DETAILED ACTION
1. This action is responsive to the following communication: Amended Claims and Remarks filed on September 9, 2025. This action is made final.
2. Claims 43-53 and 55-62 are pending in the case; Claims 43, 57, and 61 are independent claims; Claim 54 is canceled.
Election/Restrictions
3. Newly submitted independent claims 43, 57, and 61 are directed to different inventions that are independent or distinct from the invention originally claimed for the following reasons:
Since applicant has received an action on the merits for the originally presented invention, this invention has been constructively elected by original presentation for prosecution on the merits. Accordingly, Claims 57-62, as submitted on September 9, 2025, are withdrawn from consideration as being directed to non-elected inventions. Corresponding Claims 57-62 as submitted on April 20, 2023 are used as the basis for the rejection of these claims, below. See 37 CFR 1.142(b) and MPEP § 821.03. The Claim Amendment filed on September 9, 2025 significantly changed the independent Claims 43, 57, and 61 such that these three currently pending independent claims are drawn to three distinct inventions, thus the Amendment filed on September 9, 2025, with respect to Claims 57-62 is non-responsive (see MPEP § 821.03).
Newly submitted independent Claims 57 and 61 are directed to inventions that are independent or distinct from the invention originally claimed, for the following reasons:
Group 1 (Claims 43-53, 55, and 56, as filed on September 9, 2025), Group 2 (Claims 57-60, as filed on September 9, 2025), and Group 3 (Claims 61 and 62, as filed on September 9, 2025), are related as combination and subcombination because all of them have scope of operating an autonomous vehicle based on obstacle detection, but respective independent claims of these three groups comprise different steps for such operation, because amended independent Claim 43 now requires “perform at least three obstacle detection methods … wherein a difference between the obstacle detection method includes (i) processing sensor data from different types of obstacle sensors, (ii) processing the same sensor data from the obstacle sensor in different manners, or (iii) both (i) and (ii),” while amended independent Claim 57 requires “perform at least three obstacle detection methods to detect an obstacle” by using three particular obstacle detection methods in order to detect an obstacle based on a machine learning classification of the obstacle, detect an obstacle with geometric detection without classifying the obstacle, and evaluate the slices sensed by an obstacle planar sensor, respectively, and amended independent Claim 61 requires using a plurality of sensors and generating a fused point cloud from such sensors (without any mention of “perform[ing] at least three obstacle detection methods”). Accordingly, the amended limitations of independent claims place the scope of these groups in different classes of invention. The claims in Group 1 do not contain the specific features now amended into the claims of Group 2 and 3, and vice versa. It is noted that amended independent Claim 61 recites features that were similarly amended into dependent Claim 53, but Claim 53 is ultimately dependent on Claim 43 and thus it requires the performance of “at least three obstacle detection methods” as recited in Claim 43 (see also dependent Claims 55 and 56, further illustrating how the sensor recited in Claim 53 meet the requirements of independent Claim 43), but unlike Claim 53, Claim 61 does not appear to require the performance of at least three obstacle detection methods.
The restriction by original presentation appears proper, as after an office action on an application, the Applicant has presented claims directed to a different invention that is distinct from the invention previously claimed because it contains scope that does not require the scope of the previously submitted claims and therefore has a separate utility in the art. The rejection on the merits from the original claims is presented below.
Response to Arguments
4. Applicant’s arguments, see Remarks filed on, with respect to 35 U.S.C. § 103 rejections of Claims 43-53, 55, and 56 have been fully considered but not persuasive.
5. Applicant’s arguments, see Remarks filed on September 9, 2025, with respect to 35 U.S.C. § 103 rejections of Claims 57-62 have been considered but are moot because the claims have been restricted to original presentation and thus the arguments are considered moot because they were directed to the amended (i.e., non-elected) features. It is noted that Applicant has amended away the features of the claims previously examined and entered amendments to functions and structure neither previously claimed nor within the same scope of the originally elected clams by Applicant. Thus, Applicant’s arguments with respect to Claims 57-62 are considered as being directed to claims restricted by original presentation.
Claim Rejections - 35 USC § 112
The following is a quotation of relevant paragraphs of 35 U.S.C. 112:
(a) IN GENERAL.—The specification shall contain a written description of the invention, and of the manner and process of making and using it, in such full, clear, concise, and exact terms as to enable any person skilled in the art to which it pertains, or with which it is most nearly connected, to make and use the same, and shall set forth the best mode contemplated by the inventor or joint inventor of carrying out the invention.
(b) CONCLUSION.—The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the inventor or a joint inventor regards as the invention.
6. Claims 46, 53, 55, and 56 are rejected under 35 U.S.C. 112(a) as failing to comply with the written description requirement.
With respect to Claim 46, the claim contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, at the time the application was filed, had possession of the claimed invention. Dependent Claim 46, as amended, recites “wherein the electronic processor is configured to perform the action in response to determining that at least two of the three obstacle detection methods have detected the obstacle and determined the potential collision,” but the instant Specification only describes “in response to detecting the at least one of the first, second, or third obstacles … performing, using the vehicle electronic processor 410, an action to avoid collision” (see Specification, ¶ 0105). It would appear that the amended claim requires ignoring a detected obstacle unless it is recognized by at least two or more obstacle detection methods, but this would appear to be contrary to the instant Specification.
With respect to Claim 53 (from which Claims 55 and 56 are dependent upon), the claim contains subject matter which was not described in the specification in such a way as to reasonably convey to one skilled in the relevant art that the inventor or a joint inventor, at the time the application was filed, had possession of the claimed invention. Dependent Claim 53, as amended, recites “receive three-dimensional point cloud information generated by the three-dimensional long-range sensor; receive a three-dimensional image captured by the three-dimensional image sensor; generate a fused point cloud based on sensor data received from the three-dimensional long-range sensor and the three-dimensional image sensor by matching voxels from the three-dimensional point cloud information with voxels from the three-dimensional image,” but the only mention of this recited matching is found in Paragraph 0091 of the instant Specification (reciting “In three-dimensional point clouds, a voxel takes the place of a pixel. When fusing a 3D (for example, RGB-D) image from a 3D image sensor with the 3D point cloud of the 3D LiDAR sensor, a voxel of the 3D image may be matched with the corresponding voxel of the 3D point cloud. The fused point cloud includes the matched voxels from the 3D image and the 3D point cloud.”). The instant Specification merely states that the matching is performed without any explanation as to how it is performed and/or accomplished. Dependent Claims 55 and 56 do not appear to cure the deficiencies of Claim 53 from which they are dependent upon, thus they are rejected under the same rationale as Claim 53.
7. Claims 43-53, 55 and 56 are rejected under 35 U.S.C. 112(b) as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor regards as the invention.
Independent Claim 43, as amended, recites “perform at least three obstacle detection methods to detect obstacles based on sensor data captured by the obstacle sensor, wherein a difference between the obstacle detection method includes (i) processing sensor data from different types of obstacle sensors, (ii) processing the same sensor data from the obstacle sensor in different manners, or (iii) both (i) and (ii),” but it is not clear how such “difference” is to be interpreted – stated differently, it is not clear if the limitation requires performing at least three different obstacle detection methods (where such detection methods comply with either (i), (ii), or both (i) and (ii)) or if each of (i), (ii), and (iii) correspond to one of the three required detection methods. Dependent claims do not appear to cure the deficiencies of independent Claim 34, thus they are also rejected under the same rationale.
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.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
8. Claims 43, 47, and 48 are rejected under 35 U.S.C. 103 as being unpatentable over Keivan et al. (hereinafter Keivan), US 2019/0179329 A1, published on June 13, 2019.
With respect to independent Claim 43, Keivan teaches an autonomous vehicle [for operation in an airport], the autonomous vehicle comprising:
a frame (see Figs. 1A-B, ¶ 0015).
a platform coupled to the frame and configured to support a load (see Figs. 1A-B; see also ¶¶ 0010, 0061).
an obstacle sensor positioned relative to the frame and configured to detect obstacles about the frame … (see Figs. 1A-B, element 102; see also ¶¶ 0013, 0045-46, 0100).
…
an electronic processor coupled to the obstacle sensor and configured to operate the autonomous vehicle based on the obstacles detected by the obstacle sensor (see Figs. 1C-D, 8, ¶¶ 0046-47, 0049, 0057, 0085).
While Keivan does not appear to explicitly illustrate the autonomous vehicle for operation in an airport, Keivan makes it clear that the autonomous vehicle described therein can operate in a variety of environments (see ¶¶ 0007, 0048, 0141), and a skilled artisan would be able to operate such vehicle in an airport in a predictable manner.
With respect to “wherein the obstacle sensor is configured to detect obstacles on a ground in a vicinity of the autonomous vehicle and overhanging obstacles that are above the ground in the vicinity of the autonomous vehicle,” this appears to be an intended use of the obstacle sensor. It is noted that a recitation of the intended use of the claimed invention must result in a structural difference between the claimed invention and the prior art in order to patentably distinguish the claimed invention from the prior art. If the prior art structure is capable of performing the intended use, then it meets the claim. Here, Keivan teaches various obstacle sensors which do not preclude “detect[ing] obstacles on a ground in a vicinity of the autonomous vehicle and overhanging obstacles that are above the ground in the vicinity of the autonomous vehicle.” Furthermore, a skilled artisan would understand that the obstacle sensor, such as a camera-based sensor, would detect obstacles in various locations (and positions) in order to ensure that the autonomous vehicle is able to travel without colliding with an obstacle (see ¶¶ 0007, 0085).
Keivan does not appear to explicitly state “perform at least three obstacle detection methods to detect obstacles based on sensor data captured by the obstacle sensor, wherein a difference between the obstacle detection methods includes (i) processing sensor data from different types of obstacle sensors, (ii) processing the same sensor data from the obstacle sensor in different manners, or (iii) both (i) and (ii)” (but see § 112(b) rejection, above), but Keivan suggests utilizing different sensors simultaneously, and a skilled artisan would understand that processing data from such sensors would read on step (i) of this limitation (see ¶ 0045).
With respect to dependent Claim 47, Keivan teaches the autonomous vehicle according to claim 43, as discussed above, and further teaches wherein the obstacle sensor includes a plurality of obstacle planar sensors positioned relative to the frame and configured to provide overlapping sensor coverage around the autonomous vehicle (see ¶ 0045).
With respect to dependent Claim 48, Keivan teaches the autonomous vehicle according to claim 47, as discussed above, and further teaches wherein the obstacle sensor includes a plurality of obstacle depth sensors positioned relative to the frame and together configured to detect obstacles 360 degrees about the frame (see ¶¶ 0013, 0103; see also ¶¶ 0045, 0100).
9. Claims 44, 45, 49, 50, 52, 57, 61, and 62 are rejected under 35 U.S.C. 103 as being unpatentable over Keivan in view of Gariepy et al. (hereinafter Gariepy), US 2017/0197643 A1, published on July 13, 2017.
With respect to dependent Claim 44, Keivan teaches the autonomous vehicle according to claim 43, as discussed above, and while Keivan describes the vehicle sensing changes in its environment and communicating observed map changes/differences to a server (see ¶¶ 0017, 0048, 0099-100), the teachings of Gariepy, directed towards a path control in unmanned vehicles (see Gariepy, Abstract), can be relied upon for an explicit suggestion of wherein the electronic processor is configured to determine a measured value of a movement parameter of the autonomous vehicle; determine a planned value of the movement parameter of the autonomous vehicle; determine a potential collision based on an obstacle detected by the obstacle sensor and at least one of the measured value and the planned value; and perform an action to avoid the potential collision (see Gariepy, Figs. 4-8, ¶¶ 0037-38, 0040-50, showing that a measured value (i.e., speed and/or direction) can be obtained, together with a planned value (i.e., future/planned locations and set/planned speed) for the vehicle, and that such values determine sensor regions for detecting a potential collision with an obstacle, resulting in an action to avert colliding with the obstacle).
Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the path control described in Gariepy with the autonomous vehicle of Keivan in order to make the operation of the autonomous vehicle more efficient by reducing a need for emergency braking and/or a need for a manual override by a human operator (see Gariepy, ¶¶ 0003-04).
With respect to dependent Claim 45, Keivan in view of Gariepy teaches the autonomous vehicle of claim 44, as discussed above, and further teaches wherein the action includes one selected from a group consisting of applying brakes of the autonomous vehicle and applying a steering of the autonomous vehicle (see Gariepy, Fig. 8, ¶¶ 0058-64, 0066, 0068, 0070-72, showing steering to follow a different path and/or adjusting the speed in order to avoid the obstacle).
With respect to dependent Claim 49, Keivan teaches the autonomous vehicle of claim 48, as discussed above, and Keivan suggests that a plurality of different sensors can be used with the autonomous vehicle (see ¶ 0045) (and a skilled artisan would understand that such sensors could have an overlapping coverage area). Keivan appears to read on detect obstacles in sensor data captured by the plurality of obstacle depth sensors; and receive, from one or more of the obstacle planar sensors, obstacle information not detected in the sensor data captured by the plurality of obstacle depth sensors (see ¶ 0045, stating that the autonomous vehicle “can also include a two-dimensional LIDAR sensor (not shown) to look sideways and identify objects or people approaching the cart from the side that the binocular vision sensor units may not sense or identify”). However, the teachings of Gariepy can be relied upon for an explicit suggestion of this limitation.
Gariepy is directed towards a path control in unmanned vehicles (see Gariepy, Abstract) and teaches overlapping sensor regions that can be implemented using different types of sensors (see Gariepy, ¶¶ 0045, 0049, 0052, 0056-59). Therefore, Gariepy suggests different sensing modes that allow for overlapping sensing regions using different sensors. Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the path control described in Gariepy with the autonomous vehicle of Keivan in order to make the operation of the autonomous vehicle more efficient by reducing a need for emergency braking and/or a need for a manual override by a human operator (see Gariepy, ¶¶ 0003-04).
With respect to dependent Claim 50, Keivan in view of Gariepy teaches the autonomous vehicle of claim 49, as discussed above, and further teaches wherein the electronic processor is further configured to reduce a speed of the autonomous vehicle in response to receiving the obstacle information (see Gariepy, ¶¶ 0004, 0047, 0056-64).
With respect to dependent Claim 52, Keivan teaches the autonomous vehicle according to claim 43, as discussed above, and while Keivan describes obtaining a map of an environment and updating the map based on the observed changes (see ¶¶ 0004, 0017, 0048, 0099-100), Keivan does not appear to explicitly illustrate a task information or a task path plan, although a skilled artisan would understand that the assigned path corresponding to the obtained map would correspond to the task path plan as recited in the claim. However, the teachings of Gariepy can be relied upon for an explicit showing of this limitation. Gariepy teaches receiving a task to be performed and generating a path corresponding to the task(s), and controlling the autonomous vehicle to travel on that path (see Gariepy, ¶¶ 0017-19, 0021; see also ¶¶ 0030, 0038). Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the path control described in Gariepy with the autonomous vehicle of Keivan in order to make the operation of the autonomous vehicle more efficient by reducing a need for emergency braking and/or a need for a manual override by a human operator (see Gariepy, ¶¶ 0003-04).
With respect to independent Claim 57 (as presented in Claims filed on 04/20/2023) , Keivan teaches an autonomous vehicle for operation in an airport, the autonomous vehicle comprising:
a frame; a platform coupled to the frame and configured to support a load; a plurality of obstacle sensors mounted to the frame and configured to detect obstacles about the autonomous vehicle; an electronic processor coupled to the plurality of obstacle sensors and configured to (see Figs. 1A-D, 8, ¶¶ 0010, 0013, 0015, 0045-47, 0049, 0057, 0061, 0085, 0100).
While Keivan suggests using a plurality of sensors in order to detect different obstacles (i.e., obstacles that one particular sensor may not sense or identify) (see ¶ 0045), the teachings of Gariepy, directed towards a path control in unmanned vehicles, can be relied upon for an explicit suggestion of:
receive sensor data from the plurality of obstacle sensors,
determine, using a first obstacle detection layer on the sensor data, a first obstacle in a planned path of the autonomous vehicle based on a predicted trajectory of a detected object,
determine, using a second obstacle detection layer on the sensor data, a second obstacle in the planned path based on geometric obstacle detection,
determine, using a third obstacle detection layer on the sensor data, a third obstacle in the planned path based on planar obstacle detection, and
perform an action to avoid collision with at least one of the first obstacle, the second obstacle, and the third obstacle in the planned path of the autonomous vehicle
(see Gariepy, ¶¶ 0045, 0049, 0052, 0056-59). Therefore, Gariepy suggests different sensing modes that allow for overlapping sensing regions using different sensors. Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the path control described in Gariepy with the autonomous vehicle of Keivan in order to make the operation of the autonomous vehicle more efficient by reducing a need for emergency braking and/or a need for a manual override by a human operator (see Gariepy, ¶¶ 0003-04).
With respect to independent Claim 61 (as presented in Claims filed on 04/20/2023) , Keivan teaches an autonomous vehicle [for operation in an airport], the autonomous vehicle comprising:
a frame; a platform coupled to the frame and configured to support a load; a plurality of sensors including a first sensor and a second sensor; an electronic processor coupled to the plurality of sensors (see Figs. 1A-D, 8, ¶¶ 0010, 0013, 0015, 0045-47, 0049, 0057, 0061, 0085, 0100) and configured to
receive a global path plan (see ¶¶ 0004, 0017).
….
While Keivan does not appear to explicitly suggest “generate a fused point cloud based on sensor data received from a first sensor and a second sensor; detect an object based on the fused point cloud,” the teachings of Gariepy, directed towards a path control in unmanned vehicles, can be relied upon for an explicit suggestion of these limitations. Gariepy teaches receiving a task to be performed and generating a path corresponding to the task(s), and controlling the autonomous vehicle to travel on that path (see Gariepy, ¶¶ 0017-19, 0021; see also ¶¶ 0027, 0030, 0038). Gariepy suggests using a plurality of sensors (and/or using a particular sensor in different modes) in order to detect an obstacle (see Gariepy, ¶¶ 0026-27, 0052). In turn, Gariepy suggests “process obstacle information associated with the object relative to a current position of the autonomous vehicle; determine whether the object is in a planned path of the autonomous vehicle; in response to determining that the object is in the planned path, alter the planned path to avoid the object; and in response to determining that the object is in a vicinity of the autonomous vehicle but not in the planned path, continue executing the planned path” (see Gariepy, Figs. 4-8, ¶¶ 0040-59).
Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the path control described in Gariepy with the autonomous vehicle of Keivan in order to make the operation of the autonomous vehicle more efficient by reducing a need for emergency braking and/or a need for a manual override by a human operator (see Gariepy, ¶¶ 0003-04).
With respect to dependent Claim 62, Keivan in view of Gariepy suggests the autonomous vehicle of claim 61, as discussed above, and further suggests wherein the global path plan is a global map of an airport including at least one selected form the group consisting of a drivable path, a location of a landmark, a traffic pattern, a traffic sign, a speed limit (see Keivan, ¶¶ 0004, 0017).
10. Claim 51 is rejected under 35 U.S.C. 103 as being unpatentable over Keivan in view of Gariepy, and further in view of Aggarwal et al. (hereinafter Aggarwal), US 11,126,944 B1, issued on September 21, 2021.
With respect to dependent Claim 51, Keivan in view of Gariepy teaches the autonomous vehicle of claim 49, as discussed above, and while Keivan in view of Gariepy does not appear to explicitly illustrate wherein the electronic processor is further configured to generate an alert in response to receiving the obstacle information, a skilled artisan would understand that the autonomous vehicle could be further modified to generate an alert when an obstacle is detected in order to notify persons or other vehicles in the vicinity about the detected obstacle and/or to notify the obstacle (i.e., a person, another vehicle) that they are in the vicinity of the autonomous vehicle, as suggested by the teachings of Aggrawal.
Aggrawal is directed towards obstacle detection and avoidance (see Aggrawal, Abstract). Aggrawal teaches that a remedial action (i.e., a notification) can be executed in response to detecting an obstacle (see Aggrawal, col. 14, lines 46-52). Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the notification feature of Aggrawal with the autonomous vehicle and obstacle detection of Keivan in view of Gariepy, in order to ensure that the information about an unexpected obstacle is properly communicated such that an appropriate action can be taken in a timely manner (see Aggrawal, col. 1, lines 6-18).
11. Claims 58-60 (as presented in Claims filed on 04/20/2023) are rejected under 35 U.S.C. 103 as being unpatentable over Keivan in view of Gariepy, and further in view of Ebrahimi Afrouzi et al. (hereinafter Ebrahimi), US 11,348,269 B1, issued on May 31, 2022 (filed on July 2, 2020).
With respect to dependent Claim 58, Keivan in view of Gariepy teaches the autonomous vehicle of claim 57, as discussed above, but Keivan in view of Gariepy does not appear to explicitly disclose wherein the electronic processor is configured to determine a classification of the detected object, and determine the predicted trajectory at least based on the classification. While Keivan suggests observing recognizable objects detected through the sensors (see Keivan, ¶¶ 0100, 0106), a skilled artisan would understand that recognized objects can belong to different categories in order to allow for a more precise collision avoidance (see also Gariepy, ¶¶ 0066, 0072, distinguishing between a stationary and a moving obstacle, and modifying the prediction of the vehicle’s future position/trajectory accordingly). However, the teachings of Ebrahimi can be relied upon for an explicit showing of this limitation.
Ebrahimi is directed towards autonomous robots perceiving a spatial representation of an environment (see Ebrahimi, Abstract). Ebrahimi teaches that a robot can comprise a plurality of sensors used to capture different environment data in order to navigate the environment (see Ebrahimi, col. 2, lines 25-50). Ebrahimi teaches that machine learning can be used in order to recognize objects via a classification algorithm (see Ebrahimi, col. 47, line 59 – col. 48, line 51; see also col. 183, lines 47-60). Accordingly, it would have been obvious to a skilled artisan, at the time the instant application was filed, to incorporate the machine learning features of Ebrahimi with the autonomous vehicle and obstacle detection of Keivan in view of Gariepy, in order to improve the vehicle’s ability to operate autonomously (see Ebrahimi, col. 2, lines 3-11).
With respect to dependent Claim 59, Keivan in view of Gariepy and Ebrahimi teaches the autonomous vehicle of claim 58, as discussed above, and further suggests wherein the action includes at least one selected from the group consisting of altering the planned path of the autonomous vehicle, applying brakes of the autonomous vehicle, and requesting teleoperator control of the autonomous vehicle (see Gariepy, Figs. 5-8, ¶¶ 0047, 0058, 0068).
With respect to dependent Claim 60, Keivan in view of Gariepy and Ebrahimi teaches the autonomous vehicle of claim 59, as discussed above, and further suggests wherein the electronic processor is configured to alter the planned path of the autonomous vehicle in response to determining at least one of the first obstacle and the second obstacle, and apply the brakes of the autonomous vehicle in response to determining the third obstacle (see Gariepy, Figs. 5-8, illustrating different responses based on which sensor data detects the obstacle).
Discussion of Prior Art
It is noted that Claims 46 and 53 (and corresponding dependent Claims 55 and 56) are not rejected under the § 103 (but see § 112(a) rejection, above).
With respect to Claim 46, the prior art of record does not appear to disclose or suggest “perform the action in response to determining that at least two of the three obstacle detection methods have detected the obstacle and determined the potential collision.”
With respect to Claim 53 (and similarly, Claims 55 and 56), while prior art of record suggests that various sensors can be used together and corelated in order to perform obstacle detection, there does not appear to be an explicit suggestion of “generat[ing] a fused point cloud based on sensor data received from the three-dimensional long range sensor and the three-dimensional image sensor by matching voxels from the three-dimensional point cloud with voxels from the three-dimensional image.” For example, the prior art of Pollach et al. (US 2018/0068206 A1) discloses object recognition and classification based on data from multiple sensor modalities (see Abstract, Figs. 1 and 2), and teaches a sensor fusion system which spatially aligns raw measurement data in order to recognize obstacles (see ¶¶ 0028, 0063). The prior art of Nehmadi et al. (US 2022/0398851 A1) describes receiving sensor data from a plurality of sensors modalities and generating a fused 3D map to detect objects of interest (see Abstract, Figs. 1A, 16B, 25). The prior art of Bosse et al. (US 2023/0186494 A1) also discloses utilizing a combination of various sensors, such as LIDARs and cameras (see ¶ 0021), but describes comparing characteristics of spatially aligned voxels within the voxelized representations in order to determine a validity of a point cloud registration between two sets of point cloud data (see ¶ 0014; see also ¶ 0024), but it appears that such registration is typically performed on two sets of LIDAR data points (see ¶ 0012). The prior art of Staab et al. (US 0256722 A1) describes a tie point for a 3D point cloud which appears to correspond to a fusion of various data (see Figs. 1 and 2, ¶¶ 0028-31), but does not appear to disclose or suggest “generat[ing] a fused point cloud based on sensor data received from the three-dimensional long range sensor and the three-dimensional image sensor by matching voxels from the three-dimensional point cloud with voxels from the three-dimensional image,” as recited in Claim 53.
Conclusion
THIS ACTION IS MADE FINAL. Applicant is reminded of the extension of time policy as set forth in 37 CFR 1.136(a).
A shortened statutory period for reply to this final action is set to expire THREE MONTHS from the mailing date of this action. In the event a first reply is filed within TWO MONTHS of the mailing date of this final action and the advisory action is not mailed until after the end of the THREE-MONTH shortened statutory period, then the shortened statutory period will expire on the date the advisory action is mailed, and any extension fee pursuant to 37 CFR 1.136(a) will be calculated from the mailing date of the advisory action. In no event, however, will the statutory period for reply expire later than SIX MONTHS from the mailing date of this final action.
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DINO KUJUNDZIC whose telephone number is (571)270-5188. The examiner can normally be reached M-F 8am - 5pm.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Vivek Koppikar can be reached on 571-272-5109. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of published or unpublished applications may be obtained from Patent Center. Unpublished application information in Patent Center is available to registered users. To file and manage patent submissions in Patent Center, visit: https://patentcenter.uspto.gov. Visit https://www.uspto.gov/patents/apply/patent-center for more information about Patent Center and https://www.uspto.gov/patents/docx for information about filing in DOCX format. For additional questions, contact the Electronic Business Center (EBC) at 866-217-9197 (toll-free). If you would like assistance from a USPTO Customer Service Representative, call 800-786-9199 (IN USA OR CANADA) or 571-272-1000.
/DINO KUJUNDZIC/Primary Examiner, Art Unit 3667