DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Response to Amendments
Applicant’s amendment filed 07/17/2025 necessitated new grounds of rejection in this office action. Claims 1, 3, and 9-10 are amended and Claims 2, 5, and 7-8 are cancelled. Claims 1, 3-4, 6, and 9-10 are pending.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/07/2022, 08/17/2023, and 12/19/2024 were filed. The submission is in compliance with the provisions of 37 CFR 1.97. Accordingly, the information disclosure statement is being considered by the examiner.
Response to Arguments/Remarks
Applicant’s remarks, see Pg. 7-12 filed on 07/17/2025, with respect to the 35 U.S.C. § 103 Claim Rejections for Claims 1, 9-10 have been fully considered and examiner agrees Zeng and Adam do not teach all the limitations of amended claims.
In light of the claim amendments, prior arts Noda and Ogawa in combination with Zeng and Adam are used to reject Claims 1, 3-4, 6, and 9-10 under 35 U.S.C. 103.
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.
Claims 1, 3-4, 6, and 9-10 are rejected under 35 U.S.C. 103 as being unpatentable over Zeng (US 20130246020), hereinafter ‘Zeng’ in view of Adam et al. (US 20140324339), hereinafter ‘Adam’ in view of Noda et al. (US 20190213886), hereinafter Noda and further in view of Ogawa (US 20090040095), hereinafter ‘Ogawa’.
Regarding Claim 1, Zeng discloses processing circuitry configured to, during a current sampling interval of measurement sampling intervals of a LiDAR installed in a mobile entity (e.g., operations performed by a computer, a processor or other electronic calculating device that manipulate and/or transform data [0166]; receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time [Abstract]; FIG. 1 is an illustration of a host vehicle following a target vehicle and showing the fields-of-view of four LiDAR sensors on the host vehicle [0012]; be the mapped measurements in the LiDAR coordinate frame of a dynamic object [0153]),
extract a point cloud representing a mobile object present around the mobile entity from point cloud data obtained by measurements performed by the LiDAR in surroundings of the mobile entity during the current sampling interval (e.g., includes providing object files for objects detected by the LiDAR sensors. includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors (i.e., extract a point cloud representing a mobile object present around the mobile entity) at a current sample time and constructing a point cloud from the scan returns (i.e., from point cloud data obtained by measurements performed by the LiDAR in surroundings of the mobile entity during the current sampling interval). Creates new object models, deletes dying object models and updates the object files based on the object models for the current sample time [0010]),
extract, from the point cloud data obtained during the current sampling interval, a point cloud in a range of a posterior distribution determined in a preceding sampling interval for the mobile object (e.g., providing object files for objects detected by the sensors at a previous sample time, receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns (i.e., extract, from the point cloud data obtained during the current sampling interval), then segments the scan points in the point cloud into predicted clusters (i.e., a point cloud in a range of a posterior distribution), where each cluster initially identifies an object detected, matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time (i.e., determined in a preceding sampling interval for the mobile object) [Abstract]),
and perform matching of the extracted point cloud against the point cloud of the mobile object (e.g., predicted object model points and segmented scan map points for a step of matching scan clusters with predicted object models [0021]),
set a likelihood function for the mobile object in the current sampling interval based on the type of vehicle attributed to the mobile object (e.g., A probabilistic object model M is first defined, and then a proposed iterative algorithm is provided to find a rigid transformation such that the likelihood is maximized, given the scan maps of the subsequence frame. To characterize the geometric shape of an object, a contour probability density function (PDF) in sample space R2 is defined [0057]),
compute a predicted position of the mobile object for the next sampling interval based on the prior distribution (e.g., matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time [Abstract]),
wherein the posterior probability computed during the current sampling interval represents a probability distribution of the mobile object's position given the point cloud data obtained during the current sampling interval 1-(e.g., receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted clusters, where each cluster initially identifies an object [Abstract]; posterior PDF for transformation parameter at time t, and p(y/y.sub.t) is the conditional probability of the following plant model of the object motion [0086]; to derive the posterior PDF given LiDAR scan maps and target data [0155]).
Zeng does not explicitly disclose wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle, set the posterior distribution determined in the preceding sampling interval as a prior distribution for the mobile object in the current sampling interval, compute a predicted position of the mobile object for the next sampling interval based on the prior distribution and likelihood function set, and compute a posterior distribution for the mobile object during the current sampling interval using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval, wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval, and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval.
Adam discloses set the posterior distribution determined in the preceding sampling interval as a prior distribution for the mobile object in the current sampling interval (e.g., representing the measured track of a movable object. This is fed to the state update block and filtered by the Kalman filter produce the posterior state PDF 511 (i.e., set the posterior distribution determined in the preceding sampling interval) which is in turn fed to the state prediction block 509. The state prediction block 509 uses the system model, the state space, the noise space and the Kalman filter to update the prior state PDF 506 (i.e., as a prior distribution for the mobile object in the current sampling interval) [0041]),
compute a predicted position of the mobile object for the next sampling interval based on the prior distribution and likelihood function set (e.g., A measurement is made in the measurement prediction block 501 using a prior state PDF 506, The Bayes filter 502 uses the results of the measurement model 504 and the measurement space 504 to produce a likelihood integral PDF representing the measured track of a movable object. This is fed to the state update block 507 which is in turn fed to the state prediction block 509. The state prediction block 509 updates the prior state PDF 506, that is then fed to the measurement prediction block 501. The method can begin again [0041]),
and compute a posterior distribution for the mobile object during the current sampling interval using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval (e.g., A measurement is made in the measurement prediction block 501 using a prior state PDF, he results of the measurement model 504 and the measurement space 504 to produce a likelihood integral PDF representing the measured track of a movable object. This is fed to the state update block 507 and filtered by the Kalman filter 508 to produce the posterior state PDF 511 [0041]),
and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval (e.g., A measurement is made in the measurement prediction block using a prior state PDF, the measurement model and the measurement space (i.e., given the predicted position computed during the preceding sampling interval). The Bayes filter uses the results of the measurement model and the measurement space to produce a likelihood integral PDF representing the measured track of a movable object (i.e., the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval) [0041]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng with Adam to set the posterior distribution determined in the preceding sampling interval as a prior distribution for the mobile object in the current sampling interval, compute a predicted position of the mobile object for the next sampling interval based on the prior distribution and likelihood function set, and compute a posterior distribution for the mobile object during the current sampling interval using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval, and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval as this would give the advantage to not only consider the objects state's mean values, the position, heading and velocity of the object, but also the probability that the vehicle is actually located elsewhere and the probability that the object exists, (see Adam, [0014]).
Zeng and Adam do not explicitly disclose wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle, and wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval.
Noda discloses wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle (e.g., the object detector estimates the position and attitude of each three-dimensional object from a shape of a group of points (i.e., a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object) belonging to the three-dimensional object. Moreover, the object detector estimates what the object is from the shape and movement history of each three-dimensional object, and gives the detected object an object classification (a vehicle, a pedestrian, a bicycle, and the like) (i.e., said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle) [0050]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng and Adam with Noda for a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle as this would give the advantage to determine what the object is from the shape and movement history of each three-dimensional object, and gives the detected object an object classification, (see Noda, [0050]).
Zeng, Adam and Noda do not explicitly disclose wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval.
Ogawa discloses wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval (e.g., the CPU 25a acquires a prediction value showing the state of the vehicle, which is calculated at step S1800, all of which are used in the next execution cycle [0109]; the CPU 25a executes a determination where it is determined whether or not the posterior probability P0(1 side) is a maximum among the group of posterior probabilities [0136]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng, Adam and Noda with Ogawa for the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval as this would give the advantage to select a most-probable graphic pattern which typically represents the contour (i.e., attribute) of the vehicle located ahead, (see Ogawa, [0137]).
Regarding Claim 3, Zeng, Adam, Noda, and Ogawa disclose the limitations as discussed above in Claim 1.
Zeng further discloses as part of the likelihood function for the mobile object for the current sampling interval, the processing circuitry determines a direction of movement of the mobile object (e.g., a point set registration algorithm to find the transformation T that matches two frames temporally between the current scan map S (i.e., current sampling interval) and the object model M derived from the past scan maps. A probabilistic object model M is first defined, and then a proposed iterative algorithm is provided to find a rigid transformation such that the likelihood is maximized, given the scan maps of the subsequence frame. The current scan map that consists of a list of scan points sk. The likelihood function is expressed by Eq. 30 (i.e., as part of the likelihood function for the mobile object for the current sampling interval) [0056-0060]; as the sensors 16, 20, 24 and 28 track the same object that object is processed (i.e., processing circuitry) as a single target, where the algorithm outputs the position, orientation and velocity of each tracked object (i.e., determines a direction of movement of the mobile object) [0038]; the object model M defines the relative longitudinal speed Vx, the relative lateral speed Vy, the lateral displacement y, and the target vehicle heading .xi., or direction of the target's ground speed vector (i.e., determines a direction of movement of the mobile object) [0039]).
Zeng does not explicitly disclose to set the prior distribution and the likelihood function for the mobile object based on the direction of movement of the mobile object.
Adam discloses sets the prior distribution and the likelihood function for the mobile object based on the direction of movement of the mobile object (e.g., A measurement is made in the measurement prediction block 501 using a prior state PDF (i.e., set a prior distribution) 506, the measurement model 504 and the measurement space (i.e., based on the direction of movement) 505. The Bayes filter 502 uses the results of the measurement model 504 and the measurement space 504 to produce a likelihood integral PDF representing the measured track of a movable object (i.e., the likelihood function for the mobile object based on the direction of movement of the mobile object) [0041]; The state space x represents the state of a tracked object. For example, when an object is tracked, the position, heading (i.e., direction of movement of the mobile object) and velocity of the object are often of interest and therefore used as state space [0043]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng with Adam, Noda, and Ogawa to set the prior distribution and the likelihood function for the mobile object based on the direction of movement of the mobile object as this would give the advantage in determining objects in future measurements, (see Adam, [0013]).
Regarding Claim 4 and 6, Zeng, Adam, Noda, and Ogawa disclose the limitations as discussed above in Claim 1 and 3.
Zeng, Adam and Noda do not explicitly disclose the processing circuitry uses an approximate estimation scheme in determining an approximation of a posterior probability in posterior probability maximization.
Ogawa discloses the processing circuitry uses an approximate estimation scheme in determining an approximation of a posterior probability in posterior probability maximization (e.g., On completion of this posterior probability calculating process at step S1600 in FIG. 2, the CPU (i.e., processing circuitry) 25a proceeds to a selection process (step S1700 in FIG. 2), which is detailed in FIG. 14. This selection process is executed repeatedly by the CPU 25a at given execution intervals given to the vehicle-state estimating process (i.e., uses an approximate estimation scheme) [0133]; when it is determined at least one of the four conditions is met (YES at step S1710), the CPU 25a executes a determination where it is determined whether or not the posterior probability (i.e., in determining an approximation of a posterior probability) P.sub.0(1 side) is a maximum among the group of posterior probabilities (i.e., in posterior probability maximization) [0136]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng, Adam, and Noda with Ogawa for the processing circuitry uses an approximate estimation scheme in determining an approximation of a posterior probability in posterior probability maximization as this would give the advantage to select a most-probable graphic pattern which typically represents the contour (i.e., attribute) of the vehicle located ahead, (see Ogawa, [0137]).
Regarding Claim 9,
Zeng discloses during a current sampling interval of measurement sampling intervals of a LiDAR installed in a mobile entity (e.g., receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time [Abstract]; FIG. 1 is an illustration of a host vehicle following a target vehicle and showing the fields-of-view of four LiDAR sensors on the host vehicle [0012]; be the mapped measurements in the LiDAR coordinate frame of a dynamic object [0153]),
extracting, a point cloud representing a mobile object present around the mobile entity from point cloud data obtained by measurements performed by the LiDAR in surroundings of the mobile entity during the current sampling interval (e.g., includes providing object files for objects detected by the LiDAR sensors. includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors (i.e., extract a point cloud representing a mobile object present around the mobile entity) at a current sample time and constructing a point cloud from the scan returns (i.e., from point cloud data obtained by measurements performed by the LiDAR in surroundings of the mobile entity during the current sampling interval) . Creates new object models, deletes dying object models and updates the object files based on the object models for the current sample time [0010]),
extracting, from the point cloud data obtained during the current sampling interval, a point cloud in a range of a posterior distribution determined in a preceding sampling interval for the mobile object (e.g., providing object files for objects detected by the sensors at a previous sample time, receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns (i.e., extract, from the point cloud data obtained during the current sampling interval), then segments the scan points in the point cloud into predicted clusters (i.e., a point cloud in a range of a posterior distribution), where each cluster initially identifies an object detected, matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time (i.e., determined in a preceding sampling interval for the mobile object) [Abstract]),
and perform matching of the extracted point cloud against the point cloud of the mobile object (e.g., predicted object model points and segmented scan map points for a step of matching scan clusters with predicted object models [0021]),
set a likelihood function for the mobile object in the current sampling interval based on the type of vehicle attributed to the mobile object (e.g., A probabilistic object model M is first defined, and then a proposed iterative algorithm is provided to find a rigid transformation such that the likelihood is maximized, given the scan maps of the subsequence frame. To characterize the geometric shape of an object, a contour probability density function (PDF) in sample space R2 is defined [0057]),
compute a predicted position of the mobile object for the next sampling interval based on the prior distribution (e.g., matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time [Abstract]),
wherein the posterior probability computed during the current sampling interval represents a probability distribution of the mobile object's position given the point cloud data obtained during the current sampling interval 1-(e.g., receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted clusters, where each cluster initially identifies an object [Abstract]; posterior PDF for transformation parameter at time t, and p(y/y.sub.t) is the conditional probability of the following plant model of the object motion [0086]; to derive the posterior PDF given LiDAR scan maps and target data [0155]).
Zeng does not explicitly disclose wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle, setting the posterior distribution determined in the preceding sampling interval as a prior distribution, computing a predicted position of the mobile object for the next sampling interval based on the prior distribution and likelihood function set, and computing a posterior distribution for the mobile object using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval, wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval, and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval.
Adam discloses setting the posterior distribution determined in the preceding sampling interval as a prior distribution (e.g., representing the measured track of a movable object. This is fed to the state update block and filtered by the Kalman filter produce the posterior state PDF 511 (i.e., setting the posterior distribution determined in the preceding sampling interval) which is in turn fed to the state prediction block 509. The state prediction block 509 uses the system model, the state space, the noise space and the Kalman filter to update the prior state PDF 506 (i.e., as a prior distribution) [0041]),
computing a predicted position of the mobile object for the next sampling interval based on the prior distribution and likelihood function set (e.g., A measurement is made in the measurement prediction block 501 using a prior state PDF 506, The Bayes filter 502 uses the results of the measurement model 504 and the measurement space 504 to produce a likelihood integral PDF representing the measured track of a movable object. This is fed to the state update block 507 which is in turn fed to the state prediction block 509. The state prediction block 509 updates the prior state PDF 506, that is then fed to the measurement prediction block 501. The method can begin again [0041]),
and computing a posterior distribution for the mobile object using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval (e.g., A measurement is made in the measurement prediction block 501 using a prior state PDF, he results of the measurement model 504 and the measurement space 504 to produce a likelihood integral PDF representing the measured track of a movable object. This is fed to the state update block 507 and filtered by the Kalman filter 508 to produce the posterior state PDF 511 [0041]),
and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval (e.g., A measurement is made in the measurement prediction block using a prior state PDF, the measurement model and the measurement space (i.e., given the predicted position computed during the preceding sampling interval). The Bayes filter uses the results of the measurement model and the measurement space to produce a likelihood integral PDF representing the measured track of a movable object (i.e., the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval) [0041]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng with Adam for setting the posterior distribution determined in the preceding sampling interval as a prior distribution, computing a predicted position of the mobile object for the next sampling interval based on the prior distribution and likelihood function set, and computing a posterior distribution for the mobile object using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval, and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval as this would give the advantage to not only consider the objects state's mean values, the position, heading and velocity of the object, but also the probability that the vehicle is actually located elsewhere and the probability that the object exists, (see Adam, [0014]).
Zeng and Adam do not explicitly disclose wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle, and wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval.
Noda discloses wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle (e.g., the object detector estimates the position and attitude of each three-dimensional object from a shape of a group of points (i.e., a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object) belonging to the three-dimensional object. Moreover, the object detector estimates what the object is from the shape and movement history of each three-dimensional object, and gives the detected object an object classification (a vehicle, a pedestrian, a bicycle, and the like) (i.e., said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle) [0050]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng and Adam with Noda for a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle as this would give the advantage to determine what the object is from the shape and movement history of each three-dimensional object, and gives the detected object an object classification, (see Noda, [0050]).
Zeng, Adam and Noda do not explicitly disclose wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval.
Ogawa discloses wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval (e.g., the CPU 25a acquires a prediction value showing the state of the vehicle, which is calculated at step S1800, all of which are used in the next execution cycle [0109]; the CPU 25a executes a determination where it is determined whether or not the posterior probability P0(1 side) is a maximum among the group of posterior probabilities [0136]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng, Adam and Noda with Ogawa for the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval as this would give the advantage to select a most-probable graphic pattern which typically represents the contour (i.e., attribute) of the vehicle located ahead, (see Ogawa, [0137]).
Regarding Claim 10,
Zeng discloses a non-transitory computer-readable medium recorded with a predictive tracking program that causes a computer to execute (e.g., Those computers and electronic devices may employ various volatile and/or non-volatile memories including non-transitory computer-readable medium with an executable program stored thereon including various code or executable instructions able to be performed by the computer or processor, where the memory and/or computer-readable medium may include all forms and types of memory and other computer-readable media [0166]),
during a current sampling interval of measurement sampling intervals of a LiDAR installed in a mobile entity (e.g., receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time [Abstract]; FIG. 1 is an illustration of a host vehicle following a target vehicle and showing the fields-of-view of four LiDAR sensors on the host vehicle [0012]; be the mapped measurements in the LiDAR coordinate frame of a dynamic object [0153]),
a mobile object detection process of extracting a point cloud representing the mobile object present around a mobile entity from point cloud data obtained by measurements performed by the LiDAR in surroundings of the mobile entity during the current sampling interval (e.g., The method includes providing object files for objects detected by the LiDAR sensors (i.e. a mobile object detection process). The method also includes receiving a plurality of scan returns from objects detected in the field-of-view of the sensors (i.e., extracting a point cloud representing a mobile object present around the mobile entity) at a current sample time and constructing a point cloud from the scan returns(i.e., from point cloud data obtained by measurements performed by the LiDAR in surroundings of the mobile entity during the current sampling interval). Creates new object models, deletes dying object models and updates the object files based on the object models for the current sample time [0010]),
a mobile object tracking process of extracting, from the point cloud data obtained during the current sampling interval, a point cloud in a range of a posterior distribution determined in a preceding sampling interval for the mobile object (e.g., providing object files for objects detected by the sensors at a previous sample time, receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns (i.e., a mobile object tracking process of extracting, from the point cloud data obtained during the current sampling interval), then segments the scan points in the point cloud into predicted clusters (i.e., a point cloud in a range of a posterior distribution), where each cluster initially identifies an object detected, matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time (i.e., determined in a preceding sampling interval for the mobile object) [Abstract]),
and performing matching of the extracted point cloud against the point cloud of the mobile object (e.g., predicted object model points and segmented scan map points for a step of matching scan clusters with predicted object models [0021]),
setting a likelihood function for the mobile object in the current sampling interval based on the type of vehicle attributed to the mobile object (e.g., A probabilistic object model M is first defined, and then a proposed iterative algorithm is provided to find a rigid transformation such that the likelihood is maximized, given the scan maps of the subsequence frame. To characterize the geometric shape of an object, a contour probability density function (PDF) in sample space R2 is defined [0057]),
computing a predicted position of the mobile object for the next sampling interval (e.g., matches the predicted clusters with predicted object models generated from objects being tracked during the previous sample time [Abstract]),
wherein the posterior probability computed during the current sampling interval represents a probability distribution of the mobile object's position given the point cloud data obtained during the current sampling interval 1-(e.g., receiving a plurality of scan returns from objects detected in the field-of-view of the sensors at a current sample time and constructing a point cloud from the scan returns. The method then segments the scan points in the point cloud into predicted clusters, where each cluster initially identifies an object [Abstract]; posterior PDF for transformation parameter at time t, and p(y/y.sub.t) is the conditional probability of the following plant model of the object motion [0086]; to derive the posterior PDF given LiDAR scan maps and target data [0155]).
Zeng does not explicitly disclose wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle, setting the posterior distribution determined in the preceding sampling interval as a prior distribution, and computing a posterior distribution for the mobile object using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function that are determined for the mobile object during the current sampling interval, wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval, and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval.
Adam discloses setting the posterior distribution determined in the preceding sampling interval as a prior distribution (e.g., representing the measured track of a movable object. This is fed to the state update block and filtered by the Kalman filter produce the posterior state PDF 511 (i.e., setting the posterior distribution determined in the preceding sampling interval) which is in turn fed to the state prediction block 509. The state prediction block 509 uses the system model, the state space, the noise space and the Kalman filter to update the prior state PDF 506 (i.e., as a prior distribution) [0041]),
and computing a posterior distribution for the mobile object using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval (e.g., A measurement is made in the measurement prediction block 501 using a prior state PDF, he results of the measurement model 504 and the measurement space 504 to produce a likelihood integral PDF representing the measured track of a movable object. This is fed to the state update block 507 and filtered by the Kalman filter 508 to produce the posterior state PDF 511 [0041]),
and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval (e.g., A measurement is made in the measurement prediction block using a prior state PDF, the measurement model and the measurement space (i.e., given the predicted position computed during the preceding sampling interval). The Bayes filter uses the results of the measurement model and the measurement space to produce a likelihood integral PDF representing the measured track of a movable object (i.e., the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval) [0041]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng with Adam for setting the posterior distribution determined in the preceding sampling interval as a prior distribution, and computing a posterior distribution for the mobile object using the predicted position of the mobile object for the next sampling interval and the prior distribution and the likelihood function determined for the mobile object during the current sampling interval, and wherein the likelihood function represents the probability associated with the point cloud data obtained during the current sampling interval given the predicted position computed during the preceding sampling interval as this would give the advantage to not only consider the objects state's mean values, the position, heading and velocity of the object, but also the probability that the vehicle is actually located elsewhere and the probability that the object exists, (see Adam, [0014]).
Zeng and Adam do not explicitly disclose wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle, and wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval.
Noda discloses wherein a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle (e.g., the object detector estimates the position and attitude of each three-dimensional object from a shape of a group of points (i.e., a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object) belonging to the three-dimensional object. Moreover, the object detector estimates what the object is from the shape and movement history of each three-dimensional object, and gives the detected object an object classification (a vehicle, a pedestrian, a bicycle, and the like) (i.e., said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle) [0050]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng and Adam with Noda for a type of vehicle is attributed to the mobile object based on the point cloud of the mobile object, said type of vehicle being chosen from among a car, a truck, a motorcycle, and a bicycle as this would give the advantage to determine what the object is from the shape and movement history of each three-dimensional object, and gives the detected object an object classification, (see Noda, [0050]).
Zeng, Adam and Noda do not explicitly disclose wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval.
Ogawa discloses wherein the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval (e.g., the CPU 25a acquires a prediction value showing the state of the vehicle, which is calculated at step S1800, all of which are used in the next execution cycle [0109]; the CPU 25a executes a determination where it is determined whether or not the posterior probability P0(1 side) is a maximum among the group of posterior probabilities [0136]).
It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify Zeng, Adam and Noda with Ogawa for the predicted position of the mobile object for the next sampling interval is computed by the processing circuitry during the current sampling interval so as to maximize the posterior distribution computed during the current sampling interval as this would give the advantage to select a most-probable graphic pattern which typically represents the contour (i.e., attribute) of the vehicle located ahead, (see Ogawa, [0137]).
Conclusion
Applicant's amendment necessitated the new ground(s) of rejection presented in this Office action. Accordingly, THIS ACTION IS MADE FINAL. See MPEP § 706.07(a). 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 nonprovisional extension fee (37 CFR 1.17(a)) 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 Agustin R Campozano whose telephone number is
(571)- 272-0256. The examiner can normally be reached Mon-Fri 8-5 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, Catherine T. Rastovski can be reached on (571) 270-0349. 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.
/Agustin R Campozano/Examiner, Art Unit 2863
/Catherine T. Rastovski/Supervisory Primary Examiner, Art Unit 2863