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 .
Status of Claims
This FINAL action is in response to application No. 18/194,433 filed on 03 March, 2023. Claims 1-20 are currently pending and have been examined. Claims 1-20 have been rejected as follows.
Response to Arguments
Applica’s amendments and/or arguments with regard to 35 USC 101 as set forth in the office action of September 17, 2025 have been considered and are PERSUASIVE. The rejection of claims under 35 USC 101 as set forth in the office action of September 17, 2025 have been withdrawn.
Applicant’s amendments and/or arguments with respect to the rejection of claims under 35 USC 103 as set forth in the office action of September 17, 2025 have been considered and:
Applicant argues that prior art, Szubbocsev, does not teach the method with the use of a trained neural network in order to predict the energy usage of a vehicle. The examiner finds this argument PERSUASIVE, however search has been updated and a neural network is taught by Pathipati (US-11975628-B1).
Applicant argues that method taught from prior art, Szubbocsev, does not apply to a fleet dynamic. However, Szubbocsev references the application to a fleet of autonomous-driving vehicles – for example, see paragraph [37]; “However, one or more embodiments of the ADV navigation system network (described with reference to FIG. 6) can function to aide a fleet of ADVs to route and navigate a plurality of ADVs throughout the same or different geographical areas on navigational pathways.” Therefore, this argument is found NOT PERSUASIVE.
Applicant’s amendments and/or arguments with respect to the rejection of claims 1-20 under 35 USC 103 as set forth in the office action of September 17, 2025 have been considered but are moot because the new ground(s) 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
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.
Claims 1, 5, 6, 10, 11, 15 ,16 and 19 are rejected under 35 U.S.C 103 as being unpatentable over Szubbocsev (US 20190294173 A1) in view of Pathipati (US 11975628 B1), Zhu (US 12152893 B2), and Houle (US 11247579 B2).
Regarding claim 1, Szubbocsev discloses a fleet management system comprising:
(see at least ¶ [0037]; "one or more embodiments of the ADV navigation system network (described with reference to FIG. 6) can function to aide a fleet of ADVs to route and navigate a plurality of ADVs)
one or more processors coupled to the memory, the (see at least [0052]; "one or more embodiments of the on-board computer 204 includes an in-memory processing system configured to perform in-memory processing utilizing one or more processors and one or more RAM devices")
one or more processors being configured to: receive, from a plurality of autonomous vehicles (AVs) operating as a fleet while navigating in a real-world driving environment, AV location data, AV battery data and AV sensor data; (see at least [0037]; "one or more embodiments of the ADV navigation system network (described with reference to FIG. 6) can function to aide a fleet of ADVs to route and navigate a plurality of ADV..the vehicle identification can be transmitted over a network to a remote navigation service (RNS) that resides within one or more nodes 502 residing within an ADV network 610 that enables the RNS to check the status of each the ADV including the SOC (and, optionally SOH) of each battery stack…The vehicle identification can include occupant sensory and/or identification data, data concerning a route and/or other navigation data, and/or sensory, navigation, control and/or any other data discussed herein concerning the vehicle, the route, and/or the occupants therein.) Szubbocsev outlines the Remote Navigation Service being able to receive location data and battery data from a plurality of autonomous vehicles.
determine, based on the AV location data and AV dispatch information, a first predicted energy usage for routing each of the plurality of AVs to one or more waypoints, (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV)
determine, based on AV maintenance facility location data, a second predicted energy usage for routing each of the plurality of AVs to one or more AV maintenance facilities; (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV) Szubbocsev teaches a predicted energy usage for routing an AV to a location, which can therefore be applied to estimating a predicted energy usage to the AV maintenance facility.
determine, based on the first predicted energy usage, the second predicted energy usage, and the AV battery data, a projected battery charge state for each of the plurality of AVs; (see at least [0031]; "Once a route is generated utilizing one or more techniques as described herein, the state of charge (SOC) of the battery stack is determined") The route taught by Szubbocsev can include a first and second predicted energy usage, as well as the projected battery charge state for each AV.
send routing instructions to one or more of the plurality of AVs that are based on the projected battery charge state, (see at least [0037,0067]; FIG. 1 illustrates at least a portion of an ADV navigation system (e.g., ADV 602) and generally illustrates one or more of its capabilities including generating a route for an ADV that includes a starting point A and a first predetermined destination B (D.sub.N), using input data, sensed data, received data and/or other data to autonomously navigate the ADV from a geographical starting point A to a geographical destination point B, and automatically determining, utilizing sensed data, received data and/or other data, if the ADV can navigate the original current route R.sub.N to reach the predetermined geographical destination represented at point B utilizing a battery stack with its current state of charge (SOC) (and, optionally, its current state of health (SOH)).
Scubboczev does not explicitly teach a memory storing a trained neural network; and wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Pathipati teaches a memory storing a trained neural network; and (see at least [137]; " For example, in some instances, the components in the memory 922 and 936 can be implemented as a neural network.")
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 Scubboczev to incorporate teachings of Pathipati which teaches a memory with a trained neural network in order to be able to execute the method from a stored location.
Combination of Scubboczev and Pathipati do not explicitly teach wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Zhu teaches wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; (see at least [12, 13]; "
The examples set forth herein include dynamic driving models and energy estimation algorithms for accurately estimating total trip energy. The examples include a dynamic driving model (e.g., a neural network, such as a neural network toolbox (NNT), a NARX (nonlinear autoregressive network with exogenous inputs) network, or other type of machine-learning network) configured to predict vehicle speed specific to a given driver over a total trip.
(13) Accordingly, the dynamic driving model learns and accounts for individual driver acceleration, deceleration, and speed habits relative to traffic conditions and road features.")
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 Scubboczev to incorporate teachings of Zhu which teaches predicting the energy usage using a neural network based on a variety of travel conditions in order to most accurately predict how far the vehicle can travel.
Combination of Scubboczev, Pathipati and Zhu do not explicitly teach wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Houle teaches wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
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 Scubboczev to incorporate teachings of Houle which teaches routing instructions to a maintenance facility, anticipate a demand and route the vehicles to the facilities prior to the demand in order to ensure enough vehicles will be available when the demand is at it’s peak.
Regarding Claim 5, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Scubboczev discloses the fleet management system of claim 1, wherein the one or more processors are further configured to: determine that the projected battery charge state is less than a threshold battery charge state. (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV.")
Regarding Claim 6, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Scubboczev discloses the fleet management system of claim 1, wherein the first predicted energy usage is less than the second predicted energy usage, and wherein the routing instructions include instructions to the one or more waypoints (see at least [0070, 0071]; "With the aid of on-board computer 204, one or more nodes 502 may transmit one or a series (i.e., one or more) of navigable routes from the ADV's current position to one or a series of predetermined destinations that may be utilized by one or more on-board computers 204 residing in one or more ADVs 602 in each of their mapping, route generation and navigating activities described herein with reference to FIGS. 7-10C. Each of the routes generated and/or obtained along with any information associated with each of the routes and/or navigable pathways included in any one of the routes may be stored in map storage database 506 for retrieval by the mapping system 508, ADV reference system 510, routing system 512 and/or occupant ID system 522 for use in assisting one or more ADVs….With the aid of on-board computer 204, one or more nodes 502 may transmit one or a series (i.e., one or more) of navigable routes that includes the ADV's current position, a predetermined starting geographical position or a scheduled starting position and one or a series of predetermined destinations (e.g., destinations that can be determined due to input by an ADV occupant utilizing a GUI (not shown), scheduled utilizing a mobile device, laptop or desktop computer, and/or received by one or more nodes 502). The one or more nodes 502 can also transmit routing and mapping information concerning the one or more navigable pathways or relevant portions of one or more pathways included in a route that is transmitted to an ADV. This information can include inclination information, traffic information, estimated idling/stop time, speed information, environmental conditions, temperature information, power required by one or more ADV sensors, power required by one or more ADV components/devices, and any other information that would impact electrical energy discharge or accumulation. This information can be analyzed by an on-board computer 204 to determine its impact upon the state of charge (SOC) of the relevant battery stack."
Regarding Claim 10, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Scubboczev discloses the fleet management system of claim 1, wherein the first predicted energy usage and the second predicted energy usage are further based on at least one of a travel time, a road condition, a weather condition, a time of day, a traffic condition, and a vehicle attribute. (see at least ¶ [0068]; "Utilizing routing information for each generated route such as, for example, traffic patterns, mapping information that includes the geographical length (meters, kilometers, miles, etc.) and angles of inclination of one or more navigable pathways, the angles of curvature of each curve included within one or more navigable pathways, environmental conditions (e.g., rain, snow, clear, temperature, wind speed, etc.) and other information (e.g., rate of speed, distance, time of travel, etc.) described herein, and information concerning the ADV itself (e.g., transmission health, battery stack health, etc.) enables the microcontroller 410 to estimate the energy gains and losses incurred by the battery stack 402 or one or more batteries 404 due to each of these and other battery stress events in advance."
Regarding claim 11, Szubbocsev discloses A method comprising: receiving, from a plurality of autonomous vehicles (AVs) operating as a fleet while navigating in a real-world driving environment, AV location data, AV battery data and AV sensor data; (see at least [0037]; "one or more embodiments of the ADV navigation system network (described with reference to FIG. 6) can function to aide a fleet of ADVs to route and navigate a plurality of ADV..the vehicle identification can be transmitted over a network to a remote navigation service (RNS) that resides within one or more nodes 502 residing within an ADV network 610 that enables the RNS to check the status of each the ADV including the SOC (and, optionally SOH) of each battery stack…The vehicle identification can include occupant sensory and/or identification data, data concerning a route and/or other navigation data, and/or sensory, navigation, control and/or any other data discussed herein concerning the vehicle, the route, and/or the occupants therein.) Szubbocsev outlines the Remote Navigation Service being able to receive location data and battery data from a plurality of autonomous vehicles.
determine, based on the AV location data and AV dispatch information, a first predicted energy usage for routing each of the plurality of AVs to one or more waypoints, (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV)
determine, based on AV maintenance facility location data, a second predicted energy usage for routing each of the plurality of AVs to one or more AV maintenance facilities; (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV) Szubbocsev teaches a predicted energy usage for routing an AV to a location, which can therefore be applied to estimating a predicted energy usage to the AV maintenance facility.
determine, based on the first predicted energy usage, the second predicted energy usage, and the AV battery data, a projected battery charge state for each of the plurality of AVs; (see at least [0031]; "Once a route is generated utilizing one or more techniques as described herein, the state of charge (SOC) of the battery stack is determined") The route taught by Szubbocsev can include a first and second predicted energy usage, as well as the projected battery charge state for each AV.
send routing instructions to one or more of the plurality of AVs that are based on the projected battery charge state, (see at least [0037,0067]; FIG. 1 illustrates at least a portion of an ADV navigation system (e.g., ADV 602) and generally illustrates one or more of its capabilities including generating a route for an ADV that includes a starting point A and a first predetermined destination B (D.sub.N), using input data, sensed data, received data and/or other data to autonomously navigate the ADV from a geographical starting point A to a geographical destination point B, and automatically determining, utilizing sensed data, received data and/or other data, if the ADV can navigate the original current route R.sub.N to reach the predetermined geographical destination represented at point B utilizing a battery stack with its current state of charge (SOC) (and, optionally, its current state of health (SOH)).
Scubboczev does not explicitly teach a memory storing a trained neural network; and wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Pathipati teaches a memory storing a trained neural network; and (see at least [137]; " For example, in some instances, the components in the memory 922 and 936 can be implemented as a neural network.")
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 Scubboczev to incorporate teachings of Pathipati which teaches a memory with a trained neural network in order to be able to execute the method from a stored location.
Pathipati does not explicitly teach wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Zhu teaches wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; (see at least [12, 13]; "
The examples set forth herein include dynamic driving models and energy estimation algorithms for accurately estimating total trip energy. The examples include a dynamic driving model (e.g., a neural network, such as a neural network toolbox (NNT), a NARX (nonlinear autoregressive network with exogenous inputs) network, or other type of machine-learning network) configured to predict vehicle speed specific to a given driver over a total trip.
(13) Accordingly, the dynamic driving model learns and accounts for individual driver acceleration, deceleration, and speed habits relative to traffic conditions and road features.")
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 Scubboczev to incorporate teachings of Zhu which teaches predicting the energy usage using a neural network based on a variety of travel conditions in order to most accurately predict how far the vehicle can travel.
Zhu does not explicitly teach wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Houle teaches wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
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 Scubboczev to incorporate teachings of Houle which teaches routing instructions to a maintenance facility, anticipate a demand and route the vehicles to the facilities prior to the demand in order to ensure enough vehicles will be available when the demand is at it’s peak.
Regarding Claim 15, Scubboczev discloses the method of claim 11, further comprising: determining that the projected battery charge state is less than a threshold battery charge state (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV.")
Regarding Claim 16, Scubboczev discloses the method of claim 11, wherein the first predicted energy usage is less than the second predicted energy usage, and wherein the routing instructions include instructions to the one or more waypoints (see at least [0070, 0071]; "With the aid of on-board computer 204, one or more nodes 502 may transmit one or a series (i.e., one or more) of navigable routes from the ADV's current position to one or a series of predetermined destinations that may be utilized by one or more on-board computers 204 residing in one or more ADVs 602 in each of their mapping, route generation and navigating activities described herein with reference to FIGS. 7-10C. Each of the routes generated and/or obtained along with any information associated with each of the routes and/or navigable pathways included in any one of the routes may be stored in map storage database 506 for retrieval by the mapping system 508, ADV reference system 510, routing system 512 and/or occupant ID system 522 for use in assisting one or more ADVs….With the aid of on-board computer 204, one or more nodes 502 may transmit one or a series (i.e., one or more) of navigable routes that includes the ADV's current position, a predetermined starting geographical position or a scheduled starting position and one or a series of predetermined destinations (e.g., destinations that can be determined due to input by an ADV occupant utilizing a GUI (not shown), scheduled utilizing a mobile device, laptop or desktop computer, and/or received by one or more nodes 502). The one or more nodes 502 can also transmit routing and mapping information concerning the one or more navigable pathways or relevant portions of one or more pathways included in a route that is transmitted to an ADV. This information can include inclination information, traffic information, estimated idling/stop time, speed information, environmental conditions, temperature information, power required by one or more ADV sensors, power required by one or more ADV components/devices, and any other information that would impact electrical energy discharge or accumulation. This information can be analyzed by an on-board computer 204 to determine its impact upon the state of charge (SOC) of the relevant battery stack.")
Regarding Claim 19, Scubboczev discloses non-transitory computer-readable media comprising instructions stored thereon which, when executed are configured to cause a computer or processor to: (see at least [0052]; "one or more embodiments of the on-board computer 204 includes an in-memory processing system configured to perform in-memory processing utilizing one or more processors and one or more RAM devices")
from a plurality of autonomous vehicles (AVs) operating as a fleet while navigating in a real-world driving environment,: AV location data, AV battery data and AV sensor data; (see at least [0037]; "one or more embodiments of the ADV navigation system network (described with reference to FIG. 6) can function to aide a fleet of ADVs to route and navigate a plurality of ADV..the vehicle identification can be transmitted over a network to a remote navigation service (RNS) that resides within one or more nodes 502 residing within an ADV network 610 that enables the RNS to check the status of each the ADV including the SOC (and, optionally SOH) of each battery stack…The vehicle identification can include occupant sensory and/or identification data, data concerning a route and/or other navigation data, and/or sensory, navigation, control and/or any other data discussed herein concerning the vehicle, the route, and/or the occupants therein.) Szubbocsev outlines the Remote Navigation Service being able to receive location data and battery data from a plurality of autonomous vehicles.
determine, based on the AV location data and AV dispatch information, a first predicted energy usage for routing each of the plurality of AVs to one or more waypoints, (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV)
determine, based on AV maintenance facility location data, a second predicted energy usage for routing each of the plurality of AVs to one or more AV maintenance facilities; (see at least [0028]; "one or more embodiments of an ADV described herein include an on-board computer that will estimate the electrical power requirements to navigate the ADV over navigable pathways along a generated route to reach the destination and determine if the ADV can safely reach the destination using the stored energy available to operate the ADV) Szubbocsev teaches a predicted energy usage for routing an AV to a location, which can therefore be applied to estimating a predicted energy usage to the AV maintenance facility.
determine, based on the first predicted energy usage, the second predicted energy usage, and the AV battery data, a projected battery charge state for each of the plurality of AVs; (see at least [0031]; "Once a route is generated utilizing one or more techniques as described herein, the state of charge (SOC) of the battery stack is determined") The route taught by Szubbocsev can include a first and second predicted energy usage, as well as the projected battery charge state for each AV.
send routing instructions to one or more of the plurality of AVs that are based on the projected battery charge state, (see at least [0037,0067]; FIG. 1 illustrates at least a portion of an ADV navigation system (e.g., ADV 602) and generally illustrates one or more of its capabilities including generating a route for an ADV that includes a starting point A and a first predetermined destination B (D.sub.N), using input data, sensed data, received data and/or other data to autonomously navigate the ADV from a geographical starting point A to a geographical destination point B, and automatically determining, utilizing sensed data, received data and/or other data, if the ADV can navigate the original current route R.sub.N to reach the predetermined geographical destination represented at point B utilizing a battery stack with its current state of charge (SOC) (and, optionally, its current state of health (SOH)).
Scubboczev does not explicitly teach a memory storing a trained neural network; and wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Pathipati teaches a memory storing a trained neural network; and (see at least [137]; " For example, in some instances, the components in the memory 922 and 936 can be implemented as a neural network.")
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 Scubboczev to incorporate teachings of Pathipati which teaches a memory with a trained neural network in order to be able to execute the method from a stored location.
Pathipati does not explicitly teach wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Zhu teaches wherein the first predicted energy usage is determined using the trained neural network and is based on a predicted travel time, traffic conditions, road conditions, weather, and route characteristics; (see at least [12, 13]; "
The examples set forth herein include dynamic driving models and energy estimation algorithms for accurately estimating total trip energy. The examples include a dynamic driving model (e.g., a neural network, such as a neural network toolbox (NNT), a NARX (nonlinear autoregressive network with exogenous inputs) network, or other type of machine-learning network) configured to predict vehicle speed specific to a given driver over a total trip.
(13) Accordingly, the dynamic driving model learns and accounts for individual driver acceleration, deceleration, and speed habits relative to traffic conditions and road features.")
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 Scubboczev to incorporate teachings of Zhu which teaches predicting the energy usage using a neural network based on a variety of travel conditions in order to most accurately predict how far the vehicle can travel.
Zhu does not explicitly teach wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
However, Houle teaches wherein the routing instructions instruct the respective AV to travel to one of the AV maintenance facilities; anticipate a demand for the plurality of AVs in a geographic area using historical dispatch data and event data; and control one or more AVs of the plurality of AVs to travel to AV maintenance facilities prior to the anticipated demand.
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 Scubboczev to incorporate teachings of Houle which teaches routing instructions to a maintenance facility, anticipate a demand and route the vehicles to the facilities prior to the demand in order to ensure enough vehicles will be available when the demand is at it’s peak.
Claims 2, 3, 4, 7, 12, 13, 14 and 20 are rejected under 35 U.S.C 103 as being unpatentable over Szubbocsev (US20190294173A1) in view of Rakah (US 20180211541 A1).
Regarding Claim 2, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose the fleet management system of claim 1, wherein the one or more processors are further configured to: predict a demand for a portion of the plurality of AVs in a geographic area, wherein the routing instructions are further based on the demand.
However, Rakah teaches the fleet management system of claim 1, wherein the one or more processors are further configured to: predict a demand for a portion of the plurality of AVs in a geographic area, wherein the routing instructions are further based on the demand. (see at least Abstract; "An automated ridesharing dispatch system includes a memory configured to store historical data associated with past demand for ridesharing vehicles in a geographical area and a communications interface. The system also includes at least one processor configured to access the memory and to use the historical data to predict imminent demand of ridesharing requests including predicting general zones in the geographical area associated with imminent demand, select a holding zone for prepositioning empty ridesharing vehicles in order to expedite satisfaction of the predicted imminent demand)
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 Szubbocsev to incorporate teachings of Rakah to predict a demand for a geographic area in order to have enough vehicles available to service the area.
Regarding Claim 3, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose the fleet management system of claim 2, wherein the demand is based on historical dispatch information associated with the geographic area.
However, Rakah teaches the fleet management system of claim 2, wherein the demand is based on historical dispatch information associated with the geographic area. (see at least Abstract; "An automated ridesharing dispatch system includes a memory configured to store historical data associated with past demand for ridesharing vehicles in a geographical area and a communications interface. The system also includes at least one processor configured to access the memory and to use the historical data to predict imminent demand of ridesharing requests including predicting general zones in the geographical area associated with imminent demand, select a holding zone for prepositioning empty ridesharing vehicles in order to expedite satisfaction of the predicted imminent demand)
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 Szubbocsev to incorporate teachings of Rakah to base the demand on historical geographic dispatch information in order to accurately predict a demand in order to have enough vehicles available to service the area.
Regarding Claim 4, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not explicitly disclose The fleet management system of claim 2, wherein the demand is based on event data associated with the geographic area, the event data comprising a venue-egress profile that estimates the timing and magnitude of post-event passenger demand, wherein the demand signal is weighted by the venue-egress profile and by a calculated energy buffer that each AV must possess to serve the event and reach a maintenance facility.
However, Rakah The fleet management system of claim 2, wherein the demand is based on event data associated with the geographic area, (see at least [0289]; "the area with predicted demand is identified using a request history (e.g., stored in database 1250) and/or real-time information (e.g., using event information retrieved from one or more memories and/or using the communications interface). For example, route module 1220 may determine that requests are expected in an area near a stadium after a sporting event concludes..)")
the event data comprising a venue-egress profile that estimates the timing and magnitude of post-event passenger demand, and (see at least [329]; "For further example, the historical data may include data analyzed based on proximity to a given venue when a show or event ends, begins, or is occurring. For example, the historical data may include an average or median number of rides requested when a concert, play, etc. ends at a given venue on a weekend night.")
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 Szubbocsev to incorporate teachings of Rakah to base the demand on event data in order to accurately predict a demand in order to have enough vehicles available to service the area.
Rakah does not explicitly teach wherein the demand signal is weighted by the venue-egress profile and by a calculated energy buffer that each AV must possess to serve the event and reach a maintenance facility.
However, Pathipati teaches wherein the demand signal is weighted by the venue-egress profile and by a calculated energy buffer that each AV must possess to serve the event and reach a maintenance facility. (see at least [40]; " At operation 210, the process 200 may include determining a threshold power state required to provide a service offered by the vehicle 206. In some examples, the threshold power state may be based on a period of time which the vehicle 206 may provide the service, a geographic region in which the vehicle 206 will be providing the service, a size of the geographic region, a number of additional vehicles in the fleet providing the service, and/or a current and/or predicted level of demand associated with the service. ")
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 Scubboczev to incorporate teachings of Pathipati which teaches an event data that weighs the profile and energy demand so that the vehicles must have a minimum charge to serve the event in order to ensure they can reach the destinations of the users.
Regarding Claim 7, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose the fleet management system of claim 1, wherein the AV dispatch information includes at least one of a passenger pickup from the one or more waypoints, a passenger drop-off from the one or more waypoints, and a delivery to the one or more waypoints.
However, Rakah teaches the fleet management system of claim 1, wherein the AV dispatch information includes at least one of a passenger pickup from the one or more waypoints, a passenger drop-off from the one or more waypoints, and a delivery to the one or more waypoints. (see at least ¶[0018, 0460, 00479]; " an automated ridesharing dispatch system is disclosed. The system may include a communications interface, a memory, a plurality of communication devices, a plurality of ridesharing vehicles, and at least one processor. The communications interface may be configured to receive ride requests from a plurality of users, wherein each ride request includes a starting point and a desired destination… ride request module 2702 may process the ride requests received from the communications interface and assign to a ridesharing vehicle the plurality of users for pick up at a plurality of differing pick-up locations and for delivery to a plurality of differing drop-off locations…..ride request module 2702 may process the ride requests received from the communications interface and assign to a single ridesharing vehicle the plurality of users for pick up at a plurality of differing pick-up locations and for delivery to a plurality of differing drop-off locations. ")
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 Szubbocsev to incorporate teachings of Rakah to include the passenger pickup waypoint, passenger drop off waypoints, and delivery waypoints in the AV dispatch information in order to be able to predict whether the battery will have enough charge to last the entire duration of multiple waypoints.
Regarding Claim 12, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose the method of claim 11, further comprising: predicting a demand for a portion of the plurality of AVs in a geographic area, wherein the routing instructions are further based on the demand.
However, Rakah teaches the method of claim 11, further comprising: predicting a demand for a portion of the plurality of AVs in a geographic area, wherein the routing instructions are further based on the demand. (see at least Abstract; "An automated ridesharing dispatch system includes a memory configured to store historical data associated with past demand for ridesharing vehicles in a geographical area and a communications interface. The system also includes at least one processor configured to access the memory and to use the historical data to predict imminent demand of ridesharing requests including predicting general zones in the geographical area associated with imminent demand, select a holding zone for prepositioning empty ridesharing vehicles in order to expedite satisfaction of the predicted imminent demand)
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 Szubbocsev to incorporate teachings of Rakah to predict a demand for a geographic area in order to have enough vehicles available to service the area.
Regarding Claim 13, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose the method of claim 12, wherein the demand is based on historical dispatch information associated with the geographic area.
However, Rakah teaches the method of claim 12, wherein the demand is based on historical dispatch information associated with the geographic area. (see at least Abstract; "An automated ridesharing dispatch system includes a memory configured to store historical data associated with past demand for ridesharing vehicles in a geographical area and a communications interface. The system also includes at least one processor configured to access the memory and to use the historical data to predict imminent demand of ridesharing requests including predicting general zones in the geographical area associated with imminent demand, select a holding zone for prepositioning empty ridesharing vehicles in order to expedite satisfaction of the predicted imminent demand)
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 Szubbocsev to incorporate teachings of Rakah to base the demand on historical geographic dispatch information in order to accurately predict a demand in order to have enough vehicles available to service the area.
Regarding Claim 14, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 12 as discussed above, furthermore, Szubbocsev does not explicitly disclose The fleet management system of claim 2, wherein the demand is based on event data associated with the geographic area, the event data comprising a venue-egress profile that estimates the timing and magnitude of post-event passenger demand, wherein the demand signal is weighted by the venue-egress profile and by a calculated energy buffer that each AV must possess to serve the event and reach a maintenance facility.
However, Rakah The fleet management system of claim 2, wherein the demand is based on event data associated with the geographic area, (see at least [0289]; "the area with predicted demand is identified using a request history (e.g., stored in database 1250) and/or real-time information (e.g., using event information retrieved from one or more memories and/or using the communications interface). For example, route module 1220 may determine that requests are expected in an area near a stadium after a sporting event concludes..)")
the event data comprising a venue-egress profile that estimates the timing and magnitude of post-event passenger demand, and (see at least [329]; "For further example, the historical data may include data analyzed based on proximity to a given venue when a show or event ends, begins, or is occurring. For example, the historical data may include an average or median number of rides requested when a concert, play, etc. ends at a given venue on a weekend night.")
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 Szubbocsev to incorporate teachings of Rakah to base the demand on event data in order to accurately predict a demand in order to have enough vehicles available to service the area.
Rakah does not explicitly teach wherein the demand signal is weighted by the venue-egress profile and by a calculated energy buffer that each AV must possess to serve the event and reach a maintenance facility.
However, Pathipati teaches wherein the demand signal is weighted by the venue-egress profile and by a calculated energy buffer that each AV must possess to serve the event and reach a maintenance facility. (see at least [40]; " At operation 210, the process 200 may include determining a threshold power state required to provide a service offered by the vehicle 206. In some examples, the threshold power state may be based on a period of time which the vehicle 206 may provide the service, a geographic region in which the vehicle 206 will be providing the service, a size of the geographic region, a number of additional vehicles in the fleet providing the service, and/or a current and/or predicted level of demand associated with the service. ")
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 Scubboczev to incorporate teachings of Pathipati which teaches an event data that weighs the profile and energy demand so that the vehicles must have a minimum charge to serve the event in order to ensure they can reach the destinations of the users.
Regarding Claim 20, Szubbocsev does not disclose the non-transitory computer-readable media of claim 19, comprising further instructions configured to cause the computer or processor to: predict a demand for a portion of the plurality of AVs in a geographic area, wherein the routing instructions are further based on the demand.
However, Rakah teaches the non-transitory computer-readable media of claim 19, comprising further instructions configured to cause the computer or processor to: predict a demand for a portion of the plurality of AVs in a geographic area, wherein the routing instructions are further based on the demand. (see at least Abstract; "An automated ridesharing dispatch system includes a memory configured to store historical data associated with past demand for ridesharing vehicles in a geographical area and a communications interface. The system also includes at least one processor configured to access the memory and to use the historical data to predict imminent demand of ridesharing requests including predicting general zones in the geographical area associated with imminent demand, select a holding zone for prepositioning empty ridesharing vehicles in order to expedite satisfaction of the predicted imminent demand)
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 Szubbocsev to incorporate teachings of Rakah to predict a demand for a geographic area in order to have enough vehicles available to service the area.
Claims 8, 9, 17, 18 are rejected under 35 U.S.C 103 as being unpatentable over Szubbocsev (US20190294173A1) in view of Starns (US11663561B2).
Regarding Claim 8, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose The fleet management system of claim 1, wherein the one or more processors are further configured to:determine, for each of the plurality of AVs, a predicted service requirement derived from on-board diagnostic sensor data and maintenance history, wherein the predicted service requirement is based on analysis of vehicle health telemetry, fault codes, calibration counters, wear sensors, and a time-to-service threshold, and wherein the routing instructions are further based on the predicted service requirement.
However, Starns teaches The fleet management system of claim 1, wherein the one or more processors are further configured to:determine, for each of the plurality of AVs, a predicted service requirement derived from on-board diagnostic sensor data and maintenance history, wherein the predicted service requirement is based on analysis of vehicle health telemetry, fault codes, calibration counters, wear sensors, and a time-to-service threshold, and wherein the routing instructions are further based on the predicted service requirement. (see at least [11]; "Particular embodiments described herein relate to a service facility for servicing autonomous EVs that is located at a fixed location. In particular embodiments, the service facility may include a number of service bays or regions to consolidate the maintenance operations for the AVs in a single facility. As an example and not by way of limitation, these service regions may include a charging/fueling region, cleaning region, or tire changing/rotation region. In addition, one or more service region (e.g., the charging region) may also be configured to concurrently perform other maintenance or services on the AVs (e.g., update software). In particular embodiments, a service facility management system, described in further detail below, may determine one or more sequences of service tasks to be performed on the AVs, coordinate the flow of the AVs within the service facility, and/or assign the AVs to a particular region of the service facility for particular servicing, as an AV is not configured to handle such tasks, especially across a fleet of vehicles and/or to consider the requirements of the AV within the context of the larger fleet of AVs.")
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 Szubbocsev to incorporate teachings of Starns to determine a service requirement of the vehicles in order to maintain their operation and maximize their longevity as vehicles in the fleet.
Regarding Claim 9, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not The fleet management system of claim 1, wherein the one or more processors are further configured to:determine an operational metric for the one or more AV maintenance facilities, wherein the operational metric includes a predicted wait-time for each facility, the predicted wait-time being calculated based on current occupancy, historical service throughput, and scheduled arrivals, and wherein the routing instructions are further based on the operational metric so as to minimize the predicted wait-time.
The fleet management system of claim 1, wherein the one or more processors are further configured to:determine an operational metric for the one or more AV maintenance facilities, wherein the operational metric includes a predicted wait-time for each facility, the predicted wait-time being calculated based on current occupancy, historical service throughput, and scheduled arrivals, and wherein the routing instructions are further based on the operational metric so as to minimize the predicted wait-time (see at least ¶ [35]; "In particular embodiments, logistics module 417 may identify a service facility that is suitable for servicing AV 140. The identification may be based at least on particular service work to be performed on AV 140 and/or based at least on the service facilities' respective capabilities. Additional factors may include capabilities of a service facility, total capacity, availability (open service bays), or distance from the current location of AV 140 to the location of the service facility.")
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 Szubbocsev to incorporate teachings of Starns to determine an operational metric for the maintenance facility in order to route them to the appropriate maintenance facility to coordinate the usage of the facility and maximize vehicle availability.
Regarding Claim 17, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose The method of claim 11, further comprising: determining, for each of the plurality of AVs, a predicted service requirement derived from on-board diagnostic sensor data and maintenance history, wherein the predicted service requirement is based on analysis of vehicle health telemetry, fault codes, calibration counters, wear sensors, and a time-to-service threshold, and whereinthe routing instructions are further based on the predicted service reguirement
However, Starns The method of claim 11, further comprising: determining, for each of the plurality of AVs, a predicted service requirement derived from on-board diagnostic sensor data and maintenance history, wherein the predicted service requirement is based on analysis of vehicle health telemetry, fault codes, calibration counters, wear sensors, and a time-to-service threshold, and whereinthe routing instructions are further based on the predicted service reguirement (see at least [11]; "Particular embodiments described herein relate to a service facility for servicing autonomous EVs that is located at a fixed location. In particular embodiments, the service facility may include a number of service bays or regions to consolidate the maintenance operations for the AVs in a single facility. As an example and not by way of limitation, these service regions may include a charging/fueling region, cleaning region, or tire changing/rotation region. In addition, one or more service region (e.g., the charging region) may also be configured to concurrently perform other maintenance or services on the AVs (e.g., update software). In particular embodiments, a service facility management system, described in further detail below, may determine one or more sequences of service tasks to be performed on the AVs, coordinate the flow of the AVs within the service facility, and/or assign the AVs to a particular region of the service facility for particular servicing, as an AV is not configured to handle such tasks, especially across a fleet of vehicles and/or to consider the requirements of the AV within the context of the larger fleet of AVs.")
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 Szubbocsev to incorporate teachings of Starns to route based on the service need in order to route them to the appropriate maintenance facility to coordinate the usage of the facility and maximize vehicle availability.
Regarding Claim 18, Scubboczev, Pathipati, Zhu and Houle, in combination, disclose limitations of claim 1 as discussed above, furthermore, Szubbocsev does not disclose The method of claim 11, further comprising: determining an operational metric for the one or more AV maintenance facilities, wherein the operational metric includes a predicted wait-time for each facility, the predicted wait-time being calculated based on current occupancy, historical service throughput, and scheduled arrivals, and wherein the routing instructions are further based on the operational metric so as to minimize the predicted wait-time.
However, Starns teaches The method of claim 11, further comprising: determining an operational metric for the one or more AV maintenance facilities, wherein the operational metric includes a predicted wait-time for each facility, the predicted wait-time being calculated based on current occupancy, historical service throughput, and scheduled arrivals, and wherein the routing instructions are further based on the operational metric so as to minimize the predicted wait-time(see at least ¶ [35]; "In particular embodiments, logistics module 417 may identify a service facility that is suitable for servicing AV 140. The identification may be based at least on particular service work to be performed on AV 140 and/or based at least on the service facilities' respective capabilities. Additional factors may include capabilities of a service facility, total capacity, availability (open service bays), or distance from the current location of AV 140 to the location of the service facility.")
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 Szubbocsev to incorporate teachings of Starns to determine an operational metric for the maintenance facility in order to route them to the appropriate maintenance facility to coordinate the usage of the facility and maximize vehicle availability.
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 HANA VICTORIA HALL whose telephone number is (571)272-5289. The examiner can normally be reached M-F 9-5.
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, Rachid Bendidi can be reached at 5712724896. 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.
/HANA VICTORIA HALL/Examiner, Art Unit 3664
/RACHID BENDIDI/ Supervisory Patent Examiner, Art Unit 3664