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 .
This is a Final Office Action on the merits. Claims 1 and 3-7 are currently pending and are addressed below.
Response to Amendment
1. The amendment filed 12/30/2025 has been entered. Claims 1 and 3-7 remain pending in the application.
Response to Arguments
2. Regarding the rejection made under 35 USC 103, the Applicant’s amendments and arguments have been fully considered but are moot because of 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.
Claim Rejections - 35 USC § 103
3. In the event the determination of the status of the application as subject to AIA 35 U.S.C. 102 and 103 (or as subject to pre-AIA 35 U.S.C. 102 and 103) is incorrect, any correction of the statutory basis for the rejection will not be considered a new ground of rejection if the prior art relied upon, and the rationale supporting the rejection, would be the same under either status.
The following is a quotation of 35 U.S.C. 103 which forms the basis for all obviousness rejections set forth in this Office action:
A patent for a claimed invention may not be obtained, notwithstanding that the claimed invention is not identically disclosed as set forth in section 102, if the differences between the claimed invention and the prior art are such that the claimed invention as a whole would have been obvious before the effective filing date of the claimed invention to a person having ordinary skill in the art to which the claimed invention pertains. Patentability shall not be negated by the manner in which the invention was made.
4. Claims 1, 3, and 6 is/are rejected under 35 U.S.C. 103 as being unpatentable over Eggert et al. (US 20200231149, hereinafter Eggert) in view of Damerow et al. (US 20150344030, hereinafter Damerow) and further in view of Pallett et al. (US 20160009291, hereinafter Pallett).
Regarding claim 1, Eggert teaches a vehicle control device comprising one or more processors (see at least Figs. 1-2) configured to:
generate travel profile information indicating a travel state of a host vehicle for each of a plurality of possible target behavior candidates taken by the host vehicle (see at least Figs. 3-4 and [0010]: “The priority relationship can be estimated based on road maps indicating priority at intersections (e.g., Y, T and X junctions as well as roundabouts) and highway mergings (entering plus leaving ramps and overtaking), and/or based on vehicle type/state (emergency vehicle), stop lines, road signs and/or traffic lights detected by at least one optical sensor of the ego-vehicle.”; [0039]: “The priority determination module 14 individually determines a priority relationship between the ego-vehicle 1 and each traffic participant identified by the image-processing module 11 and involved in the traffic situation to be evaluated by the prediction module 16. The traffic situations may be classified into at least two categories by the priority determination module 14: a longitudinal case, in which the ego-vehicle 1 and the other traffic participant 18 drive on the same path/lane and in the same direction, i.e. one vehicle follows the other one, as shown in FIG. 3; and a lateral case, in which, at the current point in time, the ego-vehicle 1 and the other traffic participant 18 do not follow the same path, but the future paths intersect/merge within the prediction horizon, as shown in FIG. 4.”; [0040]: “In the lateral case, the priority determination module 14 determines whether the ego-vehicle 1 has right of way over the other traffic participant 18, or the other traffic participant 18 has right of way over the ego-vehicle 1 based on the lane, the position of the traffic participant 18, the course of the road, and/or the traffic signs identified by the image processing module 11. Alternatively or in addition, the priority determination module 14 performs the determination based on a position signal of the position sensor 8 and map data of the map database 15 that indicates the priority rules for the road network.”);
predict a behavior of a three-dimensional object existing around the host vehicle (see at least Figs. 3-6 and [0044]: “FIG. 5 shows a prediction model, in which the graph of the velocity of the traffic participant 18 over time shows a delayed increase of velocity. According to this model, the prediction module 16 predicts the traffic participant 18 to drive with a constant velocity V.sub.0 for a short period t.sub.const, then to increase the velocity with an acceleration of a.sub.used for a period t.sub.acc, and to drive with a constant velocity for the rest of the prediction horizon, wherein V.sub.0 is the current velocity of the traffic participant 18, t.sub.const and t.sub.acc are parameters and a.sub.used depends on the current velocity V.sub.0, the maximum speed V.sub.max, and the maximum acceleration a.sub.max, as shown in FIG. 6. It is preferred that the acceleration a.sub.used is constant over t.sub.acc.”; [0047]: “The prediction module 16 predicts a future behavior for the traffic participant 18 based on the selected prediction model, the information received from the image-processing module 11 and the signals received from the front radar 2 and the rear radar 3 and calculates a behavior relevant score for ego-vehicle 1 based on the calculated trajectories of ego-vehicle 1 and the traffic participant 18.”);
generate a risk indicating a travel safety degree of the host vehicle for each position around the host vehicle on a basis of a prediction result of the behavior of the three-dimensional object and the travel profile information (see at least Figs. 3-7 and [0046]: “In both prediction models, a.sub.used, V.sub.max, a.sub.max, t.sub.const and/or t.sub.acc can be set based on the road conditions (e.g., asphalt, rubble, ice), road geometry (e.g., curvature), weather conditions (e.g., raining, low altitude of sun, foggy), speed limit, type and/or state of the traffic participant 18, type and/or state of the ego-vehicle 1, distance between the ego-vehicle 1 and the traffic participant 18, a speed with which the ego-vehicle 1 and the traffic participant 18 move towards each other, and/or observed driver state (gaze, distraction).”; [0048]: “The behavior relevant score is relevant to plan/control the behavior of the ego-vehicle 1 and could be negatively correlated to the safety of the ego-trajectory (i.e., a high collision risk corresponds to a high behavior relevant score). For example, the distance between the ego-vehicle 1 and the traffic participant 18 or a product of collision probability and collision severity for each point in time can be used to calculate the behavior relevant score.”; [0049]: “As shown in FIG. 7, the behavior relevant score BRS is a function over the time within the prediction horizon during which the prediction is considered to remain valid. In FIG. 7, the function of the behavior relevant score BRS indicates a high risk in the distant future (maximum at time t.sub.1). In order to determine an ego-vehicle behavior, the BRS for all other traffic participants that are considered for behavior planning, the respective BRS is integrated over the prediction horizon. The final determination of the best ego-vehicle behavior is then based on the sum of all integrated behavior relevant scores BRS of the other traffic participants.”);
calculate, a priority indicating a degree to which the host vehicle is to preferentially make a selection for each of the plurality of target behavior candidates (see at least [0009]: “With the present invention, the most likely future behavior and, thus, trajectory and velocity of a traffic participant is iteratively predicted/calculated based on a prediction model selected based on the priority relationship between the ego-vehicle and the traffic participant. This enables to plan a future ego-vehicle behavior which is safe (low risks), useful (the ego-vehicle performs movement), and has a high comfort (low jerk, constrained acceleration).”; [0053]: “In order to determine the best behavior for the ego-vehicle 1, prediction module 16 can calculate a plurality of ego-trajectories and choose the one which results in the best behavior relevant score, as disclosed in EP 2 950 294 A1, or iteratively change the ego-trajectory and/or velocity profile to optimize the behavior relevant score. The prediction module 16 outputs information on the finally determined ego-trajectory (velocity profile) to the behavior determination module 17 that determines a behavior of the ego-vehicle based on this information, generates corresponding driving control signals for executing the determined behavior by controlling acceleration, braking and/or steering of the ego-vehicle 1, and outputs the generated control signals to the vehicle controller 10. Alternatively or in addition, warning and/or recommendations for drivers of the ego-vehicle 1 can be generated and outputted by the behavior determination module 17.”); and
select, as a target trajectory of the host vehicle, a trajectory corresponding to one of the plurality of target behavior candidates on a basis of the risk and the priority (see at least [0019]: “The system determines on its own, or gets it as input, the current positions and velocities of one or more other traffic participant(s), which are relevant for the intended further driving behavior of the ego-vehicle. The system makes predictions about the relevant other traffic participants' future positions/velocities on their respective given paths (e.g. from a map). Given these predictions, and an ego-vehicle's trajectory and velocity profile, the system calculates the corresponding behavior relevant score (including at least one of: collision risk, curvature, utility, and/or drive comfort aspects) and selects or determines the ego vehicle behavior, e.g., by calculating the behavior relevant score for a plurality of alternative ego-vehicle's velocity profiles and/or trajectories, and selecting the best among them. Determination may alternatively be performed by using an optimization algorithm to iteratively improve one or more trajectories and/or velocity profiles.”; [0053]: “In order to determine the best behavior for the ego-vehicle 1, prediction module 16 can calculate a plurality of ego-trajectories and choose the one which results in the best behavior relevant score, as disclosed in EP 2 950 294 A1, or iteratively change the ego-trajectory and/or velocity profile to optimize the behavior relevant score. The prediction module 16 outputs information on the finally determined ego-trajectory (velocity profile) to the behavior determination module 17 that determines a behavior of the ego-vehicle based on this information, generates corresponding driving control signals for executing the determined behavior by controlling acceleration, braking and/or steering of the ego-vehicle 1, and outputs the generated control signals to the vehicle controller 10.”).
Eggert fails to explicitly teach generating a risk map and selecting a target trajectory based on the risk map.
However, Damerow teaches a method and apparatus for a vehicle advanced driver assistance system that generates a risk map and selects a target trajectory based on the risk map (see at least Figs. 2-3 and [0011]: “One important feature of the invention is the generation of a temporal risk map that explicitly represents zones of high risk for different temporal prediction horizons, since one axis of the map is the time or the travelled distance along an intended ego-trajectory (time and distance may be transformed into each other), as well as the planning and evaluation of future behavior alternatives within these risk maps, which provide an advantage because it allows the usage of standard optimization and planning algorithms with low computational costs.”; [0049]: “We then assemble the plurality of risk functions of the different ego-trajectory alternatives to get a risk map, which is an at least 2-dimensional map/function over driven ego-car trajectory length and parameters of the ego-car future trajectories. A typical usage is a risk map with longitudinal velocity as the main parameter of the ego-car future trajectories. See FIG. 3 for a graphical explanation.”; [0063]: “After the evaluation or analysis of the risk map a control signal is output. This control signal either includes an information about risks on the intended travel path (corresponding to the predicted trajectory) exceeding a threshold for the risk measure and is suitable to generate a warning which is presented to a vehicle driver. In case of semi-automated driving or autonomous driving the control signal is suitable to directly influence the control systems of the ego-vehicle. Thereby the driving state of the vehicle is controlled in such a way that the selected preferred path through the risk map is followed.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert to incorporate the teachings of Damerow and provide a means to generate a risk map and select a target trajectory based on the risk map, with a reasonable expectation of success, in order to generate a temporal risk map that represents zones of high risk for planning and evaluation of future behavior of the vehicle while allowing the usage of standard optimization and planning algorithms with low computational costs [0011].
The combination of Eggert and Damerow fails to explicitly teach considering an expected arrival time to a location position point where a lane change of the host vehicle occurs on a basis of the travel profile information and surrounding environment information, and sets a higher lane change priority as the expected arrival time decreases.
However, Pallett teaches a method and apparatus for a vehicle advanced driver assistance system that considering an expected arrival time to a location position point where a lane change of a host vehicle occurs on a basis of a travel profile information and surrounding environment information, and sets a higher lane change priority as the expected arrival time decreases (see at least [0009]: “When operating in the “time to target” mode, the autonomous driving system 105 may prioritize reaching the target destination as quickly as possible relative to traffic laws and the current traffic patterns. This may include aggressively accelerating and decelerating the vehicle 100, performing aggressive cornering maneuvers, aggressively entering and crossing traffic, changing lanes frequently, making more abrupt steering actions. Moreover, the autonomous driving system 105 may leave less room between the autonomous vehicle 100 and a front vehicle (i.e., the vehicle immediately in front of the autonomous vehicle 100). The “time to target” mode may further have the autonomous vehicle 100 drive at appropriate speeds relative to the speed limit and traffic density.”; [0024]: “Using the signals received from the autonomous driving sensors 120 and the navigation system 115, the autonomous mode controller 125 may take the occupant to his or her target destination using driving characteristics consistent with the selected mode. The driving characteristics may relate to how aggressively the autonomous vehicle 100 accelerates and decelerates, how much space the autonomous vehicle 100 leaves behind a front vehicle, how frequently the autonomous vehicle 100 changes lanes, the abruptness of the steering actions, etc.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert and Damerow to incorporate the teachings of Damerow and provide a means to consider an expected arrival time to a location position point where a lane change of a host vehicle occurs on a basis of a travel profile information and surrounding environment information, and sets a higher lane change priority as the expected arrival time decreases, with a reasonable expectation of success, in order to prioritize how to reach a destination quickly while taking into account the frequency of lane changes to achieve this goal.
Regarding claim 3, modified Eggert teaches the limitations of claim 1. Eggert further teaches wherein the one or more processors are further configured to generate the travel profile information having different conditions regarding a speed of the host vehicle on a basis of the course change priority (see at least Figs. 3-4 and [0053]: “In order to determine the best behavior for the ego-vehicle 1, prediction module 16 can calculate a plurality of ego-trajectories and choose the one which results in the best behavior relevant score, as disclosed in EP 2 950 294 A1, or iteratively change the ego-trajectory and/or velocity profile to optimize the behavior relevant score. The prediction module 16 outputs information on the finally determined ego-trajectory (velocity profile) to the behavior determination module 17 that determines a behavior of the ego-vehicle based on this information, generates corresponding driving control signals for executing the determined behavior by controlling acceleration, braking and/or steering of the ego-vehicle 1, and outputs the generated control signals to the vehicle controller 10. Alternatively or in addition, warning and/or recommendations for drivers of the ego-vehicle 1 can be generated and outputted by the behavior determination module 17.”; [0057]: “The predictive velocity optimization for the ego-vehicle 1, which is performed by the prediction module 16 and which allows to find ego velocity profiles minimizing risks from curves and all involved vehicles while maximizing utility (needed time to arrive at a goal) and comfort (change and duration of acceleration) under the presence of regulatory conditions, is described in the following.”).
Eggert fails to explicitly teach the travel profile information having different conditions on a basis of the lane change priority.
However, Pallett teaches a method and apparatus for a vehicle advanced driver assistance system that comprises travel profile information having different conditions on a basis of the lane change priority (see at least [0009]: “When operating in the “time to target” mode, the autonomous driving system 105 may prioritize reaching the target destination as quickly as possible relative to traffic laws and the current traffic patterns. This may include aggressively accelerating and decelerating the vehicle 100, performing aggressive cornering maneuvers, aggressively entering and crossing traffic, changing lanes frequently, making more abrupt steering actions. Moreover, the autonomous driving system 105 may leave less room between the autonomous vehicle 100 and a front vehicle (i.e., the vehicle immediately in front of the autonomous vehicle 100). The “time to target” mode may further have the autonomous vehicle 100 drive at appropriate speeds relative to the speed limit and traffic density.”; [0024]: “Using the signals received from the autonomous driving sensors 120 and the navigation system 115, the autonomous mode controller 125 may take the occupant to his or her target destination using driving characteristics consistent with the selected mode. The driving characteristics may relate to how aggressively the autonomous vehicle 100 accelerates and decelerates, how much space the autonomous vehicle 100 leaves behind a front vehicle, how frequently the autonomous vehicle 100 changes lanes, the abruptness of the steering actions, etc.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert and Damerow to incorporate the teachings of Damerow and provide travel profile information having different conditions on a basis of the lane change priority, with a reasonable expectation of success, in order to consider the frequency of lane changes for different travel profile.
Regarding claim 6, modified Eggert teaches the limitations of claim 1. Eggert further teaches wherein the travel profile information includes at least one of host vehicle speed profile information that is an element for achieving a target behavior of the host vehicle and host vehicle steering angle profile information indicating a steering amount of the host vehicle (see at least Figs. 3-4 and [0036]: “A position sensor 8, e.g. a GPS navigation device, is mounted on the ego-vehicle 1 and detects the position of the ego-vehicle 1. The driver assistance system of the ego-vehicle 1 further comprises a computer 9 that receives or acquires the signals from the front radar 2, the rear radar 3, the cameras 4 . . . 7, the position sensor 8, and status data of the ego-vehicle 1, such as vehicle speed, steering angle, engine torque, brake actuation, from of at least one vehicle controller 10 (ECU).”; [0053]: “In order to determine the best behavior for the ego-vehicle 1, prediction module 16 can calculate a plurality of ego-trajectories and choose the one which results in the best behavior relevant score, as disclosed in EP 2 950 294 A1, or iteratively change the ego-trajectory and/or velocity profile to optimize the behavior relevant score. The prediction module 16 outputs information on the finally determined ego-trajectory (velocity profile) to the behavior determination module 17 that determines a behavior of the ego-vehicle based on this information, generates corresponding driving control signals for executing the determined behavior by controlling acceleration, braking and/or steering of the ego-vehicle 1, and outputs the generated control signals to the vehicle controller 10.”).
Claim Rejections - 35 USC § 103
5. Claims 4 and 5 is/are rejected under 35 U.S.C. 103 as being unpatentable over Eggert et al. (US 20200231149, hereinafter Eggert) and Damerow et al. (US 20150344030, hereinafter Damerow) and Pallett et al. (US 20160009291, hereinafter Pallett) in view of Hattori et al. (US 20190367026, hereinafter Hattori).
Regarding claim 4, modified Eggert teaches the limitations of claim 3. Eggert further teaches the one or more processors are further configured to generate, as the travel profile information, a speed profile, and the one or more processors are further configured to generate, as the travel profile information, an acceleration profile in which the host vehicle is assumed to accelerate and a deceleration profile in which the host vehicle is assumed to decelerate (see at least [0053]: “In order to determine the best behavior for the ego-vehicle 1, prediction module 16 can calculate a plurality of ego-trajectories and choose the one which results in the best behavior relevant score, as disclosed in EP 2 950 294 A1, or iteratively change the ego-trajectory and/or velocity profile to optimize the behavior relevant score. The prediction module 16 outputs information on the finally determined ego-trajectory (velocity profile) to the behavior determination module 17 that determines a behavior of the ego-vehicle based on this information, generates corresponding driving control signals for executing the determined behavior by controlling acceleration, braking and/or steering of the ego-vehicle 1, and outputs the generated control signals to the vehicle controller 10.”).
Eggert fails to explicitly teach generating a constant speed assumed profile in which the host vehicle is assumed to move at a constant speed in a case where the lane change priority is lower than a predetermined value and generating an acceleration profile in which the host vehicle is assumed to accelerate and a deceleration profile in which the host vehicle is assumed to decelerate in a case where the lane change priority is higher than the predetermined value.
However, Hattori teaches an apparatus and system for automated driving control that reacts to lane changes made by another vehicle that generates a constant speed assumed profile in which the host vehicle is assumed to move at a constant speed in a case where the lane change priority is lower than a predetermined value and generates an acceleration profile in which the host vehicle is assumed to accelerate and a deceleration profile in which the host vehicle is assumed to decelerate in a case where the lane change priority is higher than the predetermined value (see at least Figs. 3-7 and [0051]: “At S150, the travel controller 7 determines whether the current situation satisfies the predetermined acceptance condition based on the detection results of the behavior sensor group 2, information acquired by the information acquisition portion 3, map information acquired from the map DB 4, and the results of recognition by the environment recognition portion 6. The condition mentioned above in relation to S130 is excluded from the acceptance condition in this step.”; [0052]: “The acceptance condition at least includes the directional indicator of the adjacent vehicle blinking continually for a predetermined duration of time or longer. The acceptance condition may differ depending on the combination of the traveling status of the subject vehicle and the position of the moving space for moving in. The traveling status of the subject vehicle refers to one of traveling at a constant speed, decelerating, and accelerating.”; [0053]: “The following cases may be regarded as a high priority request for a lane change, and result in an immediate determination that the acceptance condition is met. The high priority request case may include, for example, a blinking hazard light. The high priority request case may include a branching road or an exit road branching off ahead in own lane on the side opposite from the adjacent lane on which the adjacent vehicle is present. The high priority request case may include a restriction ahead in the adjacent lane due to an accident or construction. The high priority request case may include the adjacent lane ending ahead because of merging roads or a lane reduction ahead.”; [0056]: “At S170, the travel controller 7 notifies the drivers of the subject vehicle, adjacent vehicle, and the vehicle behind, by way of the notification portion 8, of the intention to perform a reception control that is the control for giving way to the adjacent vehicle in accordance with the target motion set at S160, and the process proceeds to S180. For example, the driver of the subject vehicle is informed of deceleration or acceleration for giving way, by way of the vehicle interior display portion 81. The driver of the adjacent vehicle is notified of the intention of giving way, and prompted to cut in front of the subject vehicle or merge behind the subject vehicle, by way of the side display portion 82. The driver of the vehicle behind is informed of deceleration or acceleration for giving way to the adjacent vehicle, by way of the rear display portion 83.” Hattori teaches various cases when a high priority request for merging (lane change priority is higher than a predetermined value), the travel profile for the vehicle is to accelerate and decelerate vs. not merging (lane change priority is low than a predetermined value) where the travel profile is to keep the constant speed.).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert to incorporate the teachings of Hattori and provide a means to generates a constant speed assumed profile in which the host vehicle is assumed to move at a constant speed in a case where the lane change priority is lower than a predetermined value and generates an acceleration profile in which the host vehicle is assumed to accelerate and a deceleration profile in which the host vehicle is assumed to decelerate in a case where the lane change priority is higher than the predetermined value, with a reasonable expectation of success, in order to account for the speed and acceleration of the current vehicle while adapting to a surrounding vehicle when selecting a target trajectory.
Regarding claim 5, modified Eggert teaches the limitations of claim 1. Eggert further teaches the one or more processors are further configured to generate a risk in accordance with a vehicle other than the host vehicle (see at least (see at least Figs. 3-7 and [0048]: “The behavior relevant score is relevant to plan/control the behavior of the ego-vehicle 1 and could be negatively correlated to the safety of the ego-trajectory (i.e., a high collision risk corresponds to a high behavior relevant score). For example, the distance between the ego-vehicle 1 and the traffic participant 18 or a product of collision probability and collision severity for each point in time can be used to calculate the behavior relevant score.”; [0049]: “As shown in FIG. 7, the behavior relevant score BRS is a function over the time within the prediction horizon during which the prediction is considered to remain valid. In FIG. 7, the function of the behavior relevant score BRS indicates a high risk in the distant future (maximum at time t.sub.1).”).
Eggert fails to explicitly teach generating a risk map.
However, Damerow teaches a method and apparatus for a vehicle advanced driver assistance system that generates a risk map (see at least Figs. 2-3 and [0011]: “One important feature of the invention is the generation of a temporal risk map that explicitly represents zones of high risk for different temporal prediction horizons, since one axis of the map is the time or the travelled distance along an intended ego-trajectory (time and distance may be transformed into each other), as well as the planning and evaluation of future behavior alternatives within these risk maps, which provide an advantage because it allows the usage of standard optimization and planning algorithms with low computational costs.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert to incorporate the teachings of Damerow and provide a means to generate a risk map, with a reasonable expectation of success, in order to generate a temporal risk map that represents zones of high risk for planning and evaluation of future behavior of the vehicle while allowing the usage of standard optimization and planning algorithms with low computational costs [0011].
The combination of Eggert and Damerow further fails to explicitly teach lighting timing of a direction indicator of a vehicle other than the host vehicle associated with the risk.
However, Hattori teaches an apparatus and system for automated driving control that reacts to lane changes made by another vehicle wherein lighting timing of a direction indicator of a vehicle other than a host vehicle is associated with a risk (see at least Figs. 3-7 and [0034]: “The adjacent vehicle information portion 63 recognizes information in relation to an adjacent vehicle, which is a vehicle traveling on the adjacent lane identified by the lane information portion 61, based on images and the like…The illumination state may include, in addition to whether the directional indicator or hazard light is blinking, the duration of time after the light has started blinking.”; [0052]: “The acceptance condition at least includes the directional indicator of the adjacent vehicle blinking continually for a predetermined duration of time or longer. The acceptance condition may differ depending on the combination of the traveling status of the subject vehicle and the position of the moving space for moving in.”; [0069]: “For example, the target trajectory may be generated in accordance with the results of risk evaluation based on the surrounding situations.”).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert and Damerow to incorporate the teachings of Hattori and provide a means wherein lighting timing of a direction indicator of a vehicle other than a host vehicle is associated with a risk, with a reasonable expectation of success, in order to account for the turn signal lighting timing of a surrounding vehicle when selecting a target trajectory.
Claim Rejections - 35 USC § 103
6. Claim 7 is/are rejected under 35 U.S.C. 103 as being unpatentable over Eggert et al. (US 20200231149, hereinafter Eggert) and Damerow et al. (US 20150344030, hereinafter Damerow) and Pallett et al. (US 20160009291, hereinafter Pallett) in further view of Gyllenhammar et al. (US 20220089151, hereinafter Gyllenhammar).
Regarding claim 7, modified Eggert teaches the limitations of claim 1.
Eggert fails to explicitly teach calculating a prediction reliability on a basis of the surrounding environment information and past statistical information by a neural network model.
However, Gyllenhammar teaches a method and system for path planning in autonomous driving environments that calculates a prediction reliability on a basis of surrounding environment information and past statistical information by a neural network model (see at least Figs. 1-3 and [0014]: “The method comprises obtaining a risk map of a surrounding environment of the vehicle. The risk map is formed based on an actuation capability of the vehicle and a location of free-space areas in the surrounding environment, the actuation capability including an uncertainty estimation for the actuation capability and the location of free-space areas comprising an uncertainty estimation for the estimated location of free-space areas. Moreover, the risk map comprises a risk parameter for each of a plurality of area segments comprised in the surrounding environment of the vehicle. The method further comprises obtaining at least one candidate path for the vehicle, determining a total risk value for each candidate path based on the risk parameters of a set of area segments intersected by the at least one path, selecting a candidate path, of the at least one candidate path, fulfilling one or more risk value criterion, and generating, at an output, a first signal indicative of the selected candidate path.”; [0051]: “Stated differently, these high risk/low risk segments may be quantified to a probability score using statistical modelling based on historical data that has been collected over time from real driving scenarios, e.g. if the ego-vehicle's planned path were to intersect segment A, then the historical data indicated that the probability of collision/violation of safety threshold is X. In more detail, as mentioned, these statistical models may be more or less complex taking into account various factors such as time of day, day of the week, distance to other vehicles, angle relative to other vehicle, type of other vehicle, speed of other vehicle, speed of ego-vehicle, geographical position, and so forth. For example, one may statistically conclude that there is a higher probability of collision in an area segment 1 meter behind a vehicle than in an area segment 50 meters behind the same vehicle. Thus, the area segment close to the rear of the external vehicle will be given a higher risk value or a risk parameter indicative of the “higher risk”, than the area segments far away from the external vehicle.”; [0060]: “FIG. 2 is a schematic block diagram representation of a path planning system 10 for an autonomous or semi-autonomous vehicle. The risk map is supplied as input to the path planning system 10 together with additional quality constraints or criteria, such as e.g. comfort parameters. These inputs are processed by a path finder component/module 25, which may be a “black box”, based on machine learning models or similar. Accordingly, the path finding component 25 outputs a set of candidate paths 1-N, all of which are subsequently assessed by a risk evaluation component/module 26 based on their risk level.””).
Therefore, it would have been obvious to someone of ordinary skill in the art before the effective filing date of the claimed invention to have modified Eggert to incorporate the teachings of Gyllenhammar and provide a means to calculate a prediction reliability on a basis of surrounding environment information and past statistical information by a neural network model, with a reasonable expectation of success, in order to account for past history and using a machine learning model to further assist with risk evaluation with selecting a target trajectory.
Conclusion
THIS ACTION IS MADE FINAL. 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 extension fee 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 TIEN MINH LE whose telephone number is (571)272-3903. The examiner can normally be reached Monday to Friday (8:30am-5:30pm eastern time).
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, Khoi Tran can be reached on (571)272-6919. 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.
/T.M.L./Examiner, Art Unit 3656 /KHOI H TRAN/Supervisory Patent Examiner, Art Unit 3656