DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Arguments
The amendment filed July 9, 2026 has been entered. Claims 1, 12, and 14 have been amended. Claim 3 is presently canceled. The remaining claims are in original or previously presented form. Therefore, claims 1, 2, and 4-15 are pending in the application. Claims 1, 12, and 14 are the independent claims.
The applicant’s Remarks, filed July 9, 2026, has been fully considered. The applicant argues, under the heading “Representative Claim 1,” that Nister (US2019/0243371) does not teach, as present claim 1 does:
determining ego occupancy information is performed by a trained artificial neural network, and
the trained artificial neural network has been trained based on training data including traffic situations of a plurality of moving road users;
What does the first bullet mean, according to the present published disclosure Schafer (US2024/0166204)? Paragraph 0034 teaches that in step 120 this ego occupancy information is “determined by the processor.” The paragraph states that “ego occupancy information relates to the possibility of the ego vehicle being located at a particular location at a particular future point in time. A larger occupancy information value indicates a higher probability of being at a particular location compared to lower occupancy information value. The estimation in step 120 is made for a plurality of future locations which may for example be arranged in a grid around the vehicle…The estimation is also made for a plurality of future points in time, such that he estimate can be considered to provide a three-dimensional (two spatial and one temporal dimension) estimate of the future location of the ego vehicle.”
Is “determining ego occupancy information” by a neural network identical to generating a ego vehicle’s trajectory by a neural network in the present disclosure? It doesn’t seem that way. Paragraph 0019 teaches that “The stop of obtaining context information for the vehicle may comprise obtaining maneuver information relating to the future trajectory of the vehicle, and the step of determining ego occupancy information may additionally be based on the maneuver information.” The paragraph states that the control unit can provide the planned maneuver of the vehicle. Then “Using planned maneuver information” the system “improves the accuracy of the prediction of possible future locations of the ego vehicle”.
So when paragraph 0034 states that step 120 involves determining ego occupancy information, it is important to keep in mind that it also says that this is “based on the context information” which paragraph 0019 teaches is “based on the maneuver information”. Paragraph 0015 teaches that context information can be static context information such as roads and lanes, that can restrict the possible future location of the vehicle.
So a proper interpretation of the claim limitations listed above are that the system uses a neural network to determine ego occupancy information, which is based on context information, which is based on maneuver information. In one reasonable example, system can decide that the ego vehicle is going to make a right turn, as shown in Fig. 3A. The system may also know some additional context information such as some curbs. Then a neural network might determine the ego occupancy information using a neural network.
So the question really isn’t: Does Nister teach generating trajectories for the ego vehicle using a neural network? The question is: Does Nister teach “determining ego occupancy information” using a neural network?
Does Nister teach this? The applicant does not think so. It seems clear that Nister determines ego occupancy information. That is clear from the figures alone. Is this done using a neural network? It certainly seems like it. Paragraph 0085 of Nister teaches that “In some examples, machine learning models, such as neural networks…may be used to determine the states of the actors.” These “states” are the locations of actors, and other properties of the actors, including locations and properties at times in the future, according to paragraph 0131. See also paragraph 0083, which uses the term “state trajectories”. Paragraph 0085 goes on to give an “example” involving “the state of the objects 106” which is “in the environment” of the host vehicle. Paragraph 0206 teaches that the system can use “machine learning models, such as neural networks” to learn over time the “particular path” that “an actor may be likely to follow”. Paragraph 0185 teaches that the “trajectory generator 138 may generate a vehicle-occupied trajectory(ies).” Is this done using a neural network? Nister, paragraph 0091 teaches that “one or more neural networks” may be “used to identify the side of the road and/or to aid in maneuvering the vehicle 102 to the side of the road.”
The applicant characterizes Nister paragraph 0129 as “irrelevant” to the present limitations because, in the applicant’s summary, “it concerns using a neural network to perceive the latency or lag of other actors in order to adjust trajectory shapes, not to generate ego occupancy information.” The applicant here confuses generating ego occupancy information with generating trajectories. Generating ego occupancy information is several steps after generating vehicle trajectories, as has been shown above. In Nister, there are predicted trajectories of the ego vehicle and the surrounding objects, and then there are uncertainties about these trajectories. There is uncertainty with respect to what the ego vehicle is going to do because there is uncertainty with respect to what other vehicles 106 are going to do. That uncertainty is reflected in the flaring of ego vehicle and the object’s trajectories. Nister paragraph 0129 states that a road actor may get distracted “due to looking at a phone, or reaching for something, etc.” and therefore react later than expected. Also reaction times can vary. Plus, there is a “lag between when a command is received and when the actuation actually occurs.” At least some of this may be captured using “neural networks.” Then the system will adjust the “shape…of the trajectory(ies) of the claimed sets for the actors (e.g., the vehicle 102 and/ or the objects 106)”. The examiner doesn’t find this irrelevant.
It’s also hard to look at Fig. 3D, for example, or Fig. 3F, which both feature both the ego vehicle 102 and an object 106, and not think that the same procedure—namely, a neural network is determining ego occupancy information—is being used for both vehicles and objects. That’s because the occupancy forecasts for both items 102 and 106 look nearly identical. Does the flaring in Fig. 6B of vehicle 102 really get generated using a different method than the flaring of object 106? The disclosure of Nister even talks about these trajectories in the same way. In Fig. 8, the system is configured to determine an “intersection between the vehicle-occupied trajectory and an object-occupied trajectory”.
It seems unreasonable to think both sets of occupancy information are not found using a neural network. Paragraph 0085 states that neural networks are used to determine the states of actors. In the last detailed action the examiner argued that when Nister uses the term “actors” it sometimes means the vehicle. The examiner cited paragraph 0099 regarding this. The applicant characterizes the examiner’s citation of paragraph 0099 as “misleading” and states that it “does not mean that the term ‘actor’ always includes the vehicle and the objects.” In paragraph 0099, Nister writes: “actors (e.g., the [ego] vehicle 102 and the objects 106)”. In paragraph 0129, Nister writes that the disclosed system can use “neural networks” to capture at least some of this uncertainty, and that the system can
The applicant also characterizes Caldwell as using deterministic action-planning trajectories, rather than trained ANN. The examiner’s view of Caldwell is that the trajectories of about objects and the ego vehicle are generated using one or more neural networks. Then costs are added and weighted in an objective formula.
The applicant further argues that Nister Nister does not teach “dynamic occupancy grid” and that the examiner’s argument that Nister does teach this is flawed for three reasons. The applicant argues that Niter’s core representation is space-time trajectories…rather than a discretized probabilistic grid. The applicant argues that, second, “the visual ‘grid’ appearance in Figs. 9A and 9B is a visualization artificat.” Third, the applicant argues that “Nister does not ‘overlap occupancy information in a grid-map’”. The examiner views Nister as teaching a world coordinate system in which occupancies can be determined as overlapping. This is clear from the figures. If a point of one object contacts that of another, that could represent a collision. The present disclosure, focuses instead of a grid. The overlap must be on the grid, not so much on the volumes (objects) that exist within the grids coordinates. The examiner does not agree that the visualizations in Nister are mere artifacts, because these are taught as being used for determining actions executed automatically by the controller. Yet, the examiner agrees that the discretized grid in the present claim is slightly different than that found in Nister.
Therefore, the grounds for rejection have changed. Please see the second non-final rejections below.
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.
Claims 1, 2, 4-7 and 9-14 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Shridhar et al. (US2022/0105955)
Regarding claim 1, Shridhar discloses:
A computer-implemented method for collision threat assessment of a vehicle (see Fig. 2 for a vehicle computing system 210 for vehicle 205. See the methods in Figs. 8-10B), the computer-implemented method comprising:
obtaining context information for a surrounding of the vehicle including information about a road user, wherein (see Fig. 8, item 810. See paragraph 0075 for a neural network trained to predict the motion of the objects within the surrounding environment based on past and current states of those objects as well as the environment in which the objects are located, such as the lane boundaries.):
the context information includes dynamic context information, and
the dynamic context information represents information about the road user including its position and velocity (see paragraph 0074 for the system using perception data 275 including an object’s current or past location, speed, heading, size, and class (pedestrian, vehicle, bicycle, etc.).);
determining ego occupancy information for a plurality of possible future locations of the vehicle at a plurality of future points in time based on the context information, wherein (see Fig. 5 and paragraph 0094 for the ego vehicle 205 over various vehicle footprints 505A-C corresponding to “time steps” 510A-D. See paragraph 0077 for the vehicle computing system 210 using a machine-learned model to “determine an optimized vehicle trajectory through the surrounding environment”.):
determining ego occupancy information is performed by a trained artificial neural network (see paragraph 0082. See paragraph 0159 for item 1235 being a computer-based neural network.), and
the trained artificial neural network has been trained based on training data including traffic situations of a plurality of moving road users (see paragraph 0082 for training the model using simulation data indicative of a plurality of environments “and/or” testing objects/object trajectories at one or more times.);
determining road user occupancy information for a plurality of possible future locations of the road user at the plurality of future points in time based on the context information (see Fig. 8, item 810. See paragraph 0075 for a neural network trained to predict the motion of the objects within the surrounding environment based on past and current states of those objects as well as the environment in which the objects are located, such as the lane boundaries. See also paragraph 0092, second sentence.);
fusing the ego occupancy information and the road user occupancy information to obtain fused occupancy information at each future point in time, wherein (see Fig. 5):
the plurality of possible future locations of the vehicle and the road user are organized as a grid-map (see Fig. 5), and
the ego occupancy information and the road user occupancy information are overlapped in the grid-map to obtain the fused occupancy information (see Fig. 5. See time 510D in particular, where the ego vehicle 205 and object 335 overlap in the grid-map); and
determining a collision threat value based on the fused occupancy information (see paragraph 0086 for using machine learning to determine metrics for avoidance and availability of motion paths when spaces “are considered unavailable due to an overlapping predicted object trajectory”. This is used for “stopping the vehicle before an actual…collision” thus helping “avoid a collision” with the object.).
Regarding claim 2, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1 further comprising:
filtering context information by selecting a subset of the context information (in the present disclosure, paragraph 0046 teaches that filtering context information can include filtering dynamic and static context information. For example, filtering dynamic context information, broadly and reasonably means filtering out moving objects detected in sensor data, meaning, filtering out other road users. So paragraph 0046 recites that filtering out dynamic context information includes “predicting the ego vehicle’s future position assuming no other road users are on the road….the ego vehicle may still follow the road or lane [static context information] but it does not see [other pedestrians or vehicles]”. In another example given in paragraph 0046 no ambiguity over the host vehicle’s future position is included (i.e., it is filtered out) because the host vehicle is commanded by a route guidance system and thus where the host vehicle is projected to go has no ambiguity.
With that in mind, see Shridhar, paragraph 0096 for generating occupancy grids that are “agnostic to road-geometry”. The system knows this geometry, but it filters it, at least in “some implementations”. See Figs. 6A-B and paragraph 0097 for determining that some sections of a grid are “irrelevant” and there for the grid is “adapted”.),
wherein determining ego occupancy information and determining road user occupancy information are performed based on the selected subset of the context information (see paragraph 0096 for using the occupancy grid that is agnostic to road-geometry. See Figs. 6A-B and paragraph 0097 for determining that some sections of a grid are “irrelevant” and there for the grid is “adapted”. See also Fig. 7.).
Regarding claim 4, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1 further comprising
triggering an Advanced Driver Assistance Systems (ADAS) functionality in response to the collision threat value exceeding a predetermined threshold at a future point in time (see paragraph 0086 for determining an avoidance and availability metric. The avoidance metric quantifies whether a vehicle’s space is “overlapped”. The availability metric quantifies the percentage of the ego vehicle’s future path that is overlapped. Based on these, the system is configured for “stopping the vehicle earlier than necessary to avoid a collision.” The predetermined threshold is suggested here well above a preponderance of the evidence standard. The section is at least stating that if the path is blocked, the system will automatically slow down or stop, and do so earlier than necessary. The threshold here can be any percentage of blockage.).
Regarding claim 5, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1 wherein:
the context information includes static context information (see paragraph 0075 for a neural network trained to predict the motion of the objects within the surrounding environment based on past and current states of those objects as well as the environment in which the objects are located, such as the lane boundaries. Lane boundaries are static context information.); and
the static context information represents information about the surrounding of the vehicle (see the above bullet).
Regarding claim 6, Shridhar discloses the computer-implemented method of claim 5.
Shridhar further discloses:
The computer-implemented method of claim 5 wherein
the static context information is represented at least in part by at least one of map data or traffic rules (see paragraph 0071).
Regarding claim 7, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1 wherein
the dynamic context information additionally represents information about the vehicle (see Fig. 7 and paragraph 0101 for evaluation “approximate vehicle trajectories”. See paragraph 0076 for the system receiving the route the ego vehicle wants to take.).
Regarding claim 9, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1 wherein:
obtaining context information for the vehicle includes obtaining planned maneuver information relating to a planned maneuver of the vehicle (see Fig. 7 and paragraph 0101 for evaluation “approximate vehicle trajectories”. See paragraph 0076 for the system receiving the route the ego vehicle wants to take. See also Fig. 5); and
determining ego occupancy information is additionally based on the planned maneuver information (see Fig. 7 and paragraph 0101 for evaluation “approximate vehicle trajectories”. See paragraph 0076 for the system receiving the route the ego vehicle wants to take. See also Fig. 5).
Regarding claim 10, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1 further comprising
obtaining context information for the surrounding of the vehicle including information about a plurality of road users (see paragraph 0074 for the system using perception data 275 including an object’s current or past location, speed, heading, size, and class (pedestrian, vehicle, bicycle, etc.).).
Regarding claim 11, Shridhar discloses the computer-implemented method of claim 1.
Shridhar further discloses:
The computer-implemented method of claim 1, wherein:
determining road user occupancy information is performed by the trained artificial neural network (see Fig. 8, item 810. See paragraph 0075 for a neural network trained to predict the motion of the objects within the surrounding environment based on past and current states of those objects as well as the environment in which the objects are located, such as the lane boundaries.).
Regarding claim 12, Shridhar discloses:
An apparatus comprising:
a computer-readable medium storing instructions (see Fig. 2 for a vehicle computing system 210 for vehicle 205. See Fig. 11 for processor 1210 and memory 1215 with instructions 1225.); and
at least one processor configured to execute the instructions, wherein the instructions include (see Fig. 2 for a vehicle computing system 210 for vehicle 205. See Fig. 11 for processor 1210 and memory 1215 with instructions 1225.):
obtaining context information for a surrounding of a vehicle including information about a road user, wherein (for the remainder of the rejection, see the rejection of claim 1 which is substantially similar.):
the context information includes dynamic context information, and
the dynamic context information represents information about the road user including its position and velocity;
determining ego occupancy information for a plurality of possible future locations of the vehicle at a plurality of future points in time based on the context information, wherein:
determining ego occupancy information is performed by a trained artificial neural network, and the trained artificial neural network has been trained based on training data including traffic situations of a plurality of moving road users; determining road user occupancy information for a plurality of possible future locations of the road user at the plurality of future points in time based on the context information; fusing the ego occupancy information and the road user occupancy information to obtain fused occupancy information at each future point in time wherein:
the plurality of possible future locations of the vehicle and the road user are organized as a grid-map, and
the ego occupancy information and the road user occupancy information are overlapped in the grid-map to obtain the fused occupancy information; and
determining a collision threat value based on the fused occupancy information.
Regarding claim 13, Shridhar discloses the apparatus of claim 12.
Shridhar further discloses:
The apparatus of claim 12, wherein
the vehicle comprises a sensor system including a plurality of sensors configured to provide sensor data, wherein the context information is determined based at least in part on the sensor data (see Fig. 2 for sensors 235. These are in input into the computing system 240. See paragraph 0070).
Regarding claim 14, Shridhar discloses:
A non-transitory computer-readable medium comprising instructions including (see Fig. 2 for a vehicle computing system 210 for vehicle 205. See Fig. 11 for processor 1210 and memory 1215 with instructions 1225.):
obtaining context information for a surrounding of a vehicle including information about a road user, wherein (for the remainder of the rejection, see the rejection of claim 1 which is substantially similar.):
the context information includes dynamic context information, and
the dynamic context information represents information about the road user including its position and velocity;
determining ego occupancy information for a plurality of possible future locations of the vehicle at a plurality of future points in time based on the context information, wherein:
determining ego occupancy information is performed by a trained artificial neural network, and
the trained artificial neural network has been trained based on training data including traffic situations of a plurality of moving road users;
determining road user occupancy information for a plurality of possible future locations of the road user at the plurality of future points in time based on the context information;
fusing the ego occupancy information and the road user occupancy information to obtain fused occupancy information at each future point in time wherein:
the plurality of possible future locations of the vehicle and the road user are organized as a grid-map, and
the ego occupancy information and the road user occupancy information are overlapped in the grid-map to obtain the fused occupancy information; and
determining a collision threat value based on the fused occupancy information.
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 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 text of those sections of Title 35, U.S. Code not included in this action can be found in a prior Office action.
The factual inquiries set forth in Graham v. John Deere Co., 383 U.S. 1, 148 USPQ 459 (1966), that are applied 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.
Claim 8 is rejected under 35 U.S.C. 103 as being unpatentable over Shridhar in view of Narang et al. (U.S. 11,124,204 B1)
Regarding claim 8, Shridhar teaches the computer-implemented method of claim 1.
Yet Shridhar does not explicitly further teach:
A computer-implemented method further comprising:
filtering out road users by selecting a subset of road users in the surrounding of the vehicle,
wherein determining the ego occupancy information is performed based on the selected subset of road users.
However, Narang teaches:
A computer-implemented method further comprising:
filtering out road users by selecting a subset of road users in the surrounding of the vehicle (see Fig. 3C for a traffic situation labeled “Localized Environmental Representation”. The system is similar to Nester in that it is related to trajectory prediction of vehicle and trajectory generation of an ego vehicle. See Narang col. col. 1, lines 25-43 for the system having a “predefined driving goal” that is “continuously constrained by both driving rules of the road and human driving conventions”. The system considers surrounding objects as well as “map information such as: road boundaries, location of stop signs,” according to col. 24, lines 9-27 and lines 28-58. The system can determine a “safety tunnel,” which according to col. 24, lines 9-27 and lines 28-58 is essentially where the host vehicle can drive safely in the near future based on static and dynamic context information. According to col. 25, lines 11-29 “The safety tunnel can optionally be used to select which static and dynamic objects are within the safety tunnel, wherein only those objects are used for consideration and/or further processing (e.g., in determining the localized environmental representation, in determining a latent space representation, etc.). In some variations, for instance, localized dynamic and static object selectors (e.g., in the computing system) select the relevant surrounding objects based on the action output from the 1.sup.st learning module, its associated safety tunnel, as well as any information about these objects such as their location, distance from the ego vehicle, speed, and direction of travel (e.g., to determine if they will eventually enter the safety tunnel). Additionally or alternatively, relevant static and dynamic objects can be determined in absence of and/or independently from a safety tunnel (e.g., just based on the selected action, based on a predetermined set of action constraints, etc.), all static and dynamic objects can be considered, and/or S224 can be otherwise suitably performed.” See col. 25, lines 38-42 for teaching that in step S224 “The set of inputs can include any or all of the inputs described above…and/or any suitable set of combination of inputs.” This “includes any or all of: dynamic object information (e.g., within the safety tunnel) and their predicted paths; static object information (e.g., within the safety tunnel); one or more uncertainty estimates…a map” etc.
The reason to do this is described in col. 25, line 54 through col. 26, line 3. This section teaches that “The set of inputs are preferably used to determine a localized environmental representation, which takes into account the information collected…thereby producing a more targeted, relevant, and localized environmental representation for the agent based on the action selected, which is equivalently referred to herein as a localized environmental representation.” This reduces the amount of information processed.
When does S224 occur? See col. 23, lines 52-67 for the teaching that it can be done after S214. But it can also be done after S210 or S212, concurrently with S214, or “in response to S205.” According to Fig. 11, S205 is “receiving a set of inputs”. So “in response” to that, the system can run step S224 and remove or filter some inputs out. According to col. 25, lines 38-42 step S224 includes selecting or filtering “any or all” inputs, which “includes any or all of: dynamic object information (e.g., within the safety tunnel) and their predicted paths; static object information”. See Fig. 11 for the end result being generating a vehicle trajectory in S220.),
wherein determining the ego occupancy information is performed based on the selected subset of road users (see Fig. 11 for the end result being generating a vehicle trajectory in S220.).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have modified the system, as taught by Shridhar, to add the additional features of filtering out road users by selecting a subset of road users in the surrounding of the vehicle, wherein determining the ego occupancy information is performed based on the selected subset of road users, as taught by Narang. The motivation for doing so would be to produce a more targeted and relevant set of vehicle actors in the environment of the host vehicle in order to reduce processing by the computer, as recognized by Narang (see col. 25, line 54 through col. 26, line 3.).
This conclusion of obviousness corresponds to KSR rationale “A”: it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to have combined prior art elements according to known methods to yield predictable results. See MPEP § 2141, subsection III.
Potentially Allowable Subject Matter
Claim 15 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 a statement of reasons for the indication of allowable subject matter:
Claim 15 is not taught by the prior art of record, alone or in combination. The claim recites:
The computer-implemented method of claim 1 wherein:
the ego occupancy information includes at least one ego occupancy value,
the road user occupancy information includes at least one road user occupancy value,
fusing the ego occupancy information and the road user occupancy information includes multiplying the at least one ego occupancy value and the at least one road user occupancy value to obtain at least one fused occupancy value, and
the fused occupancy information includes the at least one fused occupancy value.
The closest prior art is Shridhar, who does not teach, at least “multiplying the at least one ego occupancy value and the at least one road user occupancy value to obtain at least one fused occupancy value”.
Additional Art
The prior art made of record here, though not relied upon, is considered pertinent to the present disclosure.
Refaat et al. (U.S. 11,950,166) teaches at least using a neural network to determine vehicle occupancy. See Fig. 5 below.
PNG
media_image1.png
546
796
media_image1.png
Greyscale
Wang et al. (US2021/0262808 A1) teaches much of what the present application teaches, including grid blocks, as shown in Fig. 9 attached below.
PNG
media_image2.png
480
496
media_image2.png
Greyscale
Heo et al. (US2024/0157976). Heo teaches:
[0080]
FIG. 11 is a diagram for explaining a collision avoidance control method according to a second embodiment, specifically, a collision avoidance control method in an intersection driving situation.
[0081]
For collision avoidance, a movement path of a surrounding object Ob3 is predicted every preset time k, k+1, k+2, . . . , and compared with a travel path of an ego-vehicle Ego, thereby enabling a collision risk area to be determined.
[0082]
The prediction path R3 of the third object Ob3 at time k (step: K) may be predicted according to the representative velocity and direction of the grid cell R1 occupied by the third object Ob3 at time k.
[0083]
The path R2 of the ego-vehicle Ego at time k (step: K) does not overlap the prediction path R3 of the third object Ob3, and it may therefore be determined that there is no risk of collision.
[0084]
The prediction path R4 of the third object Ob3 at time k+1 (step: K+1) may be predicted according to the representative velocity and direction of the grid cell R1 occupied by the third object Ob3 at time k+1. The predicted path R4 of the third object Ob3 at time k+1 (step: K+1) has an area that overlaps the travel path R2 of the ego-vehicle Ego. An area where the predicted path R4 of the third object Ob3 overlaps the travel path R2 of the ego-vehicle Ego may be determined as a risk area.
[0085]
Accordingly, it is possible to avoid collision by modifying the path of the ego-vehicle Ego to follow the path R5 for stopping at the current position.
See the figures below.
PNG
media_image3.png
700
638
media_image3.png
Greyscale
PNG
media_image4.png
446
860
media_image4.png
Greyscale
PNG
media_image5.png
464
870
media_image5.png
Greyscale
PNG
media_image6.png
744
652
media_image6.png
Greyscale
Sadeghi et al. (US2023/0084578), who teaches:
[0020] In some examples of the various aspects, the predicted information gain for each candidate trajectory is determined using a trained convolutional neural network to predict a set of visibility grids that each represent a future visibility of the environment to the sensor system for a respective lateral deviation of the nominal trajectory from the current vehicle state, the predicted information gain being based on a combination of the set of visibility grids and the current occupancy grid.
[0021] In some examples of the various aspects, the method includes encoding the nominal trajectory as a region of interest represented by a region of interest grid that includes cells that correspond to the same respective regions of the environment as cells of the current occupancy grid, the trained convolutional neural network receiving the current occupancy grid and the region of interest grid as inputs to predict the set of visibility grids.
PNG
media_image7.png
586
758
media_image7.png
Greyscale
PNG
media_image8.png
574
710
media_image8.png
Greyscale
PNG
media_image9.png
548
736
media_image9.png
Greyscale
PNG
media_image10.png
562
750
media_image10.png
Greyscale
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANIEL M. ROBERT whose telephone number is (571)270-5841. The examiner can normally be reached M-F 7:30-4:30 EST.
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, Hunter Lonsberry can be reached at 571-272-7298. 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.
/DANIEL M. ROBERT/Primary Examiner, Art Unit 3665
Prosecution Insights