 to Col. 20 Line 17). Zhu further describes taking an action based on the determined sensor failure, including changing whether the sensor information is relied upon for autonomous vehicle operation (Zhu, Col. 19 Lines 43-62 and Claim 9).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include in response to determining that the first object data does not correspond to the second object data, change a configuration of at least one of the first sensor or the second sensor and perform a diagnostic test of at least one of the first sensor or the second sensor; wherein the configuration of the first sensor or the second sensor is changed based on the diagnostic test.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because cross-validating sensor information provides a mechanism for determining whether a sensor is properly operating and taking corrective action when a sensor problem is identified (Zhu, Col. 19 Lines 43-62).
Regarding Claim 3, Broggi, as modified, describes the system of claim 2.
Broggi does not specifically describe the system to include determine, based on the diagnostic test, that a malfunction exists in at least one of the first sensor or the second sensor.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes cross-validating sensor information and determining, based on deviations identified by the cross-validation, that the sensor being evaluated is experiencing a problem or operational failure (Zhu, Col. 18 Line 49 to Col. 20 Line 17 and Claim 9).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include determine, based on the diagnostic test, that a malfunction exists in at least one of the first sensor or the second sensor.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because the cross-validation and associated failure thresholds are used to identify potential failures or problems in a vehicle sensor (Zhu, Col. 19 Lines 43-62).
Regarding Claim 5, Broggi, as modified, describes the system of claim 1, wherein the correlation of the first object data to the second object data provides a result (comparing lidar object data with camera object data to determine whether the data correspond, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2).
Broggi does not specifically describe the system to include determine an expected correlation; and compare the result to the expected correlation.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes determining deviation values between information generated from different sensors and comparing the deviation values with predetermined deviation thresholds representing an acceptable difference between the sensor information (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include determine an expected correlation; and compare the result to the expected correlation.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because comparison against predetermined deviation thresholds permits the system to determine whether different sensors are producing sufficiently corresponding information (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
Regarding Claim 6, Broggi, as modified, describes the system of claim 5.
Broggi does not specifically describe the system to include determine, based on at least one of the first object data or the second object data, a type of object; and the expected correlation is determined based on the type of object.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes applying object labels and classifications to objects detected using different sensors and comparing corresponding object classifications (Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44). Zhu further describes selecting thresholds used in evaluating correspondence based on the type of information being compared (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include determine, based on at least one of the first object data or the second object data, a type of object; and the expected correlation is determined based on the type of object.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because selecting comparison criteria appropriate for the information being compared permits more accurate cross-validation of detected objects (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
Regarding Claim 7, Broggi, as modified, describes the system of claim 1.
Broggi does not specifically describe the system to include wherein determining whether the first object data corresponds to the second object data comprises comparing a number of times that the first object data matches the second object data to a threshold.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes maintaining a failure count associated with repeated sensor cross-validation results and comparing the count to predetermined thresholds to determine whether a sensor problem exists (Zhu, Col. 19 Lines 33-62).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include wherein determining whether the first object data corresponds to the second object data comprises comparing a number of times that the first object data matches the second object data to a threshold.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because tracking repeated cross-validation results against a threshold enables identification of intermittent sensor problems that may not be apparent from a single comparison (Zhu, Col. 19 Lines 43-62).
Regarding Claim 23, Broggi, as modified, describes the system of claim 1.
Broggi does not specifically describe the system to include wherein a determination that the first object data does not correspond to the second object data comprises a determination that a component of the vehicle is unsafe to operate, and further wherein the instructions configured to instruct the central processing device to automatically stop the vehicle further comprise instructions to automatically stop the vehicle based on the determination that the component of the vehicle is unsafe to operate.
Zhu discloses, teaches, or at least suggests determining from discrepancies between information generated by different sensors that a vehicle sensor is experiencing a problem or operational failure (Zhu, Col. 18 Line 49 to Col. 20 Line 17 and Claim 9).
Coelingh further discloses, teaches, or at least suggests stopping an autonomous vehicle when sensor performance has degraded such that continued autonomous operation should not continue (Coelingh, Paragraphs 0005-0006).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include wherein a determination that the first object data does not correspond to the second object data comprises a determination that a component of the vehicle is unsafe to operate, and further wherein the instructions configured to instruct the central processing device to automatically stop the vehicle further comprise instructions to automatically stop the vehicle based on the determination that the component of the vehicle is unsafe to operate.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because stopping the vehicle when sensor performance is insufficient prevents continued autonomous operation using unreliable sensor information (Coelingh, Paragraphs 0005-0006).
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Broggi in view of Zhu, in further view of Coelingh, in further view of Huggins-Luthman U.S. P.G. Publication 2016/0078305A1 (hereinafter, Huggins-Luthman).
Regarding Claim 8, Broggi, as modified, describes the system of claim 7.
Broggi, as modified, does not specifically describe the system to include wherein the threshold varies based on a time of day.
Huggins-Luthman discloses, teaches, or at least suggests the missing limitation. Huggins-Luthman describes changing sensor sensitivity used for detecting and evaluating objects based on whether operation occurs during daytime or nighttime (Huggins-Luthman, Paragraphs 0103, 0121-0123, and 0133-0155).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include wherein the threshold varies based on a time of day.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because adjusting detection thresholds based on daytime or nighttime conditions improves object-detection accuracy under different lighting conditions (Huggins-Luthman, Paragraphs 0009, 0122, and 0133-0155).
Claims 9-14 and 16 are rejected under 35 U.S.C. 103 as being unpatentable over Broggi, in view of Zhu, in further view of Zheng et al. U.S. P.G. Publication 2018/0348784A1 (hereinafter, Zheng), in further view of Fushimi et al. U.S. P.G. Publication 2020/0039531A1 (hereinafter, Fushimi).
Regarding Claim 9, Broggi describes a vehicle comprising:
-a first sensor configured to generate first data indicative of a first object type (a lidar sensor generates first object data corresponding to detected objects, Broggi, Paragraphs 0038 and 0054 and Figures 2-3); …
-a second sensor configured to generate second data indicative of a second object type (a camera system generates second object data corresponding to detected objects, Broggi, Paragraphs 0038 and 0054 and Figures 2-3); … and
-a central processing device configured to:
-receive the first data indicative of the first object type from the first sensor;
-receive the second data indicative of the second object type from the second sensor (a processor receives object data generated by the lidar and vision systems, Broggi, Paragraphs 0029 and 0054 and Figure 1);
-make a comparison between the first data indicative of the first object type and the second data indicative of the second object type (comparing object data generated by the lidar system with object data generated by the camera system, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2); …
Broggi does not specifically describe the vehicle to include determine, based on the comparison of the first data and the second data, whether the first object type is a same object type as the second object type.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes applying a first object label to an object detected using a first sensor and a second object label to the object detected using a second sensor and comparing the labels, including comparing object classifications, to determine whether the sensor detections correspond (Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include determine, based on the comparison of the first data and the second data, whether the first object type is a same object type as the second object type.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because comparing classifications generated from different sensors provides a mechanism for determining whether the sensors accurately detected and classified the same object (Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44).
Broggi, as modified, does not specifically describe the vehicle to include wherein the first sensor uses a first artificial neural network to generate the first data indicative of the first object type based on first raw data collected by the first sensor; wherein the second sensor uses a second artificial neural network to generate the second data indicative of the second object type based on second raw data collected by the second sensor; and in response to determining that the first object type is not the same object type as the second object type, change a configuration of at least one of the first sensor or the second sensor by updating at least one of the first artificial neural network used by the first sensor or the second artificial neural network used by the second sensor.
Zheng discloses, teaches, or at least suggests the missing limitations. Zheng describes object-detection models processing sensor data to detect objects and object features, wherein the models may be deep-learning neural networks (Zheng, Paragraphs 0078 and 0145). Zheng further describes cross-modality validation in which an object detection generated from passive sensor data is compared with information obtained from a different sensor modality, including lidar data (Zheng, Paragraphs 0093 and 0096-0101). When the detection results obtained from different sensor modalities differ, Zheng describes that the discrepancy indicates that the models need to be adjusted and uses the discrepancy to locally adapt the object-detection model (Zheng, Paragraphs 0117 and 0119). Zheng further describes updating structural or functional parameters of a deep neural network model (Zheng, Paragraph 0145).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include wherein the first sensor uses a first artificial neural network to generate the first data indicative of the first object type based on first raw data collected by the first sensor; wherein the second sensor uses a second artificial neural network to generate the second data indicative of the second object type based on second raw data collected by the second sensor; and in response to determining that the first object type is not the same object type as the second object type, change a configuration of at least one of the first sensor or the second sensor by updating at least one of the first artificial neural network used by the first sensor or the second artificial neural network used by the second sensor.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because adapting an object-detection model when detections obtained from different sensor modalities disagree permits the model to learn from incorrect detection results and improve future detection performance (Zheng, Paragraphs 0117 and 0119).
Broggi, as modified, does not specifically describe the vehicle to include wherein the first sensor comprises a first memory configured to store third data associated with the first artificial neural network; wherein the second sensor comprises a second memory configured to store fourth data associated with the second artificial neural network, and wherein the first memory is different from the second memory.
Fushimi discloses, teaches, or at least suggests the missing limitations. Fushimi describes a first sensor module having a first processor and a first memory, wherein the first memory stores an artificial-intelligence program that may comprise a learned neural network (Fushimi, Paragraph 0156 and Figures 5-6A). Fushimi separately describes a second sensor module having a second processor and a second memory, wherein the second memory stores an artificial-intelligence program that may comprise a learned neural network (Fushimi, Paragraphs 0159-0161 and Figures 5-6B). Fushimi further expressly distinguishes the first processor and first memory supported by the first sensor module from the second processor and second memory supported by the second sensor module (Fushimi, Paragraph 0187).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include wherein the first sensor comprises a first memory configured to store third data associated with the first artificial neural network; wherein the second sensor comprises a second memory configured to store fourth data associated with the second artificial neural network, and wherein the first memory is different from the second memory.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because distributing the processors and memories among separate sensor modules reduces the processing workload imposed on the vehicle control device (Fushimi, Paragraph 0187).
Regarding Claim 10, Broggi, as modified, describes the vehicle of claim 9, wherein making the comparison comprises comparing the first object type to the second object type (comparing object classifications generated from different vehicle sensors, Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44).
Regarding Claim 11, Broggi, as modified, describes the vehicle of claim 9, wherein the comparison comprises performing a correlation of the first data indicative of the first object type to the second data indicative of the second object type (comparing and cross-validating corresponding object information generated from different sensors, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2; Zhu, Col. 18 Lines 22-44).
Regarding Claim 12, Broggi, as modified, describes the vehicle of claim 11.
Broggi does not specifically describe the vehicle to include wherein the correlation is based on a type of object.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes applying object labels and classifications to detected objects and comparing the classifications generated from different sensors (Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include wherein the correlation is based on a type of object.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because comparing classifications generated from different sensors permits the system to determine whether the sensors detected and classified the same object (Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44).
Regarding Claim 13, Broggi, as modified, describes the vehicle of claim 9, wherein the first data indicative of the first object type comprises a first position of a first object detected by the first sensor, and the second data indicative of the second object type comprises a second position of a second object detected by the second sensor (object data generated from the lidar and camera systems include position information used to compare corresponding detected objects, Broggi, Paragraphs 0038, 0046, and 0054-0059).
Regarding Claim 14, Broggi, as modified, describes the vehicle of claim 9, wherein the central processing device is further configured to: determine a context of the vehicle based on data from at least one sensor other than the first sensor and the second sensor; wherein determining whether the first data indicative of the first object type corresponds to the second data indicative of the second object type is based in part on the context (sensor information is evaluated in connection with the autonomous vehicle path and path-planning information, Broggi, Paragraphs 0037, 0046, 0054-0059, 0062, and 0064).
Regarding Claim 16, Broggi, as modified, describes the vehicle of claim 9.
Broggi does not specifically describe the vehicle to include the determining comprises comparing a number of times that the first data indicative of the first object type matches the second data indicative of the second object type to a threshold; and the threshold is a predetermined percentage of a total number of comparisons.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes maintaining a failure count corresponding to repeated results of cross-validating sensor information and comparing the count against predetermined thresholds (Zhu, Col. 19 Lines 33-62).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include the determining comprises comparing a number of times that the first data indicative of the first object type matches the second data indicative of the second object type to a threshold; and the threshold is a predetermined percentage of a total number of comparisons.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because evaluating repeated sensor-comparison results against a threshold provides a mechanism for identifying recurring or intermittent sensor discrepancies (Zhu, Col. 19 Lines 43-62).
Claims 17-22 are rejected under 35 U.S.C. 103 as being unpatentable over Broggi, in view of Zhu, in further view of Coelingh, in further view of Kozak U.S. P.G. Publication 2017/0102700A1 (hereinafter, Kozak).
Regarding Claim 17, Broggi describes a vehicle comprising:
-a lidar sensor (lidar sensing system of an autonomous vehicle, Broggi, Paragraphs 0038 and 0054 and Figures 2-3);
-a camera (vision or camera sensing system of the autonomous vehicle, Broggi, Paragraphs 0038 and 0046 and Figures 2-3); and
-a central processing device configured to:
-receive first object data from the lidar sensor;
-receive second object data from the camera (a processor receives and processes object data generated by the lidar and camera systems, Broggi, Paragraphs 0029 and 0054-0055 and Figures 1-3);
-make a comparison of the first object data to the second object data (comparing lidar object data with camera object data, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2);
-determine, based on the comparison of the first object data to the second object data, whether the first object data corresponds to the second object data (comparing the lidar and camera object data to determine whether corresponding object information agrees, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2); …
Broggi does not specifically describe the vehicle to include in response to determining that the first object data does not correspond to the second object data, automatically stop the vehicle.
Zhu discloses, teaches, or at least suggests determining from differences between corresponding information generated from two sensors that a sensor is experiencing a problem or operational failure (Zhu, Col. 18 Line 49 to Col. 20 Line 17 and Claim 9).
Coelingh further discloses, teaches, or at least suggests stopping an autonomous vehicle when sensor performance has degraded (Coelingh, Paragraphs 0005-0006).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include in response to determining that the first object data does not correspond to the second object data, automatically stop the vehicle.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because stopping an autonomous vehicle when sensor performance is insufficient prevents continued operation using unreliable sensor information (Coelingh, Paragraphs 0005-0006).
Broggi, as modified, does not specifically describe the vehicle to include disable an autonomous mode of operation for the vehicle after the vehicle is stopped.
Kozak discloses, teaches, or at least suggests the missing limitation. Kozak describes operating a vehicle in an automatic mode while routing the vehicle to and stopping the vehicle at a standby location (Kozak, Paragraph 0057). Kozak further describes that after stopping the vehicle while in the automatic mode, the vehicle transitions to a manual mode (Kozak, Paragraph 0058 and Paragraph 0007).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include disable an autonomous mode of operation for the vehicle after the vehicle is stopped.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because maintaining automatic operation through the stopping operation and transitioning to manual operation after the vehicle is stopped permits the vehicle to complete the stopping maneuver before relinquishing autonomous control (Kozak, Paragraphs 0057-0058).
Regarding Claim 18, Broggi, as modified, describes the vehicle of claim 17.
Broggi does not specifically describe the vehicle to include wherein determining whether the first object data corresponds to the second object data comprises determining whether a statistical detection relationship is maintained between the first object data and the second object data.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes repeatedly cross-validating information generated by different sensors, maintaining failure counts associated with the comparison results, and comparing the counts with predetermined thresholds (Zhu, Col. 19 Lines 33-62).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include wherein determining whether the first object data corresponds to the second object data comprises determining whether a statistical detection relationship is maintained between the first object data and the second object data.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because repeated comparisons and failure-count thresholds enable identification of recurring or intermittent sensor problems (Zhu, Col. 19 Lines 43-62).
Regarding Claim 19, Broggi, as modified, describes the vehicle of claim 17.
Broggi does not specifically describe the vehicle to include wherein the central processing device is further configured to, in response to determining that the first object data does not correspond to the second object data, require a person to take over control of the vehicle.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes determining from sensor cross-validation that a sensor problem exists and, when a failure threshold is reached, requesting that a passenger take control of the autonomous vehicle (Zhu, Col. 19 Lines 33-62 and Claim 9).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include wherein the central processing device is further configured to, in response to determining that the first object data does not correspond to the second object data, require a person to take over control of the vehicle.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because requesting manual control when sensor cross-validation identifies a sufficiently significant sensor problem prevents continued reliance on unreliable autonomous sensing (Zhu, Col. 19 Lines 33-62).
Regarding Claim 20, Broggi, as modified, describes the vehicle of claim 17, wherein the central processing device is further configured to perform a correlation of the first object data to the second object data to provide a result (comparing lidar object data with camera object data to determine whether the data correspond, Broggi, Paragraphs 0038, 0046, and 0054-0059 and Figure 2); …
Broggi does not specifically describe the vehicle to include determine an expected correlation; and compare the result to the expected correlation.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes determining deviations between corresponding information produced by different sensors and comparing those deviations to predetermined thresholds defining an acceptable difference between the sensor information (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include determine an expected correlation; and compare the result to the expected correlation.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because comparing sensor deviations against predetermined acceptable thresholds provides a mechanism for determining whether the sensor information sufficiently corresponds (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
Regarding Claim 21, Broggi, as modified, describes the vehicle of claim 20.
Broggi does not specifically describe the vehicle to include wherein the central processing device is further configured to determine, based on at least one of the first object data or the second object data, a type of object; and the expected correlation is determined based on the determined type of object.
Zhu discloses, teaches, or at least suggests the missing limitation. Zhu describes applying object labels and classifications to objects detected by different sensors and comparing the classifications generated by the sensors (Zhu, Col. 17 Lines 9-22 and Col. 18 Lines 22-44). Zhu further describes selecting comparison thresholds based on the information being compared (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
As a result, a person of ordinary skill in the art would have found it obvious to modify the vehicle to include wherein the central processing device is further configured to determine, based on at least one of the first object data or the second object data, a type of object; and the expected correlation is determined based on the determined type of object.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because selecting comparison criteria appropriate for the information being compared improves the accuracy of sensor cross-validation (Zhu, Col. 18 Line 49 to Col. 19 Line 32).
Regarding Claim 22, Broggi, as modified, describes the system of claim 1.
Broggi, as modified, does not specifically describe the system to include in response to determining that the first object data does not correspond to the second object data, disable an autonomous mode of operation for the vehicle after the vehicle is stopped.
Kozak discloses, teaches, or at least suggests the missing limitation. Kozak describes operating a vehicle in an automatic mode while routing the vehicle to and stopping the vehicle at a standby location (Kozak, Paragraph 0057). Kozak further describes that after stopping the vehicle while in the automatic mode, the vehicle transitions to a manual mode (Kozak, Paragraph 0058 and Paragraph 0007).
As a result, a person of ordinary skill in the art would have found it obvious to modify the system to include in response to determining that the first object data does not correspond to the second object data, disable an autonomous mode of operation for the vehicle after the vehicle is stopped.
It would have been obvious to combine and modify the cited references, with a reasonable expectation of success, because maintaining automatic operation through the stopping operation and transitioning to manual operation after the vehicle is stopped permits the vehicle to complete the stopping maneuver before relinquishing autonomous control (Kozak, Paragraphs 0057-0058).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to ANDREW J CROMER whose telephone number is (313)446-6563. The examiner can normally be reached M-F: ~ 8:15 A.M. - 6:00 P.M..
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, Faris Almatrahi can be reached at (313) 446-4821. 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.
/ANDREW J CROMER/Examiner, Art Unit 3667
Prosecution Insights