DETAILED ACTION
This Non-Final Office action is in response to the amendment filed 6/4/2026.
Claims 2, 4, 5, 13, 15, 16, and 20 have been amended.
Claims 17 and 19 have been canceled.
Claims 21 and 22 are new claims.
Claims 1-16, 18, and 20-22 are pending.
Response to Arguments
Rejections under 35 U.S.C. 112(b)
Upon further review of the amendment filed 6/4/2026, new issues are presented under 35 U.S.C. 112(b).
Rejections under 35 U.S.C. 102 and 103
Applicant’s arguments with respect to the claims have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument. Specifically, new references have been applied to teach the amendment filed 6/4/2026; therefore, the present Office action has been made non-final.
Key to Interpreting this Office Action
To enhance clarity, claim language is underlined throughout this Office action.
Citations to the prior art are provided in parentheses following each claim limitation, along with any necessary supplemental explanations.
Claim Rejections - 35 USC § 112
The following is a quotation of 35 U.S.C. 112(b):
(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.
The following is a quotation of 35 U.S.C. 112 (pre-AIA ), second paragraph:
The specification shall conclude with one or more claims particularly pointing out and distinctly claiming the subject matter which the applicant regards as his invention.
Claims 1-16, 18, and 20-22 are rejected under 35 U.S.C. 112(b) or 35 U.S.C. 112 (pre-AIA ), second paragraph, as being indefinite for failing to particularly point out and distinctly claim the subject matter which the inventor or a joint inventor (or for applications subject to pre-AIA 35 U.S.C. 112, the applicant), regards as the invention.
Claim 1 recites a camera track, in a previous frame, obtained via the camera within a specified time before the specific frame, or a radar track, in the previous frame, obtained via the radar, while preceding limitations recite obtain, via at least one of the LiDAR, the camera, or the radar, a plurality of dynamic fusion tracks in a specific frame,…delete, among the plurality of dynamic fusion tracks, a target dynamic fusion track corresponding to a target object among the plurality of external objects in the specific frame.
Specifically, claim 1 defines the “specific frame” as including the “plurality of dynamic fusion tracks” and “target dynamic fusion track,” not a “camera track” or a “radar track.” There are no limitations that associate the “radar track” or “camera track” with the “plurality of dynamic fusion tracks;” therefore, the limitation of a “previous frame,” defined “within a specified time before the specific frame,” cannot be reasonably interpreted.
Further, there is insufficient antecedent basis for the limitation of the previous frame in claim 1. Specifically, the “previous frame” is defined in claim 1 with respect to the “camera track,” as part of an optional alternative. A “previous frame” cannot be considered be considered an inherent feature of a “radar track.” No limitations are provided that create a synchronized global buffer of frames across all sensors, such that a “previous frame” would reasonably pertain to the different sensor data.
Claim 12 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 1 recites an error has occurred in the radar and the camera in the specific frame. However, the “specific frame” is defined in the limitation of obtain, via at least one of the LiDAR, the camera, or the radar, a plurality of dynamic fusion tracks in a specific frame.
The “specific frame” cannot be reasonably interpreted by one of ordinary skill in the art. Specifically, both the plurality of dynamic fusion tracks and the error in the radar or camera are defined as being “in the specific frame.” This limitation associates the “specific frame” with target object state estimations (i.e. dynamic fusion tracks) and then redefines the “specific frame” to be associated with system level data (i.e. error in the radar or camera).
Claim 12 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 2 recites deleting the target dynamic fusion track, based on the target dynamic fusion track being obtained via the LiDAR only in the specific frame, and further based on at least one of:
…the target dynamic fusion track obtained in the previous frame being not obtained via the radar track in the previous frame.
There is insufficient antecedent basis for the limitation of the previous frame in claim 2. Specifically, the “previous frame” is defined in claim 1 with respect to the “camera track,” as part of an optional alternative. A “previous frame” cannot be considered be considered an inherent feature of a “radar track.” No limitations are provided that create a synchronized global buffer of frames across all sensors, such that a “previous frame” would reasonably pertain to the different sensor data.
Claim 13 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 3 recites obtain a fusion track in the specific frame, based on at least one of the camera track in the specific frame, or the radar track in the specific frame; and obtain the target dynamic fusion track, based on at least one of a LiDAR track in the specific frame or the fusion track, while claim 1, from which claim 3 depends, recites obtain, via at least one of the LiDAR, the camera, or the radar, a plurality of dynamic fusion tracks in a specific frame, and delete, among the plurality of dynamic fusion tracks, a target dynamic fusion track…based on the target dynamic fusion track being obtained via only the LiDAR.
Specifically, claim 1 deletes the “target dynamic fusion track” in a “specific frame,” while claim 3 attempts to obtain the same deleted “target dynamic fusion track” in the same “specific frame.” Further, claim 1 requires the deleted “target dynamic fusion track,” defined as being “in the specific frame,” to be obtained by only the LiDAR, which inherently excludes the use of the camera or radar in the “specific frame,” while claim 3 further limits the “target dynamic fusion track” to be based on the “fusion track in the specific frame,” defined as being based on “the camera track in the specific frame or the radar track in the specific frame.” One of ordinary skill in the art cannot reasonably interpret the scope of the “target dynamic fusion track” of claim 3, due to the contradictions that the limitations of claim 3 incorporate with respect to claim 1.
Claim 14 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 4 recites deleting the second target dynamic fusion track, based on the second target dynamic fusion track being obtained only via the radar track in the specified time, and based on at least one of:
a position of the second target dynamic fusion track being included in a specified area with respect to the vehicle, the second target dynamic fusion track being obtained based on only the fusion track obtained in the specific frame.
Specifically, the “second target dynamic track” is defined as being obtained “only via the radar track in the specified time” and then redefined as being obtained “based only on the fusion track obtained in the specific frame.” One of ordinary skill in the art cannot reasonably interpret the scope of the “second target dynamic track” of claim 4, due to the claimed contractions within itself.
Further, the “specified time” is defined in claim 1 with respect to the “camera track,” as part of an optional alternative. A “specified time” cannot be considered be considered an inherent feature of a “radar track.” No limitations are provided that create a synchronized global time period across all sensors, such that a “specified time” would reasonably pertain to the different sensor data.
Claim 15 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 4 recites deleting the second target dynamic fusion track, based on the second target dynamic fusion track being obtained only via the radar track in the specified time, and based on at least one of:
…the second target dynamic fusion track in the previous frame, corresponding to the second target dynamic fusion track, being obtained via the LiDAR and corresponding to the target object.
There is insufficient antecedent basis for the limitation of the previous frame in claim 4. Specifically, the “previous frame” is defined in claim 1 with respect to the “camera track,” as part of an optional alternative. A “previous frame” cannot be considered be considered an inherent feature of a “second target dynamic fusion track.” No limitations are provided that create a synchronized global buffer of frames across all sensors, such that a “previous frame” would reasonably pertain to the different sensor data.
Further, the limitation of “the second target fusion track” is defined as corresponding to itself, which is not limiting and creates ambiguity in the claim.
Claim 15 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 5 recites deleting the second target dynamic fusion track, based on the second target dynamic fusion track being obtained only via the radar track in the specific frame, and based on at least one of:
the second target dynamic fusion track being obtained based on only the fusion track obtained in the specific frame.
The “second target dynamic track” is defined as being obtained “only via the radar track in the specific frame” and then redefined as being obtained “based only on the fusion track obtained in the specific frame,” where the “fusion track” is defined in claim 3 as being based on the “camera track.” One of ordinary skill in the art cannot reasonably interpret the scope of the “second target dynamic track” of claim 5, due to the contradictions within itself.
Claim 16 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 7 recites classify the target object corresponding to the deleted target dynamic fusion track as an object incapable of being in the movement state, while claim 1, from which claim 7 depends, defines the plurality of dynamic fusion tracks corresponding to a plurality of external objects classified into objects capable of being in a movement state and a target dynamic fusion track corresponding to a target object among the plurality of external objects.
Specifically, claim 1 defines the “target object” as “capable of being in a movement state,” while claim 7 redefines the “target object” as “incapable of being in a movement state.” One of ordinary skill in the art cannot reasonably interpret the scope of the “target object” of claim 7, due to the contradictions within itself.
Claim 18 is rejected under 35 U.S.C. 112(b) for similar reasons.
Claim 10 recites deleting the target dynamic fusion track based on the error not having occurred in the radar, the camera, the NVD camera, and the RSIR camera, while claim 1 defines the “error” with respect to an optional alternative limitation of whether an error has occurred in the radar and the camera in the specific frame.
Specifically, the “error” is defined in claim 1 with respect to the “camera” and “radar,” while claim 10 redefines the “error” with respect to additional cameras (i.e. NVD camera and RSIR camera). One of ordinary skill in the art cannot reasonably interpret the scope of the “error” of claim 10.
Claim 21 recites maintain a second target dynamic fusion track in a second specific frame…based on an error having occurred in at least one of the radar or the camera in the second specific frame.
The “second specific frame” cannot be reasonably interpreted by one of ordinary skill in the art. Specifically, both the second target dynamic fusion track and the error in the radar or camera are defined as being “in the second specific frame.” This limitation associates the “second specific frame” with object state estimations (i.e. second target dynamic fusion track) and then redefines the “second specific frame” to be associated with system level data (i.e. error in the radar or camera).
Claim 22 recites a camera track, in a previous frame, obtained via the camera within a specified time before the specific frame, or a radar track, in the previous frame, obtained via the radar.
Specifically, claim 22 defines the “specific frame” as including the “plurality of dynamic fusion tracks” and “target dynamic fusion track,” not a “camera track” or a “radar track.” There are no limitations that associate the “radar track” or “camera track” with the “plurality of dynamic fusion tracks;” therefore, the limitation of a “previous frame,” defined “within a specified time before the specific frame,” cannot be reasonably interpreted.
Further, there is insufficient antecedent basis for the limitation of the previous frame in claim 22. Specifically, the “previous frame” is defined in claim 22 with respect to the “camera track,” as part of an optional alternative. A “previous frame” cannot be considered be considered an inherent feature of a “radar track.” No limitations are provided that create a synchronized global buffer of frames across all sensors, such that a “previous frame” would reasonably pertain to the different sensor data.
Claims 6, 8, 9, 11, and 20 are rejected under 35 U.S.C. 112(b) for incorporating the errors of claims 1 and 12 by dependency.
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 (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 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.
Claims 1, 3-5, 7, 8, 12, 14-16, and 18 are rejected under 35 U.S.C. 102(a)(1) as being anticipated by Yun (US 2022/0185268 A1), hereinafter Yun.
Claim 1
Due to the ambiguity discussed in the rejection of claim 1 under 35 U.S.C. 112(b), the scope of the limitations of claim 1 has been interpreted broadly for the purposes of the prior art rejection.
Yun discloses the claimed vehicle control apparatus (see Figure 2, depicting sensor fusion system 200, described as used to support autonomous driving control of a vehicle in ¶0039) comprising:
a light detection and ranging device (LiDAR) (i.e. roof lidar 132, described in ¶0034, with respect to Figure 1);
a camera (i.e. front camera 112 and rear camera 124, described in ¶0034, with respect to Figure 1);
a radar (i.e. front radar 111 and rear/front side radars 113, as described in ¶0034, with respect to Figure 1);
one or more processors (see ¶0032, regarding the units/modules/blocks are implemented as software or hardware, e.g., processor); and
memory storing instructions (see ¶0128, regarding that the method is implemented as computer readable code in a computer readable recording medium in which programs are recorded, e.g., hard disk drive) that, when executed by the one or more processors, cause the vehicle control apparatus to:
obtain, via at least one of the LiDAR, the camera, or the radar, a plurality of dynamic fusion tracks in a specific frame, the plurality of dynamic fusion tracks corresponding to a plurality of external objects (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, where fusion tracks may pertain to different objects, as described in ¶0093, with respect to the sensor groups that include roof lidar 132, as described in ¶0034) classified into objects capable of being in a movement state (see ¶0059-0065, regarding that fusion tracks correspond to object types, e.g., commercial vehicle, passenger vehicle, pedestrian, bicycle, and powered two wheeler).
The limitation of “dynamic fusion tracks” requires only one sensor (i.e. LiDAR, camera, or radar); therefore, the term “fusion” imparts no patentable weight.
Yun further discloses that vehicle control apparatus is caused to delete, among the plurality of dynamic fusion tracks, a target dynamic fusion track (e.g., roof lidar-only track FT2) corresponding to a target object among the plurality of external objects in the specific frame, based on the target dynamic fusion track being obtained via only the LiDAR among the LiDAR, the camera, and the radar (see ¶0043-0045, with respect to Figure 4, regarding track mergence 430 deletes a corresponding track among a plurality of received tracks based on the track deletion conditions, as further described in ¶0049-0051, with respect to Figure 5; ¶0059-0070, with respect to the first phenomenon of Figure 7, regarding that the roof lidar-only track FT2 is deleted when first track deletion condition C_11 is satisfied, which requires deletion variable C to be met, i.e. FT2 is a combined roof lidar-only track, where roof lidar-only track FT2 is a track generated by only roof lidar 132, as opposed to fusion track F1 generated by DOF unit 131, as described in ¶0055), and further based on an object type of the target dynamic fusion track (see ¶0060-0070, regarding that satisfying first track deletion condition C_11 further requires deletion variable E to be met, i.e. FT2 does not correspond to a pedestrian, a person riding a bicycle, and a powered two wheeler, and one of deletion variables A or B, i.e. FT1 corresponds to a commercial vehicle or a passenger vehicle). The equation in ¶0066 of Yun is known to one of ordinary skill in the art to be interpreted as satisfying A or B and simultaneously satisfying C, D, and E.
Yun further discloses that vehicle control apparatus is caused to control a vehicle, based on at least one remaining dynamic fusion track of the plurality of dynamic fusion tracks in the specific frame after the deletion of the target dynamic fusion track (see ¶0077-0078, regarding that upon deletion of fusion track FT2, the situation is determined only based on the actual fusion track FT1, so as to not cause erroneous autonomous braking; ¶0129, regarding that a track to be deleted may be accurately deleted by generating track deletion conditions adaptively corresponding to various situations in which a host vehicle is placed, thereby being capable of prevent collision and erroneous braking of the host vehicle; ¶0039, regarding that the sensor fusion tracks are using in normal autonomous driving control of a vehicle).
Claims 3 and 14
Due to the ambiguity discussed in the rejections of claims 3 and 14 under 35 U.S.C. 112(b), the scope of the limitations of claims 3 and 14 have been interpreted broadly for the purposes of the prior art rejection.
Yun further discloses that the instructions, when executed by the one or more processors, further cause the vehicle control apparatus to:
obtain a fusion track in the specific frame, based on at least one of the camera track in the specific frame, or the radar track in the specific frame (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, with respect to the sensor groups that include front camera 112, rear camera 124, front radar 111, and rear/front side radars 113 associated with and/or collected by DOF sensor group 120, as described in ¶0034); and
obtain the target dynamic fusion track, based on at least one of a LiDAR track in the specific frame or the fusion track (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, with respect to the sensor groups that include roof lidar 132, as described in ¶0034; ¶0059-0070, with respect to the first phenomenon of Figure 7, regarding that the roof lidar-only track FT2 is deleted when first track deletion condition C_11 is satisfied, which requires deletion variable C to be met, i.e. FT2 is a combined roof lidar-only track, where roof lidar-only track FT2 is a track generated by only roof lidar 132, as opposed to fusion track F1 generated by DOF unit 131, as described in ¶0055).
Claims 4 and 15
Yun has not been applied to the optional alternative limitation of “a radar track, in the previous frame, obtained via the radar” of claim 1; therefore, prior art is not required to be applied to teach limitations that further limit the “radar track,” including the instructions, when executed by the one or more processors, cause the vehicle control apparatus to delete a second target dynamic fusion track by:
deleting the second target dynamic fusion track, based on the second target dynamic fusion track being obtained only via the radar track in the specified time, and based on at least one of:
a position of the second target dynamic fusion track being included in a specified area with respect to the vehicle,
the second target dynamic fusion track being obtained based on only the fusion track obtained in the specific frame,
the second target dynamic fusion track in the previous frame, corresponding to the second target dynamic fusion track, being obtained via the LiDAR and corresponding to the target object, or
a third dynamic fusion track different from the second target dynamic fusion track being obtained via the LiDAR track in the specific frame.
See the rejection of claims 4 and 15 under 35 U.S.C. 112(b) regarding issues with this limitation.
Claims 5 and 16
Yun has not been applied to the optional alternative limitation of “a radar track, in the previous frame, obtained via the radar” of claim 1; therefore, prior art is not required to be applied to teach limitations that further limit the “radar track,” including the instructions, when executed by the one or more processors, cause the vehicle control apparatus to delete a second target dynamic fusion track by:
deleting the second target dynamic fusion track, based on the second target dynamic fusion track being obtained only via the radar track in the specific frame, and based on at least one of:
a position of the second target dynamic fusion track being included in a specified area with respect to the vehicle,
the second target dynamic fusion track being obtained based on only the fusion track obtained in the specific frame,
the fusion track in the previous frame being obtained via the camera track,
a second fusion track different from the fusion track in the specific frame being obtained via the camera track,
a third fusion track different from the fusion track being obtained via the camera track in the specific frame, or
a third dynamic fusion track different from the second target dynamic fusion track being obtained via the camera track in the specific frame.
See the rejection of claims 5 and 16 under 35 U.S.C. 112(b) regarding issues with this limitation.
Claims 7 and 18
Due to the ambiguity discussed in the rejections of claims 7 and 18 under 35 U.S.C. 112(b), the scope of the limitations of claims 7 and 18 have been interpreted broadly for the purposes of the prior art rejection.
Yun further discloses that the instructions, when executed by the one or more processors, further cause the vehicle control apparatus to:
classify the target object corresponding to the deleted target dynamic fusion track as an object incapable of being in the movement state (see ¶0080-0089, with respect to the second phenomenon in Figure 10, regarding that roof lidar-only track FT2 is deleted upon being determined to be a stationary object).
Claim 8
Yun further discloses that each of the plurality of dynamic fusion tracks correspond to at least one of a pedestrian, an automobile, a two-wheeled vehicle, or a bicycle (see ¶0059-0065, regarding the fusion tracks as corresponding to vehicles, a pedestrian, bicycle, or powered two wheeler).
Claim 12
Yun discloses the claimed vehicle control method performed by one or more processors, as discussed in the rejection of claim 1.
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.
Claims 2 and 13 are rejected under 35 U.S.C. 103 as being unpatentable over Yun in view of an alternative embodiment of Yun, described in ¶0092-0106, with respect to Figure 11A-B.
Claims 2 and 13
Yun further discloses that the instructions, when executed by the one or more processors, cause the vehicle control apparatus to delete the target dynamic fusion track by:
deleting the target dynamic fusion track, based on the target dynamic fusion track being obtained via the LiDAR only in the specific frame (see ¶0043-0045, with respect to Figure 4, regarding track mergence 430 deletes a corresponding track among a plurality of received tracks based on the track deletion conditions, as further described in ¶0049-0051, with respect to Figure 5; ¶0059-0070, with respect to the first phenomenon of Figure 7, regarding that the roof lidar-only track FT2 is deleted when first track deletion condition C_11 is satisfied, which requires deletion variable C to be met, i.e. FT2 is a combined roof lidar-only track, where roof lidar-only track FT2 is a track generated by only roof lidar 132, as opposed to fusion track F1 generated by DOF unit 131, as described in ¶0055).
While Yun discloses that deletion of the fusion track F2 is further based on the object type of fusion track F1 being an automobile (see ¶0060-0070), Yun does not disclose that the deletion of the fusion track F2 is further based on the object type of the target dynamic fusion track being an automobile.
However, Yun discloses an alternative embodiment in which a deleted roof lidar-only track F2 (similar to the target dynamic fusion track of Yun) is defined as being an automobile (see ¶0092-0106, with respect to Figure 11A-B). As described in ¶0055, Yun teaches the roof lidar-only track FT2 as generated by roof lidar 132, as opposed to fusion track FT1 that’s generated by the DOF unit 131; therefore, the deleted roof lidar-only track F2 is inherently based on being obtained via the LiDAR only in the specific frame. The “object type” and “LiDAR only” condition are merely used as a basis to delete the “target dynamic fusion track,” without claiming any specific method for determining them.
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 step of delete the target dynamic fusion of Yun to be further based on the object type of the target dynamic fusion track being an automobile, in light of the alternative embodiment described in ¶0092-0106, with respect to Figure 11A-B of Yun, with the predictable result of deleting sensor fusion tracks that obstruct normal autonomous driving control (¶0039 of Yun) that include the situation in which two overlapping tracks represent the same vehicle rather than different vehicles (¶0092-0093 of Yun).
Claims 9-11 and 20 are rejected under 35 U.S.C. 103 as being unpatentable over Yun in view of Official Notice.
Claims 9 and 20
Yun further discloses a near vehicle detector (NVD) camera, different from the camera, configured to capture one of a front of the vehicle or a rear of the vehicle (see ¶0034, with respect to Figure 1, regarding front camera 112, surround view monitor 123, surround object detection camera 133). Any one of the plurality of cameras described in Yun may reasonably pertain to a “different” camera in combination. Further, any one of the cameras of Yun may reasonably pertain to “near vehicle detection,” due to the absence of limitations pertaining to particular range of field of view.
Yun further discloses a rear side view (RSIR) camera, different from the camera (see ¶0034, with respect to Figure 1, regarding rear side camera 124) and does not explicitly disclose that rear side camera 124 is configured to capture a rear corner of the vehicle. However, it would be capable of instant and unquestionable demonstration to modify the placement of rear side camera 124 of Yun to capture a rear corner of the vehicle, given that no subsequent limitations require vehicle corner-related data, thus providing the predictable result of capturing data at particular locations associated with a vehicle, where the benefits of an improved design are well-known. See MPEP 2143(I)(F), Examples 1-4.
Yun further discloses that the instructions, when executed by the one or more processors, further cause the vehicle control apparatus to obtain the plurality of dynamic fusion tracks by:
obtaining the plurality of dynamic fusion tracks via at least one of the LiDAR, the camera, the radar, the NVD camera, or the RSIR camera (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, where fusions tracks may pertain to different objects, as described in ¶0093, with respect to the sensor groups that include roof lidar 132, front camera 112, surround view monitor 123, rear side camera 124, surround object detection camera 133, as described in ¶0034).
Only one of the LiDAR, camera, radar, NVD camera, or RSIR camera is required to be taught by prior art.
Claim 10
Yun has not been applied to the optional alternative limitation of “whether an error has occurred in the radar and the camera in the specific frame” of claim 1; therefore, prior art is not required to be applied to teach the limitations that further limit “the error,” including the instructions, when executed by the one or more processors, further cause the vehicle control apparatus to delete the target dynamic fusion track by: deleting the target dynamic fusion track based on the error not having occurred in the radar, the camera, the NVD camera, and the RSIR camera.
See the rejection of claim 10 under 35 U.S.C. 112(b) regarding issues with this limitation.
Claim 11
Yun further discloses that the instructions, when executed by the one or more processors, cause the vehicle control apparatus to obtain the plurality of dynamic fusion tracks by:
obtaining, via the NVD camera, an NVD track corresponding to the target object (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, with respect to the sensor groups that include front camera 112, surround view monitor 123, surround object detection camera 133, as described in ¶0034, with respect to Figure 1);
obtaining, via the RSIR camera, an RSIR track corresponding to the target object (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, with respect to the sensor groups that include rear side camera 124, as described in ¶0034, with respect to Figure 1).
Yun further teaches obtaining a fusion track, based on at least one of the NVD track, or the RSIR track (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, where fusion track FT1 is generated by DOF unit 131 that collects information from front camera 112, surround view monitor 123, and rear side camera 124, and surround object detection camera 133, as described in ¶0034, with respect to Figure 1). Yun has not been applied to the optional alternative limitations associated with the “camera track” and “radar track” in claim 1.
Yun further discloses obtaining the plurality of dynamic fusion tracks based on at least one of the fusion track or LiDAR track in the specific frame (see ¶0055, regarding fusion track FT1 indicates a fusion track generated by the DOF unit 131, and fusion track FT2 indicates a roof lidar-only track generated by roof lidar 132).
Claim 21 is rejected under 35 U.S.C. 103 as being unpatentable over Yun in view of Levinson et al. (US 2017/0123428 A1), hereinafter Levinson.
Claim 21
Yun further discloses that the object type of the target dynamic fusion track indicates a physical object type of the target object corresponding to the target dynamic fusion track (see ¶0060-0070, regarding that satisfying first track deletion condition C_11 further requires deletion variable E to be met, i.e. FT2 does not correspond to a pedestrian, a person riding a bicycle, and a powered two wheeler, and one of deletion variables A or B, i.e. FT1 corresponds to a commercial vehicle or a passenger vehicle).
Yun does not further disclose that the instructions, when executed by the one or more processors, further cause the vehicle control apparatus to maintain a second target dynamic fusion track in a second specific frame based on the second target dynamic fusion track being obtained via only the LiDAR among the LiDAR, the camera, and the radar and further based on an error having occurred in at least one of the radar or the camera in the second specific frame. However, the “second target dynamic fusion track” is not influenced by the target dynamic fusion track; therefore, it would be reasonable to incorporate the known technique of not considering sensor data associated with errors, in light of Levinson.
Specifically, Levinson teaches AV system 3602 (similar to the vehicle control apparatus of Yun) that maintain[s] a second target dynamic in a second specific frame based on the second dynamic fusion track being obtained via only LIDAR sensors 3604 (similar to the LiDAR among the LiDAR, the camera, and the radar of Yun) and further based on an error having occurred in at least one of RADAR sensors 3708 (similar to the radar of Yun) or cameras 3710 (similar to the camera of Yun) in the second specific frame (see ¶0106, with respect to Figure 23, regarding object tracker 2330 performs frame-to-frame estimation of motion based on lidar data 2372, camera data 2374, and radar data 2376, where an indication of a failure of RADAR sensors 3708 and cameras 3710 may be received, as described in ¶0147-0148, and alternative sensors are relied upon to cover for the sensor anomaly, as described in the abstract; ¶0146, regarding the example in which LIDAR sensor 3604A is relied upon for generating a field of perception until failed sensor 3604b becomes operational again).
Since the systems of Yun and Levinson are directed to the same purpose, i.e. tracking objects using a combination of LIDAR, camera, and radar data, 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 vehicle control apparatus of Yun to maintain a second target dynamic fusion track in a second specific frame based on the second target dynamic fusion track being obtained via only the LiDAR among the LiDAR, the camera, and the radar and further based on an error having occurred in at least one of the radar or the camera in the second specific frame, in light of Levinson, with the predictable result of relying upon alternative sensors to cover for sensor anomaly (see abstract) that affect the safety and operational efficiency of an autonomous vehicle (¶0144 of Levinson).
Claim 22 is rejected under 35 U.S.C. 103 as being unpatentable over Yun in view of Zeng (US 2013/0242284 A1), hereinafter Zeng.
Claim 22
Due to the ambiguity discussed in the rejection of claim 22 under 35 U.S.C. 112(b), the scope of the limitations of claim 22 has been interpreted broadly for the purposes of the prior art rejection.
Yun discloses the claimed vehicle control apparatus (see Figure 2, depicting sensor fusion system 200, described as used to support autonomous driving control of a vehicle in ¶0039) comprising:
a light detection and ranging device (LiDAR) (i.e. roof lidar 132, described in ¶0034, with respect to Figure 1);
a camera (i.e. front camera 112 and rear camera 124, described in ¶0034, with respect to Figure 1);
a radar (i.e. front radar 111 and rear/front side radars 113, as described in ¶0034, with respect to Figure 1);
one or more processors (see ¶0032, regarding the units/modules/blocks are implemented as software or hardware, e.g., processor); and
memory storing instructions (see ¶0128, regarding that the method is implemented as computer readable code in a computer readable recording medium in which programs are recorded, e.g., hard disk drive) that, when executed by the one or more processors, cause the vehicle control apparatus to:
obtain, via at least one of the LiDAR, the camera, or the radar, a plurality of dynamic fusion tracks in a specific frame, the plurality of dynamic fusion tracks corresponding to a plurality of external objects (see ¶0038-0039, regarding that track management module 230 generates a plurality of sensor fusion tracks with respect to one target object, where fusions tracks may pertain to different objects, as described in ¶0093, with respect to the sensor groups that include roof lidar 132, as described in ¶0034) classified into objects capable of being in a movement state (see ¶0059-0065, regarding that fusion tracks correspond to object types, e.g., commercial vehicle, passenger vehicle, pedestrian, bicycle, and powered two wheeler).
The limitation of “dynamic fusion tracks” requires only one sensor (i.e. LiDAR, camera, or radar); therefore, the term “fusion” imparts no patentable weight.
Yun further discloses that vehicle control apparatus is caused to determine whether to delete, among the plurality of dynamic fusion tracks, a target dynamic fusion track (e.g., roof lidar-only track FT2) corresponding to a target object among the plurality of external objects in the specific frame, based on the target dynamic fusion track being obtained via only the LiDAR among the LiDAR, the camera, and the radar (see ¶0043-0045, with respect to Figure 4, regarding track mergence 430 deletes a corresponding track among a plurality of received tracks based on the track deletion conditions, as further described in ¶0049-0051, with respect to Figure 5; ¶0059-0070, with respect to the first phenomenon of Figure 7, regarding that the roof lidar-only track FT2 is deleted when first track deletion condition C_11 is satisfied, which requires deletion variable C to be met, i.e. FT2 is a combined roof lidar-only track, where roof lidar-only track FT2 is a track generated by only roof lidar 132, as opposed to fusion track F1 generated by DOF unit 131, as described in ¶0055).
Yun does not further disclose that the “determine” step is further based on at least one of:
a camera track, in a previous frame, obtained via the camera within a specified time before the specific frame, or
a radar track, in the previous frame, obtained via the radar.
However, the technique of determining whether to delete LIDAR sensor data based on camera and/or radar sensor data received in a previous frame would be obvious to incorporate into Yun, in light of Zeng.
Specifically, Zeng teaches deleting dying objects, defined as an object that matches segmented cluster S from LiDAR sensor 166 in ¶0148 (similar to the target dynamic fusion track of Yun) based on at least one of a camera track, in a previous frame, obtained via vision system 174 (similar to the camera of Yun) or a radar track, in the previous frame, obtained via radar sensor 170 (similar to the radar of Yun) (see ¶0121-0122, regarding that dying objects in an object file are deleted before providing tracking model updating, where the object files are generated at each time step and provide position, velocity, and heading of the objects that are detected and tracked, as described in ¶0102; ¶0148, regarding that if there is no match to a target from the radar sensor 170 or the vision system 174 in several consecutive time steps, the object will be removed from the object file). Due to the requirement to observe several consecutive time steps prior to deletion in ¶0148, a determination on whether to delete the object file associated with a segmented cluster from a LiDAR sensor may be reasonably based on a radar track or camera track in a previous frame, under the broadest reasonable interpretation of the claim language.
Since the systems of Yun and Zeng are directed to the same purpose, i.e. deleting object tracks acquired from a combination of a LIDAR, camera, and radar, 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 “determine” step of Yun to be further based on at least one of a camera track, in a previous frame, obtained via the camera within a specified time before the specific frame, or a radar track, in the previous frame, obtained via the radar, in light of Zeng, with the predictable result of distinguishing an object from clutter background (¶0133 of Zeng) through the use of outputs from one or both of a radar sensor or a vision system on the vehicle to operate as a cueing signal, thus addressing the limitations pertaining to LiDAR sensors (¶0134 of Zheng).
Yun further discloses that vehicle control apparatus is caused to control the vehicle, based on at least one remaining dynamic fusion track of the plurality of dynamic fusion tracks in the specific frame (see ¶0077-0078, regarding that upon deletion of fusion track FT2, the situation is determined only based on the actual fusion track FT1, so as to not cause erroneous autonomous braking; ¶0129, regarding that a track to be deleted may be accurately deleted by generating track deletion conditions adaptively corresponding to various situations in which a host vehicle is placed, thereby being capable of prevent collision and erroneous braking of the host vehicle; ¶0039, regarding that the sensor fusion tracks are using in normal autonomous driving control of a vehicle).
Conclusion
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Specifically, Ma et al. (US 2023/0011829 A1) teaches discarding a ghost LiDAR object while image objects are categorized as persistent tracks (see ¶0057-0058), Portnoy et al. (US 2022/0414923 A1) teaches removing dynamic objects from multiple lidar scans before aggregating the point-cloud onto the camera image (see ¶0005), Kupershtein et al. (US 2024/0053438 A1) teaches removing ghost objects from the LIDAR measurement data (see ¶0134), where different types of sensors are used to generate the sensor signal output (see ¶0149), and Keilaf et al. (US 2025/0299441 A1) teaches determining a “ghost” detection by comparing the point cloud data of a LIDAR system and an ambient light image from a camera (see ¶0185).
Any inquiry concerning this communication or earlier communications from the examiner should be directed to Sara J Lewandroski whose telephone number is (571)270-7766. The examiner can normally be reached Monday-Friday, 9 am-5 pm ET.
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, Ramya P Burgess can be reached at (571)272-6011. 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.
/SARA J LEWANDROSKI/Examiner, Art Unit 3661
Prosecution Insights