DETAILED ACTION
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
This Office Action is in response to RCE and Amendment filed on 10/27/2025.
Claims 3, 9 were canceled.
Claims 1-2, 4-8, 10-12 are pending for examination.
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and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114.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 10/27/2025 has been entered.
Information Disclosure Statement
The information disclosure statement (IDS) submitted on 10/27/2025 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
(A) Applicant’s arguments, see pages 8, filed “Claim 9 is canceled. Therefore, rejection under §101 is moot.” on 10/27/2025, with respect to Rejection of Claims 9 under 35 U.S.C. 101 have been fully considered and are persuasive.
As to point (A), the Rejection of Claims 9 under 35 U.S.C. 101 has been withdrawn.
(B) Applicant’s arguments, see pages 9-10, filed “While the cited inventions share some similarities with the present invention in that they relate to predicting future trajectories by clustering locations of objects or predicting a distribution of locations, they do not teach "generating clusters based on a probability distribution of locations to which vehicles, that were at the same location at a specific time point, moved at a subsequent time point", nor do they teach "predicting a future trajectory by connecting predetermined points within two or more clusters"” on 10/27/2025 have been fully considered but they are not persuasive.
As to point (B), the examiner respectfully disagrees. The examiner further notes in response to applicant's argument that the references fail to show certain features of the invention, it is noted that the features upon which applicant relies (i.e., "generating clusters based on a probability distribution of locations to which vehicles, that were at the same location at a specific time point, moved at a subsequent time point" and "predicting a future trajectory by connecting predetermined points within two or more clusters") are not recited in the rejected claim(s). Although the claims are interpreted in light of the specification, limitations from the specification are not read into the claims. See In re Van Geuns, 988 F.2d 1181, 26 USPQ2d 1057 (Fed. Cir. 1993).
(C) Applicant's arguments filed “Claim 11 is an independent claim reciting the similar features discussed above with respect to claim 1. Therefore, claim 11 is patentable based on the similar reasons presented above” and “Claims 2, 4-8, 10 and 12 are dependent claims depending upon claims 1 or 11. Therefore, these claims are patentable in virtue of their dependencies.” on 10/27/2025 have been fully considered but they are not persuasive.
As to point (C), the examiner respectfully disagrees. The examiner further notes the amended claim 1 would still be fully encompassed by the references cited in the pervious office action and would not patentable.
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.
Claim 1-2, 4-6, 10-11 is/are rejected under 35 U.S.C. 103 as being unpatentable over Hardå (US20200023835A1) in view of Zhao (US20210107532A1).
In regards to claim 1, Hardå teaches A method of predicting a future trajectory of a current target vehicle by using pieces of movement information about a plurality of past nearby vehicles, the method comprising:
receiving, by a server, the pieces of movement information about the plurality of past nearby vehicles at a reference location of a past driving vehicle(Hardå: Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”);
obtaining, by the server, from the pieces of movement information, first state information about the plurality of past nearby vehicles located at a first location at a first time point(Hardå: Fig. 3B Element 304; Para 12 “modelled clusters of trajectories for traffic situations may be established based on historical trajectories for the traffic situations and used for learning how a vehicle may drive through a traffic situation”; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; i.e. a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B indicating different location of the vehicle as different times (first time point) and GPS coordinate(first state information)), wherein the first time point corresponds to a previous time point before a reference time point;
obtaining, by the server, from the pieces of movement information, second location values of the plurality of past nearby vehicles at a second time point (Hardå: Fig. 3B Element 304; Para 12 “modelled clusters of trajectories for traffic situations may be established based on historical trajectories for the traffic situations and used for learning how a vehicle may drive through a traffic situation”; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; i.e. a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B indicating different location of the vehicle as different times (second time point)and GPS coordinate (second location values)) at which a preset time period has elapsed from the first time point; and
probabilistically calculating, by the server, distributions of the second location values by using a clustering technique for the second location values(Hardå: Fig. 3C Element 306 and 308; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302”; Para 74 “the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; Para 74 “as conceptually illustrated in FIG. 3C the clustered trajectories may be parameterized providing a density contour 306 of trajectories through the intersection with an average trajectory set 308 being represented”),
estimating, based on the distributions of second location values, a distribution of target locations of the current target vehicle at a third time point at which the preset time period has elapsed from the reference time point(Hardå: Fig. 2; Para 75 “The control unit on the server 112 uses a supervised learning algorithm taught on the training data provided by the trajectories 304 and/or the parameterized clustered trajectories 306 in order to be able to reproduce trajectories using satellite images of traffic situations as input”; Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”; i.e. the model trajectory 230 would encompass distribution of target locations of the current target vehicle at a third time point); and
predicting a future trajectory of the current target vehicle(Hardå: Fig. 2; Para 75 “The control unit on the server 112 uses a supervised learning algorithm taught on the training data provided by the trajectories 304 and/or the parameterized clustered trajectories 306 in order to be able to reproduce trajectories using satellite images of traffic situations as input”; Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”) by connecting an average point of a cluster with respect to the distribution of target locations of the current target vehicle at the third time point with an average point of a cluster with respect to a distribution of target locations of the current target vehicle at a fourth time point at which the preset time period has elapsed from the third time point(Hardå: Fig. 3B and 3C; Para 74 “FIG. 3C the clustered trajectories may be parameterized providing a density contour 306 of trajectories through the intersection with an average trajectory set 308 being represented”; i.e. average trajectory set 308 would encompasses an average point of a cluster and the average trajectory set 308 would include locations of different time points),
wherein the distribution of target locations of the current target vehicle at the fourth time point is estimated on the basis of distributions of location values of the plurality of past nearby vehicles at a time point at which the preset time period has elapsed from the second time point(Hardå: Fig. 3B; Para 73 “the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc”; i.e. GPS coordinates and other information of road users would encompass distributions of location values of the plurality of past nearby vehicles),
wherein the method further comprises controlling driving of a current driving vehicle based on the predicted future trajectory of the current target vehicle (Hardå: Para 39 “control the host vehicle to perform at least one action based on the selected at least one feasible trajectory”).
Yet Hardå do not explicitly teach wherein the first time point corresponds to a previous time point before a reference time point;
second time point at which a preset time period has elapsed from the first time point.
However, in the same field of endeavor, Zhao teaches wherein the first time point corresponds to a previous time point before a reference time point (Zhao: Fig. 2 Element t-1; Para 18 “the plurality of time points may include or may be or may be referred to as past time points, and the pre-determined time point may be a time point succeeding the plurality of time points, so that determining (for example predicting) the attribute may include or may be determining the attribute at a future time point”; Para 45 “each row represents the trajectory of one object (for example of one vehicle); an exemplary row is indicated by reference sign 204; each column represents one time frame of the trajectories of the objects (for example assuming that t is the current time and n−1 past frames are demonstrated in FIG. 2, wherein n is an integer number); an exemplary column is indicated by reference sign 206; each entry in the image-like data structure 202 (wherein each entry may be referred to as pixel) stores the information (in other words: property) of a specific object at a specific past time frame (in other words: time point)”);
second time point at which a preset time period has elapsed from the first time point (Zhao: Fig. 2 Element t; Para 18 “the plurality of time points may include or may be or may be referred to as past time points, and the pre-determined time point may be a time point succeeding the plurality of time points, so that determining (for example predicting) the attribute may include or may be determining the attribute at a future time point”; Para 45 “each row represents the trajectory of one object (for example of one vehicle); an exemplary row is indicated by reference sign 204; each column represents one time frame of the trajectories of the objects (for example assuming that t is the current time and n−1 past frames are demonstrated in FIG. 2, wherein n is an integer number); an exemplary column is indicated by reference sign 206; each entry in the image-like data structure 202 (wherein each entry may be referred to as pixel) stores the information (in other words: property) of a specific object at a specific past time frame (in other words: time point)”).
Therefore, it would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention, to modify the method of Hardå with the feature of wherein the first time point corresponds to a previous time point before a reference time point; second time point at which a preset time period has elapsed from the first time point disclosed by Zhao. One would be motivated to do so for the benefit of “efficiently and reliable determine traffic situations” (Zhao: Para 5).
In regards to claim 2, the combination of Hardå and Zhao teaches The method of claim 1, and Hardå further teaches receiving second state information about the current target vehicle at the reference location and the reference time point(Hardå: Fig. 2; (Hardå: Fig. 2; Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”); and
selecting, from among the distributions of the second location values of the plurality of past nearby vehicles, the distribution of the second location values that matches the second state information about the current target vehicle. (Hardå: Fig. 2; Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”).
In regards to claim 4, the combination of Hardå and Zhao teaches The method of claim 2, and Hardå further teaches the first state information about the plurality of past nearby vehicles (Hardå: Fig. 3B Element 304; Para 12 “modelled clusters of trajectories for traffic situations may be established based on historical trajectories for the traffic situations and used for learning how a vehicle may drive through a traffic situation”; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”) and the second state information about the current target vehicle comprise location values and speed values of the respective vehicles(Hardå: Para 10 “detecting the position and speed of the at least one secondary road user in the vicinity of the present traffic situation; predicting at least one feasible trajectory for the at least one secondary road user based on the position and the speed of the at least one secondary road user and the plurality of modelled clusters of trajectories for the present traffic situation”)..
In regards to claim 5, the combination of Hardå and Zhao teaches The method of claim 2, and Hardå further teaches the selecting of the distribution of the second location values that matches the second state information comprises:
receiving the location value and the speed value of the current target vehicle(Hardå: Para 10 “detecting the position and speed of the at least one secondary road user in the vicinity of the present traffic situation; predicting at least one feasible trajectory for the at least one secondary road user based on the position and the speed of the at least one secondary road user and the plurality of modelled clusters of trajectories for the present traffic situation; selecting at least one feasible trajectory of the feasible trajectories for each secondary road user based on a selection criterion, and performing at least one action based on the selected at least one feasible trajectory”);
extracting, from the first state information, the location values of the plurality of past nearby vehicles within a preset range from the location value of the current target vehicle(Hardå: Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”);
selecting the plurality of past nearby vehicles having speed values within a preset range from the speed value of the current target vehicle, from among the plurality of past nearby vehicles having the location value of the current target vehicle(Hardå: Para 23 “the modelled clusters of trajectories may further include a speed profile for each of the trajectories, the method may include: predicting a speed profile for each of the plurality of trajectories for the at least one secondary road user based on comparing the position and the speed of the at least one secondary road user to the modelled clusters of trajectories including modelled speed profiles for the present traffic situation; selecting at least one feasible trajectory of the feasible trajectories including a speed profile for each secondary road user based on the selection criterion, and performing at least one action based on the selected at least one feasible trajectory”); and
selecting distributions of second location values of the selected plurality of past nearby vehicles at the second time point(Hardå: Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”).
In regards to claim 6, the combination of Hardå and Zhao teaches The method of claim 1, and Zhao further teaches the second location values are specified by at least one of a road on which the plurality of past nearby vehicles were driving at the second time point, and a lane included in the road(Zhao: Para 8 “data representing a respective property of a plurality of objects at a plurality of time points (in other words: the values of a property for a plurality of objects at a plurality of time points) may be arranged in an image-like data structure so that each column of the image-like data structure corresponds to properties of the plurality of objects at a single time point, and that each row of the image-like data structure corresponds to properties of a single object”; Para 23 “the property may include or may be at least one of a location, a speed, a linear velocity, a rotational speed, an acceleration, a type of the object, a distance to a middle of a lane, a lane driving direction of a lane in which the object is, types (for example solid, dashed, etc.) of left and right markings of the lane in which the object is, the condition (for example wet, dry, etc.) of the lane in which the object is, a (possibly detected) breaking light status of the object, and a (possibly detected) turning light status of the object.”). The Examiner supplies the same rationale for the combination of references Hardå and Zhao as in Claim 1 above.
As per claim 10, it recites A non-transitory computer-readable recording medium having recorded thereon a program for executing the method of claim 1 on a computer having limitations similar to those of claim 1 and therefore is rejected on the same basis. Hardå further teaches A non-transitory computer-readable recording medium (Hardå: Para 93 “The control functionality of the present disclosure may be implemented using existing computer processors, or by a special purpose computer processor for an appropriate system, incorporated for this or another purpose, or by a hardwire system. Embodiments within the scope of the present disclosure include program products including machine-readable medium for carrying or having machine-executable instructions or data structures stored thereon. Such machine-readable media can be any available media that can be accessed by a general purpose or special purpose computer or other machine with a processor. By way of example, such machine-readable media can include RAM, ROM, EPROM, EEPROM, CD-ROM or other optical disk storage, magnetic disk storage or other magnetic storage devices, or any other medium which can be used to carry or store desired program code in the form of machine-executable instructions or data structures and which can be accessed by a general purpose or special purpose computer or other machine with a processor. When information is transferred or provided over a network or another communications connection (either hardwired, wireless, or a combination of hardwired or wireless) to a machine, the machine properly views the connection as a machine-readable medium. Thus, any such connection is properly termed a machine-readable medium. Combinations of the above are also included within the scope of machine-readable media. Machine-executable instructions include, for example, instructions and data which cause a general purpose computer, special purpose computer, or special purpose processing machines to perform a certain function or group of functions”).
In regards to claim 11, Hardå teaches A system for predicting a future trajectory of a current target vehicle by using pieces of movement information about a plurality of past nearby vehicles, the system comprising:
a processor in a past driving vehicle, configured to receive the pieces of movement information about the one or more past nearby vehicles at a reference location of the past driving vehicle(Hardå: Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; i.e. the road users may transmit their GPS coordinates and other information would indicate that there is a processor that receive the pieces of movement information);
a server configured to probabilistically calculate distributions of second location values of the one or more past nearby vehicles by using the pieces of movement information (Hardå: Fig. 3C Element 306 and 308; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; Para 74 “as conceptually illustrated in FIG. 3C the clustered trajectories may be parameterized providing a density contour 306 of trajectories through the intersection with an average trajectory set 308 being represented”); and
a processor in a current driving vehicle, configured to predict the future trajectory of the current target vehicle by using the distributions of the movement locations (Hardå: Para 39 “an active safety system for a host vehicle, including: at least one detection unit for detecting the position and the speed of a secondary road user; a positioning system for determining the present location of the host vehicle, and a vehicle control unit configured to: retrieve a plurality of modelled clusters of trajectories for a present traffic situation, the present traffic situation is based on the present location of the host vehicle; predict at least one feasible trajectory for the at least one secondary road user based on the position and the speed of the at least one secondary road user and the plurality of modelled clusters of trajectories for the present traffic situation; select at least one feasible trajectory of the feasible trajectories for each secondary road user based on a selection criterion, and control the host vehicle to perform at least one action based on the selected at least one feasible trajectory.”),
wherein the server is further configured to receive, the pieces of movement information about the plurality of past nearby vehicles at a reference location of a past driving vehicle(Hardå: Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”), obtain, from the pieces of movement information, first state information about the plurality of past nearby vehicles located at a first location at a first time point(Hardå: Fig. 3B Element 304; Para 12 “modelled clusters of trajectories for traffic situations may be established based on historical trajectories for the traffic situations and used for learning how a vehicle may drive through a traffic situation”; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; i.e. a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B indicating different location of the vehicle as different times (first time point) and GPS coordinate(first state information)), wherein the first time point corresponds to a previous time point before a reference time point, obtain, from the pieces of movement information, second location values of the plurality of past nearby vehicles at a second time point (Hardå: Fig. 3B Element 304; Para 12 “modelled clusters of trajectories for traffic situations may be established based on historical trajectories for the traffic situations and used for learning how a vehicle may drive through a traffic situation”; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; i.e. a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B indicating different location of the vehicle as different times (second time point)and GPS coordinate (second location values))at which a preset time period has elapsed from the first time point; and probabilistically calculate, by the server, distributions of the second location values by using a clustering technique for the second location values(Hardå: Fig. 3C Element 306 and 308; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302”; Para 74 “the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc.”; Para 74 “as conceptually illustrated in FIG. 3C the clustered trajectories may be parameterized providing a density contour 306 of trajectories through the intersection with an average trajectory set 308 being represented”),
wherein the processor in the current driving vehicle is further configured to obtain second state information about the current target vehicle at the reference location and a reference time point (Hardå: Para 39 “an active safety system for a host vehicle, including: at least one detection unit for detecting the position and the speed of a secondary road user; a positioning system for determining the present location of the host vehicle, and a vehicle control unit configured to: retrieve a plurality of modelled clusters of trajectories for a present traffic situation, the present traffic situation is based on the present location of the host vehicle; predict at least one feasible trajectory for the at least one secondary road user based on the position and the speed of the at least one secondary road user and the plurality of modelled clusters of trajectories for the present traffic situation; select at least one feasible trajectory of the feasible trajectories for each secondary road user based on a selection criterion, and control the host vehicle to perform at least one action based on the selected at least one feasible trajectory.”),
receive, from the server, the second location values of the one or more plurality of past nearby vehicles that matches the second state information about the current target vehicle (Hardå: Para 39 “an active safety system for a host vehicle, including: at least one detection unit for detecting the position and the speed of a secondary road user; a positioning system for determining the present location of the host vehicle, and a vehicle control unit configured to: retrieve a plurality of modelled clusters of trajectories for a present traffic situation, the present traffic situation is based on the present location of the host vehicle; predict at least one feasible trajectory for the at least one secondary road user based on the position and the speed of the at least one secondary road user and the plurality of modelled clusters of trajectories for the present traffic situation; select at least one feasible trajectory of the feasible trajectories for each secondary road user based on a selection criterion, and control the host vehicle to perform at least one action based on the selected at least one feasible trajectory”; Para 73 “FIG. 3A-C conceptually illustrates exemplary data collection for a supervised learning algorithm subsequently used for reproducing trajectories for a plurality of traffic situations. In FIG. 3A a conceptual satellite image 300 or HD map 300 of a traffic situation 302 is shown. Trajectory data for a traffic situation is received by a control unit, i.e. located on a server 112 as illustrated in FIG. 1. The trajectory data is received from a plurality of road user travelling through the same traffic situation. For example, the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302”),
estimate, based on the distributions of second location values, a distribution of target locations of the current target vehicle at a third time point at which the preset time period has elapsed from the reference time point(Hardå: Fig. 2; Para 75 “The control unit on the server 112 uses a supervised learning algorithm taught on the training data provided by the trajectories 304 and/or the parameterized clustered trajectories 306 in order to be able to reproduce trajectories using satellite images of traffic situations as input”; Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”; i.e. the model trajectory 230 would encompass distribution of target locations of the current target vehicle at a third time point); and
predict a future trajectory of the current target vehicle(Hardå: Fig. 2; Para 75 “The control unit on the server 112 uses a supervised learning algorithm taught on the training data provided by the trajectories 304 and/or the parameterized clustered trajectories 306 in order to be able to reproduce trajectories using satellite images of traffic situations as input”; Para 71 “FIG. 2 illustrates a simplified scenario of predicting at least one feasible trajectory for the secondary road user 108. FIG. 2 illustrates four clusters of model trajectories, a first cluster 210, a second cluster 220, a third cluster 230, and a fourth cluster 240. In accordance with embodiments, the position of the secondary road 108 user is detected by the host vehicle and is matched with a set of positions along each of the clusters 210, 220, 230, and 240. Using a distance metric it may be possible to determine that the vehicle is closest to the cluster 230. For the present scenario it may be assumed that the vehicle 108 has just started travelling along the model trajectory 230”) by connecting an average point of a cluster with respect to the distribution of target locations of the current target vehicle at the third time point with an average point of a cluster with respect to a distribution of target locations of the current target vehicle at a fourth time point at which the preset time period has elapsed from the third time point(Hardå: Fig. 3B and 3C; Para 74 “FIG. 3C the clustered trajectories may be parameterized providing a density contour 306 of trajectories through the intersection with an average trajectory set 308 being represented”; i.e. average trajectory set 308 would encompasses an average point of a cluster and the average trajectory set 308 would include locations of different time points),
control driving of the current driving vehicle based on the predicted future trajectory of the current target vehicle(Hardå: Para 39 “control the host vehicle to perform at least one action based on the selected at least one feasible trajectory”),
wherein the distribution of target locations of the current target vehicle at the fourth time point is estimated on the basis of distributions of location values of the plurality of past nearby vehicles at a time point at which the preset time period has elapsed from the second time point(Hardå: Fig. 3B; Para 73 “the road users may transmit their GPS coordinates and other information such as vehicle speed, yaw rate, acceleration, detected traffic signs, detected position and speed of nearby objects, weather data, time of day, date, friction measurements, road condition data as they travel through the traffic situation 302. This results in a large set of trajectories 304 for the traffic situation 302 as conceptually illustrated in FIG. 3B. This data collection is performed for a large set of traffic situations. Further, the trajectories 304 may be clustered into classes of trajectories such as turning left, stopping at stop line, driving straight, etc”; i.e. GPS coordinates and other information of road users would encompass distributions of location values of the plurality of past nearby vehicles).
Yet Hardå do not explicitly teach wherein the first time point corresponds to a previous time point before a reference time point;
second time point at which a preset time period has elapsed from the first time point.
However, in the same field of endeavor, Zhao teaches wherein the first time point corresponds to a previous time point before a reference time point (Zhao: Fig. 2 Element t-1; Para 18 “the plurality of time points may include or may be or may be referred to as past time points, and the pre-determined time point may be a time point succeeding the plurality of time points, so that determining (for example predicting) the attribute may include or may be determining the attribute at a future time point”; Para 45 “each row represents the trajectory of one object (for example of one vehicle); an exemplary row is indicated by reference sign 204; each column represents one time frame of the trajectories of the objects (for example assuming that t is the current time and n−1 past frames are demonstrated in FIG. 2, wherein n is an integer number); an exemplary column is indicated by reference sign 206; each entry in the image-like data structure 202 (wherein each entry may be referred to as pixel) stores the information (in other words: property) of a specific obje