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 .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 07/07/2026 has been entered.
Status of Claims
Claims 1-20 of U.S. Application No. 18/506352 filed on 06/08/2026 have been examined.
Office Action is in response to the Applicant's amendments and remarks filed06/08/2026. Claims 1-4, 6, 10-15, & 17 are presently amended. Claims 1-20 are presently pending and are presented for examination.
Response to Arguments
In regards to the previous rejection under 35 U.S.C. § 103: Applicant’s arguments with respect to the independent claim(s) 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. A new grounds of rejection is made in view of US 2023/0080193A1 (“Depeweg”).
Claim Rejections - 35 USC § 103
In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis (i.e., changing from AIA to pre-AIA ) for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
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.
Claim(s) 1, 6, 10, 12, & 17 is/are rejected under 35 U.S.C. 103 as being unpatentable over US 2022/0068123A1 (“Guo”), in view of US 2023/0080193A1 (“Depeweg”).
As per claim 1 Guo discloses
An estimation system (see at least Guo, para. [0023]), comprising:
a memory storing instructions that, when executed by a processor (see at least Guo, para. [0023]: The traffic system 200 is shown as including a processor 205. In one embodiment, the traffic system 200 includes a memory 210 that stores an aggregation module 220 and a graphing module 230.), cause the processor to:
form multi-channel data from partial data and timing data about traffic on a road, and a vehicle and road sensors capture and output the multi-channel data, the partial data is acquired from the road sensors (see at least Guo, para. [0027-0028]: Thus, in one embodiment, the data store 240 stores data used by the modules220 and 230 in executing various functions. In one embodiment, the data store 240 includes the sensor data 250 along with, for example, metadata that characterize various aspects of the sensor data 250. For example, the metadata can include location coordinates (e.g., longitude and latitude), relative map coordinates or tile identifiers, time/date stamps from when the separate sensor data 250 was generated, and so on….In one embodiment, the data store 240 may also include the graph structure 260, the completion target 270, and the graph model 280. The traffic system 200 may generate the graph structure 260 according to aggregating structured sensor and perception data from information sources to a server. A graph structure 260 may be a graph that illustrates traffic intersections and vehicle flows in a geographic area. & para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with a k-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on. & para. [0056]);
generate an adjacency matrix from the partial data and geometry about the road (see at least Guo, para. [0043]: The neural network model 510 may use matrices G, A, and E to form a clean and complete graph model of the traffic flows associated with a road network. The neural network model 510 may use a graph structure denoted as a matrix G with the dimensions N×k. The variable N may be the total number of vertices and k the feature vector associated with each vertex. The variable k-dimension may represent reported traffic information from SRVs such as speed, flow rates, density, and so on. A connection relation, such as between vertices, may be represented by an adjacent matrix A with the dimension N×N.); and
train a graph model using temporal patterns for the different graph nodes from the multi-channel data and the adjacency matrix to complete the partial data, output a traffic pattern (see at least Guo, para. [0038]: The server 310 may also aggregate, collect, or synchronize data from fixed RSUs, traffic cameras, vehicle counters, roadside sensors, and so on. In one approach, the server 310 maybe a cloud server that processes perception or traffic data using a neural network model to graph, complete, auto-complete, clean, or correct the data for a road network. para. [0048]: In one approach, a traffic system may train the neural network model 510 using a completed, cleaned, or corrected ground-truth G, such as for supervised learning. A module may train the neural network model 510 using perception data. By minimizing the error |Ġ-Ĝ| and back-propagating the derivate, the parameterized encoder-decoder network updates their weights to reach a stable point. The neural network model 510 may use the learned parameters or weights for mapping the data to filter out noise values and fill-in or correct missing values to structure, complete, or clean graphed perception data. In this way, the neural network model 510 may generate the reconstruction matrix Ĝ with satisfactory confidence levels for the completed and cleaned data values when inferred with the noisy and incomplete matrix G.),
and execute an automated task by the vehicle (see at least Guo, para. [0024]: The traffic system 200 may use the perception data to complete a graph model of the traffic flows and communicate the graph model to the vehicle100, thereby improving traffic, congestion, navigation, automated driving maneuvers, automated motion plans, and so on. & para. [0055-0057]).
However Guo does not explicitly disclose
form multi-channel data from partial data and signal phase and timing data (SP AT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes;
train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data.
Depeweg teaches
form multi-channel data from partial data and signal phase and timing data (SPAT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes (see at least Depeweg, para. [0021]: FIG. 1 shows, by way of example, a schematic illustration of an intersection KR having a traffic signaling system which comprises a plurality of traffic lights S1, ..., S4 as traffic signal generators. In this case, traffic lights controlled in phase each form a signal group. In the present exemplary embodiment, S1 and S3 form a first signal group and S2 and S4 form a second signal group. The traffic signal generators S1, ..., S4 are each used to control or regulate the local on the basis of current or other influencing factors. & para. [0029]: The predictions of the remaining time RP1 and RP2 are determined on the basis of VD currently captured in an environment of the signal generators S1, ..., S4, signal phase specifications SPA and possibly other influencing a switching behavior of the signal generators S1, ..., S4. The number and speeds of vehicles, their waiting times, approaches of vehicles with priority, events such as accidents or other disruptions, or further relating to a current load can be captured as VD. In order to capture or measure the , the influencing device RSU has a sensor system S which may comprise, for example, vehicle sensors, cameras, speed sensors or other sensors. Alternatively or additionally, the influencing device RSU may have a receiving device for influencing the switching behavior which are captured in another manner. para. [0038]: The neural network NN also has an input network EN. The latter is used to receive input data of the neural network NN and to preprocess said input data and to forward the preprocessed input data to both subnetworks TNA and TNB. In the present exemplary embodiment, the input network EN is formed by the input B and the concealed D. VD, specifications SPA and other (not illustrated) influencing a switching behavior of the signal generators are supplied to the input layer B as input. & para. [0039-0042]: The layers A to M may each comprise one or more neurons. A connection between two layers in each case is indicated by means of arrows in FIG. 2. In the case of such a connection of two layers, each neuron of a starting layer may potentially be connected to each neuron of a target layer… In the present exemplary embodiment, the subnetwork TNA with the concealed layers E, G, I and K is used for predictions of the remaining time of signal groups currently in the “green”, whereas the subnetwork TNB with the concealed F, H, J and L is used for predictions of the remaining time of signal groups currently in the phase “non-green”. Insofar as the same data are supplied to both subnetworks TNA and TNB by the input network EN, both the layer I and the layer J generate predictions of the remaining time for all signal groups, but only those predictions of the remaining time which are assigned to those signal groups which are currently in the “green” influence the end result in the I. Accordingly, only those predictions of the remaining time which are assigned to the signal groups in the “non-green” influence the end result in the layer J.);
train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data (see at least Depeweg, para. [0059-0060]: In the present exemplary embodiment, in order to train the neural network NN, its output dataRP1 and RP2 are compared with times of phase changes which actually occur later, and time discrepancies Δt between predicted phase changes and actually occurring phase changes are determined. In this case, the time discrepancies Δt may be formed by an absolute value or a square of a respective time difference. The times of the actual occurring phase changes may be determined on the basis of the signal phase specifications SPA. The time discrepancies Δt represent a prediction error of the neural network NN and are fed back to the latter. On the basis of the time discrepancy Δt which has been fed back, the neural network NN — as indicated by a dotted arrow in FIG. 3 – is trained to minimize the time discrepancies Δt on average. As a result of this training, the neural network NN is able to determine relatively accurate predictions of expected times remaining to the next respective phase change.).
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 Guo to incorporate the teaching of form multi-channel data from partial data and signal phase and timing data (SP AT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes; train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data of Depeweg, with a reasonable expectation of success, in order for the basis of the prediction of the remaining time transmitted to the means of transport or to the road user, an automatic start/stop system, a brake, a recuperation device, an autonomous vehicle, a navigation device and/or a route planner can be controlled or a notification can be output to the road user (see at least Depeweg, para. [0015]).
As per claim 6 Guo discloses
further including instructions to derive the adjacency matrix using a relationship between the different graph nodes that factors any one of a travel distance, a road layout, and a time-series correlation (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. para. [0042-0043]: A neural network model may improve graphing or mapping data by defining constraints for de-noising. A constraint may limit, reduce, or refine a prediction space for data thereby improving prediction accuracy and speed. For example, the edge information may include details of driving conditions, road constraints, map constraints, traffic incidents, and so on. The edge information may also specify the length between two adjacent nodes as a travel time constraint, a road curvature as a maneuvering constraint, a number of lanes as a road capacity constraint, and so on.).
As per claim 10 Guo discloses
A non-transitory computer-readable medium comprising (see at least Guo, para. [0023]):
instructions that, when executed by a processor (see at least Guo, para. [0023]: The traffic system 200 is shown as including a processor 205. In one embodiment, the traffic system 200 includes a memory 210 that stores an aggregation module 220 and a graphing module 230.), cause the processor to:
form multi-channel data from partial data and timing data about traffic on a road, and a vehicle and road sensors capture and output the multi-channel data, the partial data is acquired from the road sensors (see at least Guo, para. [0027-0028]: Thus, in one embodiment, the data store 240 stores data used by the modules220 and 230 in executing various functions. In one embodiment, the data store 240 includes the sensor data 250 along with, for example, metadata that characterize various aspects of the sensor data 250. For example, the metadata can include location coordinates (e.g., longitude and latitude), relative map coordinates or tile identifiers, time/date stamps from when the separate sensor data 250 was generated, and so on….In one embodiment, the data store 240 may also include the graph structure 260, the completion target 270, and the graph model 280. The traffic system 200 may generate the graph structure 260 according to aggregating structured sensor and perception data from information sources to a server. A graph structure 260 may be a graph that illustrates traffic intersections and vehicle flows in a geographic area. & para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with a k-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on. & para. [0056]);
generate an adjacency matrix from the partial data and geometry about the road (see at least Guo, para. [0043]: The neural network model 510 may use matrices G, A, and E to form a clean and complete graph model of the traffic flows associated with a road network. The neural network model 510 may use a graph structure denoted as a matrix G with the dimensions N×k. The variable N may be the total number of vertices and k the feature vector associated with each vertex. The variable k-dimension may represent reported traffic information from SRVs such as speed, flow rates, density, and so on. A connection relation, such as between vertices, may be represented by an adjacent matrix A with the dimension N×N.); and
train a graph model using temporal patterns for graph nodes from the multi-channel data and the adjacency matrix to complete the partial data, output a traffic pattern (see at least Guo, para. [0048]: In one approach, a traffic system may train the neural network model 510 using a completed, cleaned, or corrected ground-truth G, such as for supervised learning. A module may train the neural network model 510 using perception data. By minimizing the error |Ġ-Ĝ| and back-propagating the derivate, the parameterized encoder-decoder network updates their weights to reach a stable point. The neural network model 510 may use the learned parameters or weights for mapping the data to filter out noise values and fill-in or correct missing values to structure, complete, or clean graphed perception data. In this way, the neural network model 510 may generate the reconstruction matrix Ĝ with satisfactory confidence levels for the completed and cleaned data values when inferred with the noisy and incomplete matrix G.),
and execute an automated task by the vehicle (see at least Guo, para. [0024]: The traffic system 200 may use the perception data to complete a graph model of the traffic flows and communicate the graph model to the vehicle100, thereby improving traffic, congestion, navigation, automated driving maneuvers, automated motion plans, and so on. & para. [0055-0057]).
However Guo does not explicitly disclose
form multi-channel data from partial data and signal phase and timing data (SP AT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes;
train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data.
Depeweg teaches
form multi-channel data from partial data and signal phase and timing data (SPAT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes (see at least Depeweg, para. [0021]: FIG. 1 shows, by way of example, a schematic illustration of an intersection KR having a traffic signaling system which comprises a plurality of traffic lights S1, ..., S4 as traffic signal generators. In this case, traffic lights controlled in phase each form a signal group. In the present exemplary embodiment, S1 and S3 form a first signal group and S2 and S4 form a second signal group. The traffic signal generators S1, ..., S4 are each used to control or regulate the local on the basis of current or other influencing factors. & para. [0029]: The predictions of the remaining time RP1 and RP2 are determined on the basis of VD currently captured in an environment of the signal generators S1, ..., S4, signal phase specifications SPA and possibly other influencing a switching behavior of the signal generators S1, ..., S4. The number and speeds of vehicles, their waiting times, approaches of vehicles with priority, events such as accidents or other disruptions, or further relating to a current load can be captured as VD. In order to capture or measure the , the influencing device RSU has a sensor system S which may comprise, for example, vehicle sensors, cameras, speed sensors or other sensors. Alternatively or additionally, the influencing device RSU may have a receiving device for influencing the switching behavior which are captured in another manner. para. [0038]: The neural network NN also has an input network EN. The latter is used to receive input data of the neural network NN and to preprocess said input data and to forward the preprocessed input data to both subnetworks TNA and TNB. In the present exemplary embodiment, the input network EN is formed by the input B and the concealed D. VD, specifications SPA and other (not illustrated) influencing a switching behavior of the signal generators are supplied to the input layer B as input. & para. [0039-0042]: The layers A to M may each comprise one or more neurons. A connection between two layers in each case is indicated by means of arrows in FIG. 2. In the case of such a connection of two layers, each neuron of a starting layer may potentially be connected to each neuron of a target layer… In the present exemplary embodiment, the subnetwork TNA with the concealed layers E, G, I and K is used for predictions of the remaining time of signal groups currently in the “green”, whereas the subnetwork TNB with the concealed F, H, J and L is used for predictions of the remaining time of signal groups currently in the phase “non-green”. Insofar as the same data are supplied to both subnetworks TNA and TNB by the input network EN, both the layer I and the layer J generate predictions of the remaining time for all signal groups, but only those predictions of the remaining time which are assigned to those signal groups which are currently in the “green” influence the end result in the I. Accordingly, only those predictions of the remaining time which are assigned to the signal groups in the “non-green” influence the end result in the layer J.);
train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data (see at least Depeweg, para. [0059-0060]: In the present exemplary embodiment, in order to train the neural network NN, its output dataRP1 and RP2 are compared with times of phase changes which actually occur later, and time discrepancies Δt between predicted phase changes and actually occurring phase changes are determined. In this case, the time discrepancies Δt may be formed by an absolute value or a square of a respective time difference. The times of the actual occurring phase changes may be determined on the basis of the signal phase specifications SPA. The time discrepancies Δt represent a prediction error of the neural network NN and are fed back to the latter. On the basis of the time discrepancy Δt which has been fed back, the neural network NN — as indicated by a dotted arrow in FIG. 3 – is trained to minimize the time discrepancies Δt on average. As a result of this training, the neural network NN is able to determine relatively accurate predictions of expected times remaining to the next respective phase change.).
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 Guo to incorporate the teaching of form multi-channel data from partial data and signal phase and timing data (SP AT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes; train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data of Depeweg, with a reasonable expectation of success, in order for the basis of the prediction of the remaining time transmitted to the means of transport or to the road user, an automatic start/stop system, a brake, a recuperation device, an autonomous vehicle, a navigation device and/or a route planner can be controlled or a notification can be output to the road user (see at least Depeweg, para. [0015]).
As per claim 12 Guo discloses
A method comprising: forming multi-channel data from partial data and timing data about traffic on a road, and a vehicle and road sensors capture and output the multi-channel data, the partial data is acquired from the road sensors (see at least Guo, para. [0027-0028]: Thus, in one embodiment, the data store 240 stores data used by the modules220 and 230 in executing various functions. In one embodiment, the data store 240 includes the sensor data 250 along with, for example, metadata that characterize various aspects of the sensor data 250. For example, the metadata can include location coordinates (e.g., longitude and latitude), relative map coordinates or tile identifiers, time/date stamps from when the separate sensor data 250 was generated, and so on….In one embodiment, the data store 240 may also include the graph structure 260, the completion target 270, and the graph model 280. The traffic system 200 may generate the graph structure 260 according to aggregating structured sensor and perception data from information sources to a server. A graph structure 260 may be a graph that illustrates traffic intersections and vehicle flows in a geographic area. & para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with a k-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on. & para. [0056]);
generating an adjacency matrix from the partial data and geometry about the road (see at least Guo, para. [0043]: The neural network model 510 may use matrices G, A, and E to form a clean and complete graph model of the traffic flows associated with a road network. The neural network model 510 may use a graph structure denoted as a matrix G with the dimensions N×k. The variable N may be the total number of vertices and k the feature vector associated with each vertex. The variable k-dimension may represent reported traffic information from SRVs such as speed, flow rates, density, and so on. A connection relation, such as between vertices, may be represented by an adjacent matrix A with the dimension N×N.); and
training a graph model using temporal patterns for graph nodes from the multi-channel data and the adjacency matrix to complete the partial data, output a traffic pattern (see at least Guo, para. [0048]: In one approach, a traffic system may train the neural network model 510 using a completed, cleaned, or corrected ground-truth G, such as for supervised learning. A module may train the neural network model 510 using perception data. By minimizing the error |Ġ-Ĝ| and back-propagating the derivate, the parameterized encoder-decoder network updates their weights to reach a stable point. The neural network model 510 may use the learned parameters or weights for mapping the data to filter out noise values and fill-in or correct missing values to structure, complete, or clean graphed perception data. In this way, the neural network model 510 may generate the reconstruction matrix Ĝ with satisfactory confidence levels for the completed and cleaned data values when inferred with the noisy and incomplete matrix G.),
and executing an automated task by the vehicle (see at least Guo, para. [0024]: The traffic system 200 may use the perception data to complete a graph model of the traffic flows and communicate the graph model to the vehicle100, thereby improving traffic, congestion, navigation, automated driving maneuvers, automated motion plans, and so on. & para. [0055-0057]).
However Guo does not explicitly disclose
form multi-channel data from partial data and signal phase and timing data (SP AT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes;
train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data.
Depeweg teaches
form multi-channel data from partial data and signal phase and timing data (SPAT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes (see at least Depeweg, para. [0021]: FIG. 1 shows, by way of example, a schematic illustration of an intersection KR having a traffic signaling system which comprises a plurality of traffic lights S1, ..., S4 as traffic signal generators. In this case, traffic lights controlled in phase each form a signal group. In the present exemplary embodiment, S1 and S3 form a first signal group and S2 and S4 form a second signal group. The traffic signal generators S1, ..., S4 are each used to control or regulate the local on the basis of current or other influencing factors. & para. [0029]: The predictions of the remaining time RP1 and RP2 are determined on the basis of VD currently captured in an environment of the signal generators S1, ..., S4, signal phase specifications SPA and possibly other influencing a switching behavior of the signal generators S1, ..., S4. The number and speeds of vehicles, their waiting times, approaches of vehicles with priority, events such as accidents or other disruptions, or further relating to a current load can be captured as VD. In order to capture or measure the , the influencing device RSU has a sensor system S which may comprise, for example, vehicle sensors, cameras, speed sensors or other sensors. Alternatively or additionally, the influencing device RSU may have a receiving device for influencing the switching behavior which are captured in another manner. para. [0038]: The neural network NN also has an input network EN. The latter is used to receive input data of the neural network NN and to preprocess said input data and to forward the preprocessed input data to both subnetworks TNA and TNB. In the present exemplary embodiment, the input network EN is formed by the input B and the concealed D. VD, specifications SPA and other (not illustrated) influencing a switching behavior of the signal generators are supplied to the input layer B as input. & para. [0039-0042]: The layers A to M may each comprise one or more neurons. A connection between two layers in each case is indicated by means of arrows in FIG. 2. In the case of such a connection of two layers, each neuron of a starting layer may potentially be connected to each neuron of a target layer… In the present exemplary embodiment, the subnetwork TNA with the concealed layers E, G, I and K is used for predictions of the remaining time of signal groups currently in the “green”, whereas the subnetwork TNB with the concealed F, H, J and L is used for predictions of the remaining time of signal groups currently in the phase “non-green”. Insofar as the same data are supplied to both subnetworks TNA and TNB by the input network EN, both the layer I and the layer J generate predictions of the remaining time for all signal groups, but only those predictions of the remaining time which are assigned to those signal groups which are currently in the “green” influence the end result in the I. Accordingly, only those predictions of the remaining time which are assigned to the signal groups in the “non-green” influence the end result in the layer J.);
train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data (see at least Depeweg, para. [0059-0060]: In the present exemplary embodiment, in order to train the neural network NN, its output dataRP1 and RP2 are compared with times of phase changes which actually occur later, and time discrepancies Δt between predicted phase changes and actually occurring phase changes are determined. In this case, the time discrepancies Δt may be formed by an absolute value or a square of a respective time difference. The times of the actual occurring phase changes may be determined on the basis of the signal phase specifications SPA. The time discrepancies Δt represent a prediction error of the neural network NN and are fed back to the latter. On the basis of the time discrepancy Δt which has been fed back, the neural network NN — as indicated by a dotted arrow in FIG. 3 – is trained to minimize the time discrepancies Δt on average. As a result of this training, the neural network NN is able to determine relatively accurate predictions of expected times remaining to the next respective phase change.).
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 Guo to incorporate the teaching of form multi-channel data from partial data and signal phase and timing data (SP AT) information about traffic on a road, and channels from the multi-channel data have a first layer representing the partial data and a second layer representing the SPAT information for different graph nodes; train a graph model using temporal patterns for the different graph nodes from the multi-channel data to complete the partial data of Depeweg, with a reasonable expectation of success, in order for the basis of the prediction of the remaining time transmitted to the means of transport or to the road user, an automatic start/stop system, a brake, a recuperation device, an autonomous vehicle, a navigation device and/or a route planner can be controlled or a notification can be output to the road user (see at least Depeweg, para. [0015]).
As per claim 17 Guo discloses
further comprising deriving the adjacency matrix using a relationship between the different graph nodes that factors any one of a travel distance, a road layout, and a time-series correlation (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. para. [0042-0043]: A neural network model may improve graphing or mapping data by defining constraints for de-noising. A constraint may limit, reduce, or refine a prediction space for data thereby improving prediction accuracy and speed. For example, the edge information may include details of driving conditions, road constraints, map constraints, traffic incidents, and so on. The edge information may also specify the length between two adjacent nodes as a travel time constraint, a road curvature as a maneuvering constraint, a number of lanes as a road capacity constraint, and so on.).
Claim(s) 2, 11, & 13 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo, in view of Depeweg, in view of US 2021/0064999A1 (“Liu 999` ”).
As per claim 2 Guo discloses
the different graph nodes in part represent spatial locations of the road sensors between lane bounds associated with the road (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.).
However Guo does not explicitly disclose
to estimate the temporal patterns by a learning model from time-series data associated with the graph nodes individually
Liu 999` teaches
to estimate the temporal patterns by a learning model from time-series data associated with the graph nodes individually (see at least Liu 999` , para. [0031-0033]: The graph convolutional network is defined over the networks Gs and Gr and is able to extract feature vectors from neighborhood nodes in the graph.…After K layers of the MG-MGCN, the vectors XKs,r can be fed to a fully-connected layer to obtain spatial feature vectors of IV) sites, xs,r E JR I v,ixD,, which encodes both the fine-grained and coarse-grained multi-graph spatial correlations. Then xs,r, at multiple time steps, is used for subsequent temporal modeling. This processing can be done in parallel for spatial correlations at fine granularity ( e.g., site-level) and at coarse granularity (e.g., region-level), with separate MG-MGCN networks handling each granularity output….Block 204 performs temporal modeling, where complex temporal correlations also exist in different time steps. For example, the traffic volume of previous weeks, previous days, and previous hours can all affect the traffic volume of an upcoming time slot. To predict the traffic volume accurately, the correlations between previous time steps are discovered and utilized. )
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 Guo to incorporate the teaching of to estimate the temporal patterns by a learning model from time-series data associated with the different graph nodes individually of Liu 999`, with a reasonable expectation of success, in order to enhance the site-level traffic volume prediction (see at least Liu 999`, para. [0016]).
As per claim 11 Guo discloses
the different graph nodes in part represent spatial locations of the road sensors between lane bounds associated with the road (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.).
However Guo does not explicitly disclose
to estimate the temporal patterns by a learning model from time-series data associated with the different graph nodes individually
Liu 999` teaches
to estimate the temporal patterns by a learning model from time-series data associated with the different graph nodes individually (see at least Liu 999` , para. [0031-0033]: The graph convolutional network is defined over the networks Gs and Gr and is able to extract feature vectors from neighborhood nodes in the graph.…After K layers of the MG-MGCN, the vectors XKs,r can be fed to a fully-connected layer to obtain spatial feature vectors of IV) sites, xs,r E JR I v,ixD,, which encodes both the fine-grained and coarse-grained multi-graph spatial correlations. Then xs,r, at multiple time steps, is used for subsequent temporal modeling. This processing can be done in parallel for spatial correlations at fine granularity ( e.g., site-level) and at coarse granularity (e.g., region-level), with separate MG-MGCN networks handling each granularity output….Block 204 performs temporal modeling, where complex temporal correlations also exist in different time steps. For example, the traffic volume of previous weeks, previous days, and previous hours can all affect the traffic volume of an upcoming time slot. To predict the traffic volume accurately, the correlations between previous time steps are discovered and utilized. )
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 Guo to incorporate the teaching of to estimate the temporal patterns by a learning model from time-series data associated with the different graph nodes individually of Liu 999`, with a reasonable expectation of success, in order to enhance the site-level traffic volume prediction (see at least Liu 999`, para. [0016]).
As per claim 13 Guo discloses
the graph nodes represent spatial locations of the road sensors between lane bounds associated with the road (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.).
However Guo does not explicitly disclose
further comprising estimating the temporal patterns by a learning model from time-series data associated with the graph nodes individually.
Liu 999` teaches
further comprising estimating the temporal patterns by a learning model from time-series data associated with the graph nodes individually (see at least Liu 999` , para. [003-0033]: After K layers of the MG-MGCN, the vectors XKs,r can be fed to a fully-connected layer to obtain spatial feature vectors of IV) sites, xs,r E JR I v,ixD,, which encodes both the fine-grained and coarse-grained multi-graph spatial correlations. Then xs,r, at multiple time steps, is used for subsequent temporal modeling. This processing can be done in parallel for spatial correlations at fine granularity ( e.g., site-level) and at coarse granularity (e.g., region-level), with separate MG-MGCN networks handling each granularity output….Block 204 performs temporal modeling, where complex temporal correlations also exist in different time steps. For example, the traffic volume of previous weeks, previous days, and previous hours can all affect the traffic volume of an upcoming time slot. To predict the traffic volume accurately, the correlations between previous time steps are discovered and utilized.).
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 Guo to incorporate the teaching of to estimate the temporal patterns by a learning model from time-series data associated with the graph nodes individually of Liu 999`, with a reasonable expectation of success, in order to enhance the site-level traffic volume prediction (see at least Liu 999`, para. [0016]).
Claim(s) 3 & 14 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo, in view of Depeweg, in view of Liu 999`, in view of US 2016/0284212A1 (“Tatourian”).
As per claim 3 Guo discloses
further including instructions to: transform the data point into a map having the different graph nodes that includes bound nodes for the road (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.).
However Guo does not explicitly disclose
group the road sensors of a lane for the road into a data point, and the data point having complete data, incomplete data, and the partial data, and the road sensors include devices that are malfunctioning on the vehicle and an infrastructure equipment.
Tatourian teaches
group the road sensors of a lane for the road into a data point, and the data point having complete data, incomplete data, and the partial data, and the road sensors include devices that are malfunctioning on the vehicle and an infrastructure equipment (see at least Tatourian, para. [0015-0016]: Additionally, the traffic analysis server 108 determines the traffic patterns for each road segment 114based on an analysis of the historical vehicle and infrastructure data for that road segment 114 at a given time, or for a given time window (e.g., a one-hour window of time, rush hour, morning, evening, etc.)….The traffic analysis server 108 additionally determines whether the received vehicle data and/or the infrastructure data is indicative of an anomaly, or deviation, from the expected traffic behavior based on the road segment 114 and a present time. To detect the anomaly, the traffic analysis server108 compares the historical traffic patterns to present vehicle data and/or present infrastructure data. & para. [0026]).
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 Guo to incorporate the teaching of group the road sensors of a lane for the road into a data point, and the data point having complete data, incomplete data, and the partial data, and the road sensors include devices that are malfunctioning on the vehicle and an infrastructure equipment of Tatourian, with a reasonable expectation of success, in order for the ECU to successfully navigate the vehicle into and out of the parking spots (see at least Tatourian, para. [0002]).
As per claim 14 Guo discloses
further comprising: transforming the data point into a map having the different graph nodes that includes bound nodes for the road (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.).
However Guo does not explicitly disclose
grouping the road sensors of a lane for the road into a data point, and the data point having complete data, incomplete data, and the partial data, and the road sensors include devices that are malfunctioning on the vehicle and an infrastructure equipment.
Tatourian teaches
grouping the road sensors of a lane for the road into a data point, and the data point having complete data, incomplete data, and the partial data, and the road sensors include devices that are malfunctioning on the vehicle and an infrastructure equipment (see at least Tatourian, para. [0015-0016]: Additionally, the traffic analysis server 108 determines the traffic patterns for each road segment 114based on an analysis of the historical vehicle and infrastructure data for that road segment 114 at a given time, or for a given time window (e.g., a one-hour window of time, rush hour, morning, evening, etc.)….The traffic analysis server 108 additionally determines whether the received vehicle data and/or the infrastructure data is indicative of an anomaly, or deviation, from the expected traffic behavior based on the road segment 114 and a present time. To detect the anomaly, the traffic analysis server108 compares the historical traffic patterns to present vehicle data and/or present infrastructure data. & para. [0026]).
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 Guo to incorporate the teaching of grouping the road sensors of a lane for the road into a data point, and the data point having complete data, incomplete data, and the partial data, and the road sensors include devices that are malfunctioning on the vehicle and an infrastructure equipment of Tatourian, with a reasonable expectation of success, in order for the ECU to successfully navigate the vehicle into and out of the parking spots (see at least Tatourian, para. [0002]).
Claim(s) 4, 15, & 18 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo, in view of Depeweg, in view of US 2024/0054321A1 (“Bogaerts”).
As per claim 4 Guo discloses
wherein the instructions to train the graph model further include instructions to: process data that factors bounds represented by the different graph nodes, a length of a feature vector, and channels producing the multi-channel data (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.); and
minimize a loss of the graph model by comparing the data and the traffic pattern against a ground truth about the partial data (see at least Guo, para. [0048]: In one approach, a traffic system may train the neural network model 510 using a completed, cleaned, or corrected ground-truth G, such as for supervised learning. A module may train the neural network model 510 using perception data. By minimizing the error |Ġ-Ĝ| and back-propagating the derivate, the parameterized encoder-decoder network updates their weights to reach a stable point. The neural network model 510 may use the learned parameters or weights for mapping the data to filter out noise values and fill-in or correct missing values to structure, complete, or clean graphed perception data. In this way, the neural network model 510 may generate the reconstruction matrix Ĝ with satisfactory confidence levels for the completed and cleaned data values when inferred with the noisy and incomplete matrix G.).
However Guo does not explicitly
wherein the instructions to train the graph model further include instructions to: process historical data, and
minimize a loss of the graph model by comparing the historical data and the traffic pattern.
Bogaerts teaches
wherein the instructions to train the graph model further include instructions to:
process historical data that factors bounds represented by the different graph nodes, a length of a feature vector, and channels producing the multi-channel data (see at least Bogaerts, para. [0023]: In other words, the processing may further take into account the relation-based traffic representation observed at one or more past time periods. Thus, not only current but also historic relation-based traffic representation may be taken into account during the training of the learning model. & para. [0070]: In this case, at the first convolution iteration, the convolution for the respective nodes is performed in the same manner as described above, taking into account the traffic information from their direct neighbours. In this example, the convolution will be performed for all nodes in the graph. More specifically, the traffic data of S1 will be convolved with the traffic data of S2, the traffic data ofS2 will be convolved with the traffic data of S1 and S6, the traffic data of S6 will be convolved with the traffic data of S2, S3 and S4 and so on. The resulting relation-based traffic representation for the respective nodes will thus contain a partial abstract representation of the traffic information of the direct neighbouring nodes.); and
minimize a loss of the graph model by comparing the historical data and the traffic pattern against a ground truth about the data (see at least Bogaerts, para. [0077-0078]: To do so, the learning system then evaluates the correctness of the predicted traffic information, i.e. the values of the features for the respective nodes at the time intervals t=+1, . . . , t=+5, with respect to the actual values of the features for the respective nodes at these time intervals. The evaluation is done, as conventionally, using a loss function which estimates the loss between the predicted and the actual traffic data. Based on the estimated loss, the learning model and, more specifically, the weights used in the weighted average, the convolution weights, and the encoder-decoder weights, are updated by employing, a backpropagation mechanism. This results in updating or, in other words, in training the learning model….The steps of convolving 332, processing 334 and updating 336 are repeated until the learning model achieves a desired level of traffic prediction performance, i.e. until the resulting loss is below a desired level, which marks the completion of the training of the learning model.).
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 Guo to incorporate the teaching of wherein the instructions to train the graph model further include instructions to: process historical data, and minimize a loss of the graph model by comparing the historical data and the traffic pattern of Bogaerts, with a reasonable expectation of success, in order to allow for a time-efficient and cost-effective training of the learning models (see at least Bogaerts, para. [0021]).
As per claim 15 Guo discloses
wherein training the graph model further includes: processing data that factors hounds represented by the different graph nodes, a length of a feature vector, and channels producing the multi-channel data (see at least Guo, para. [0041]: The traffic system 400 may generate a graph structure from data 410 according to the road network 420 and the traffic information received from SRVs. The graph structure of data 410 may indicate each traffic intersection as a traffic or road link node and vertex 430. For example, the graph structure from data 410 may include V.sub.1-V.sub.20 vertices. Each vertex may be associated with ak-dimension vector or feature that represents reported traffic information from SRVs such as speed, flow rates, density, and so on.); and
minimizing a loss of the graph model by comparing the data and the traffic pattern against a ground truth about the partial data (see at least Guo, para. [0048]: In one approach, a traffic system may train the neural network model 510 using a completed, cleaned, or corrected ground-truth G, such as for supervised learning. A module may train the neural network model 510 using perception data. By minimizing the error |Ġ-Ĝ| and back-propagating the derivate, the parameterized encoder-decoder network updates their weights to reach a stable point. The neural network model 510 may use the learned parameters or weights for mapping the data to filter out noise values and fill-in or correct missing values to structure, complete, or clean graphed perception data. In this way, the neural network model 510 may generate the reconstruction matrix Ĝ with satisfactory confidence levels for the completed and cleaned data values when inferred with the noisy and incomplete matrix G.).
However Guo does not explicitly disclose
wherein training the graph model further includes: processing historical data and
minimizing a loss of the graph model by comparing the historical data and the traffic pattern.
Bogaerts teaches
wherein training the graph model further includes: processing historical data that factors hounds represented by the different graph nodes, a length of a feature vector, and channels producing the multi-channel data (see at least Bogaerts, para. [0023]: In other words, the processing may further take into account the relation-based traffic representation observed at one or more past time periods. Thus, not only current but also historic relation-based traffic representation may be taken into account during the training of the learning model. & para. [0070]: In this case, at the first convolution iteration, the convolution for the respective nodes is performed in the same manner as described above, taking into account the traffic information from their direct neighbours. In this example, the convolution will be performed for all nodes in the graph. More specifically, the traffic data of S1 will be convolved with the traffic data of S2, the traffic data ofS2 will be convolved with the traffic data of S1 and S6, the traffic data of S6 will be convolved with the traffic data of S2, S3 and S4 and so on. The resulting relation-based traffic representation for the respective nodes will thus contain a partial abstract representation of the traffic information of the direct neighbouring nodes.); and
minimizing a loss of the graph model by comparing the historical data and the traffic pattern against a ground truth about the partial data (see at least Bogaerts, para. [0077-0078]: To do so, the learning system then evaluates the correctness of the predicted traffic information, i.e. the values of the features for the respective nodes at the time intervals t=+1, . . . , t=+5, with respect to the actual values of the features for the respective nodes at these time intervals. The evaluation is done, as conventionally, using a loss function which estimates the loss between the predicted and the actual traffic data. Based on the estimated loss, the learning model and, more specifically, the weights used in the weighted average, the convolution weights, and the encoder-decoder weights, are updated by employing, a backpropagation mechanism. This results in updating or, in other words, in training the learning model….The steps of convolving 332, processing 334 and updating 336 are repeated until the learning model achieves a desired level of traffic prediction performance, i.e. until the resulting loss is below a desired level, which marks the completion of the training of the learning model.).
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 Guo to incorporate the teaching of wherein training the graph model further includes: processing historical data and minimizing a loss of the graph model by comparing the historical data and the traffic pattern of Bogaerts, with a reasonable expectation of success, in order to allow for a time-efficient and cost-effective training of the learning models (see at least Bogaerts, para. [0021]).
As per claim 18 Guo discloses
further comprising shaping the traffic pattern at an intersection and bound individually by a linearizing layer of the graph model (see at least Guo, para. [0028]: A graph structure 260 may be a graph that illustrates traffic intersections and vehicle flows in a geographic area. & para. [0046]: In the encoding processing, the high-dimensional graph structure from data maybe mapped multiple-times linearly and non-linearly through a layered neural network.).
Claim(s) 5, 7 & 16 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo, in view of Depeweg, in view of Bogaerts, in view of Liu 999`.
As per claim 5 Guo does not explicitly disclose
wherein the feature vector represents a number of time intervals and the time-intervals are one of consecutive time-intervals and non-consecutive blocks
Liu 999` teaches
wherein the feature vector represents a number of time intervals and the time-intervals are one of consecutive time-intervals and non-consecutive blocks (see at least Liu 999` , para. [0032-0033]: After K layers of the MG-MGCN, the vectors XKs,r can be fed to a fully-connected layer to obtain spatial feature vectors of IV) sites, xs,r E JR I v,ixD,, which encodes both the fine-grained and coarse-grained multi-graph spatial correlations. Then xs,r, at multiple time steps, is used for subsequent temporal modeling. This processing can be done in parallel for spatial correlations at fine granularity ( e.g., site-level) and at coarse granularity (e.g., region-level), with separate MG-MGCN networks handling each granularity output….Block 204 performs temporal modeling, where complex temporal correlations also exist in different time steps. For example, the traffic volume of previous weeks, previous days, and previous hours can all affect the traffic volume of an upcoming time slot. To predict the traffic volume accurately, the correlations between previous time steps are discovered and utilized.).
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 Guo to incorporate the teaching of wherein the feature vector represents a number of time intervals and the time-intervals are one of consecutive time-intervals and non-consecutive blocks of Liu 999`, with a reasonable expectation of success, in order to enhance the site-level traffic volume prediction (see at least Liu 999`, para. [0016]).
As per claim 7 Guo discloses
further including instructions to shape the traffic pattern at an intersection and bound individually by a linearizing layer of the graph model (see at least Guo, para. [0028]: A graph structure 260 may be a graph that illustrates traffic intersections and vehicle flows in a geographic area. & para. [0046]: In the encoding processing, the high-dimensional graph structure from data maybe mapped multiple-times linearly and non-linearly through a layered neural network.).
As per claim 16 Guo does not explicitly disclose
wherein the feature vector represents a number of time-intervals and the time-intervals are one of consecutive time-intervals and non-consecutive blocks.
Liu 999` teaches
wherein the feature vector represents a number of time-intervals and the time-intervals are one of consecutive time-intervals and non-consecutive blocks (see at least Liu 999` , para. [0032-0033]: After K layers of the MG-MGCN, the vectors XKs,r can be fed to a fully-connected layer to obtain spatial feature vectors of IV) sites, xs,r E JR I v,ixD,, which encodes both the fine-grained and coarse-grained multi-graph spatial correlations. Then xs,r, at multiple time steps, is used for subsequent temporal modeling. This processing can be done in parallel for spatial correlations at fine granularity ( e.g., site-level) and at coarse granularity (e.g., region-level), with separate MG-MGCN networks handling each granularity output….Block 204 performs temporal modeling, where complex temporal correlations also exist in different time steps. For example, the traffic volume of previous weeks, previous days, and previous hours can all affect the traffic volume of an upcoming time slot. To predict the traffic volume accurately, the correlations between previous time steps are discovered and utilized.).
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 Guo to incorporate the teaching of wherein the feature vector represents a number of time-intervals and the time-intervals are one of consecutive time-intervals and non-consecutive blocks of Liu 999`, with a reasonable expectation of success, in order to enhance the site-level traffic volume prediction (see at least Liu 999`, para. [0016]).
Claim(s) 8 & 19 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo, in view of Depeweg, in view of US 2018/0293884A1 (“Liu 884` ”).
As per claim 8 Guo does not explicitly disclose
wherein the timing data indicates any one of vehicle prioritization, vehicle platooning, pedestrian crossings, and fractional phases of a traffic light associated with a time-interval that represents abnormal conditions for the traffic
Liu 884` teaches
wherein the timing data indicates any one of vehicle prioritization, vehicle platooning, pedestrian crossings, and fractional phases of a traffic light associated with a time-interval that represents abnormal conditions for the traffic (see at least Liu 884`, para. [0083]: The signal phase and timing (SPaT) data broadcast by the RSEs have also been collected at deployed intersections. The SPaT data contain information of signal status that can be used as the input for "signal aware" CV applications, e.g., red light violation warning or eco-approach/ departure assistance. Here, only a portion of the data fields in the SPaT are used, including: timestamp when a message was generated, signal phase ID and signal status. A sample of SPaT data is shown in FIG. 5.).
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 Guo to incorporate the teaching of wherein the timing data indicates any one of vehicle prioritization, vehicle platooning, pedestrian crossings, and fractional phases of a traffic light associated with a time-interval that represents abnormal conditions for the traffic of Liu 884`, with a reasonable expectation of success, in order to operate traffic control devices for increased efficiency of traffic flow (see at least Liu 884`, para. [0002]).
As per claim 19 Guo does not explicitly disclose
wherein the timing data indicates any one of vehicle prioritization, vehicle platooning, pedestrian crossings, and fractional phases of a traffic light associated with a time-interval that represents abnormal conditions for the traffic.
Liu 884` teaches
wherein the timing data indicates any one of vehicle prioritization, vehicle platooning, pedestrian crossings, and fractional phases of a traffic light associated with a time-interval that represents abnormal conditions for the traffic (see at least Liu 884`, para. [0083]: The signal phase and timing (SPaT) data broadcast by the RSEs have also been collected at deployed intersections. The SPaT data contain information of signal status that can be used as the input for "signal aware" CV applications, e.g., red light violation warning or eco-approach/ departure assistance. Here, only a portion of the data fields in the SPaT are used, including: timestamp when a message was generated, signal phase ID and signal status. A sample of SPaT data is shown in FIG. 5.).
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 Guo to incorporate the teaching of wherein the timing data indicates any one of vehicle prioritization, vehicle platooning, pedestrian crossings, and fractional phases of a traffic light associated with a time-interval that represents abnormal conditions for the traffic of Liu 884`, with a reasonable expectation of success, in order to operate traffic control devices for increased efficiency of traffic flow (see at least Liu 884`, para. [0002]).
Claim(s) 9 & 20 is/are rejected under 35 U.S.C. 103 as being unpatentable over Guo, in view of Depeweg, in view of Tatourian, in view of Liu 884`.
As per claim 9 Guo does not explicitly disclose
wherein the road sensors are infrastructure sensors that are malfunctioning, the SPAT for a signalized intersection associated with the road, and the traffic pattern is traffic volume.
Tatourian teaches
wherein the road sensors are infrastructure sensors that are malfunctioning, the timing data is for a signalized intersection associated with the road, and the traffic pattern is traffic volume (see at least Tatourian, para. [0015-0016]: Additionally, the traffic analysis server 108 determines the traffic patterns for each road segment 114based on an analysis of the historical vehicle and infrastructure data for that road segment 114 at a given time, or for a given time window (e.g., a one-hour window of time, rush hour, morning, evening, etc.)….The traffic analysis server 108 additionally determines whether the received vehicle data and/or the infrastructure data is indicative of an anomaly, or deviation, from the expected traffic behavior based on the road segment 114 and a present time. To detect the anomaly, the traffic analysis server108 compares the historical traffic patterns to present vehicle data and/or present infrastructure data. & para. [0026]).
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 Guo to incorporate the teaching of wherein the road sensors are infrastructure sensors that are malfunctioning, the timing data is for a signalized intersection associated with the road, and the traffic pattern is traffic volume of Tatourian, with a reasonable expectation of success, in order for the ECU to successfully navigate the vehicle into and out of the parking spots (see at least Tatourian, para. [0002]).
Liu 884` teaches
wherein the road sensors are infrastructure sensors, the SPAT information includes data for a signalized intersection associated with the road, and the traffic pattern is traffic volume (see at least Liu 884`, para. [0083-0085]: The signal phase and timing (SPaT) data broadcast by the RSEs have also been collected at deployed intersections. The SPaT data contain information of signal status that can be used as the input for "signal aware" CV applications, e.g., red light violation warning or eco-approach/ departure assistance. Here, only a portion of the data fields in the SPaT are used, including: timestamp when a message was generated, signal phase ID and signal status. A sample of SPaT data is shown in FIG. 5….By combining these arrival information from vehicle trajectories, volume of overall vehicle arrivals can be estimated….For the traffic volume estimation method, the inputs include vehicle trajectories (e.g., which can be generated from two or more TL data) approaching to an intersection as well as traffic signal status (or statuses). In other embodiments, the estimation method can take into account other data, such as other TL data, data from RSEs, data from mobile devices, or data from other devices that may be in communication with the remote facility 16, which may carry out at least part of the method discussed herein.).
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 Guo to incorporate the teaching of wherein the road sensors are infrastructure sensors, the SPAT information includes data for a signalized intersection associated with the road, and the traffic pattern is traffic volume of Liu 884`, with a reasonable expectation of success, in order to operate traffic control devices for increased efficiency of traffic flow (see at least Liu 884`, para. [0002]).
As per claim 20 Guo does not explicitly disclose
wherein the road sensors are infrastructure sensors that are malfunctioning, the SPAT information includes data for a signalized intersection associated with the road, and the traffic pattern is traffic volume.
Tatourian teaches
wherein the road sensors are infrastructure sensors that are malfunctioning, the timing data is for a signalized intersection associated with the road, and the traffic pattern is traffic volume (see at least Tatourian, para. [0015-0016]: Additionally, the traffic analysis server 108 determines the traffic patterns for each road segment 114based on an analysis of the historical vehicle and infrastructure data for that road segment 114 at a given time, or for a given time window (e.g., a one-hour window of time, rush hour, morning, evening, etc.)….The traffic analysis server 108 additionally determines whether the received vehicle data and/or the infrastructure data is indicative of an anomaly, or deviation, from the expected traffic behavior based on the road segment 114 and a present time. To detect the anomaly, the traffic analysis server108 compares the historical traffic patterns to present vehicle data and/or present infrastructure data. & para. [0026]).
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 Guo to incorporate the teaching of wherein the road sensors are infrastructure sensors that are malfunctioning, the timing data is for a signalized intersection associated with the road, and the traffic pattern is traffic volume of Tatourian, with a reasonable expectation of success, in order for the ECU to successfully navigate the vehicle into and out of the parking spots (see at least Tatourian, para. [0002]).
Liu 884` teaches
wherein the road sensors are infrastructure sensors, the SPAT information includes data for a signalized intersection associated with the road, and the traffic pattern is traffic volume (see at least Liu 884`, para. [0083-0085]: The signal phase and timing (SPaT) data broadcast by the RSEs have also been collected at deployed intersections. The SPaT data contain information of signal status that can be used as the input for "signal aware" CV applications, e.g., red light violation warning or eco-approach/ departure assistance. Here, only a portion of the data fields in the SPaT are used, including: timestamp when a message was generated, signal phase ID and signal status. A sample of SPaT data is shown in FIG. 5….By combining these arrival information from vehicle trajectories, volume of overall vehicle arrivals can be estimated….For the traffic volume estimation method, the inputs include vehicle trajectories (e.g., which can be generated from two or more TL data) approaching to an intersection as well as traffic signal status (or statuses). In other embodiments, the estimation method can take into account other data, such as other TL data, data from RSEs, data from mobile devices, or data from other devices that may be in communication with the remote facility 16, which may carry out at least part of the method discussed herein.).
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 Guo to incorporate the teaching of wherein the road sensors are infrastructure sensors, the SPAT information includes data for a signalized intersection associated with the road, and the traffic pattern is traffic volume of Liu 884`, with a reasonable expectation of success, in order to operate traffic control devices for increased efficiency of traffic flow (see at least Liu 884`, para. [0002]).
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 MOHAMED ABDO ALGEHAIM whose telephone number is (571)272-3628. The examiner can normally be reached Monday-Friday 8-5PM 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, Fadey Jabr can be reached at 571-272-1516. 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.
/MOHAMED ABDO ALGEHAIM/Primary Examiner, Art Unit 3668
Prosecution Insights