DETAILED ACTION
Notice of Pre-AIA or AIA Status
The present application, filed on or after March 16, 2013, is being examined under the first inventor to file provisions of the AIA .
Continued Examination Under 37 CFR 1.114
A request for continued examination under 37 CFR 1.114, including the fee set forth in 37 CFR 1.17(e), was filed in this application after final rejection. Since this application is eligible for continued examination under 37 CFR 1.114, and the fee set forth in 37 CFR 1.17(e) has been timely paid, the finality of the previous Office action has been withdrawn pursuant to 37 CFR 1.114. Applicant's submission filed on 4/26/2026 has been entered.
Response to Arguments
Applicant’s arguments, filed 4/26/2026, have been fully considered and the examiner’s responses are given below.
The claim objections are withdrawn.
The 35 U.S.C. 112(b) rejections are withdrawn.
The 35 U.S.C. 103 rejections are not withdrawn.
Applicant argues that Schildwaechter’s system provides two different planning units, rather than a single artificial intelligence model. Examiner respectfully disagrees as it is obvious that the two artificial intelligence models taught by the combination of Benisch and Schildwaechter can essentially be defined/combined as one larger artificial intelligence model. Under broadest reasonable interpretation, an artificial intelligence model is able to be composed of multiple smaller models. In addition, combining these two artificial intelligence models that uses separate steps would perform equally well as a single artificial intelligence model that decides how to output, based on the type of input.
Applicant argues that the map-less surroundings modeling receives the same input and provides the same output. Examiner respectfully disagrees. It appears the map-less surroundings modeling does not use the HD map that is used in the normal mode. Also, it appears the optimal trajectory is different for the map-less mode and map mode.
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 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, 7-12, and 14-19 are rejected under 35 U.S.C. 103 as being unpatentable over Benisch (US 20210191407 A1, cited in a previous office action) in view of Schildwaechter (US 20230112417 A1, cited in a previous office action).
Claim 1
Benisch teaches:
A method of providing adaptive decision for autonomous driving applications, the method comprises (Benisch - Paragraphs 0034-0035);
obtaining sensor data input relating to an environment of a vehicle (Benisch - Paragraph 0075);
determining a driving scenario, based on the sensor input data (Benisch - Paragraphs 0025-0030, 0075);
providing, by an artificial intelligence model, a special purpose decision making that is adaptive to a road segment being approached by the vehicle, in accordance with the driving scenario, when obtaining a road segment indication that is indicative of the road segment (Benisch - Paragraphs 0025, 0031-0032, Fig. 1B) “separate localized machine-learning models can be trained for each road segment that a vehicle may travel”
wherein the artificial intelligence model, is trained, in a scenario-level learning by using sensed data captured in the environment of the vehicle (Benisch - Paragraphs 0025-0028) “Generalized machine-learning models are trained based on many different environments where the majority of events/training data are not unusual features or events”
and is further trained in a special purpose learning, by collecting special-purpose data relating directly to the road segment indication and reflecting behavioral data of drivers captured along the road segment (Benisch - Paragraphs 0025, 0031-0032, Fig. 1B) “separate localized machine-learning models can be trained for each road segment that a vehicle may travel”
outputting by the scenario-level decision making or the special-purpose decision making, an instruction executable by an autonomous control unit of the vehicle to perform an autonomous driving related operation that comprises changing at least one of a speed, direction or acceleration of the vehicle; and performing the autonomously driving related operation (Benisch - Paragraph 0025, 0100) “control module 1025 may transmit commands to an accelerator actuator”
Benisch does not teach:
Providing a scenario level decision making artificial intelligence (AI) model when provided with the driving scenario and not with the road segment.
However, Schildwaechter teaches:
providing, by the artificial intelligence model, a scenario-level decision making in accordance with the driving scenario when provided with a driving scenario indication and not with the road segment indication; wherein the driving scenario indicator is indicative of the driving scenario (Schildwaechter - Paragraphs 0028-0030, 0038) “If no suitable localization result is available, switching module 160, in contrast, switches to the safety mode, in this case trajectory 422 ascertained in a map-less manner”
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Benisch with providing a scenario level decision making artificial intelligence (AI) model when provided with the driving scenario and not with the road segment of Schildwaechter with a reasonable expectation of success. One of ordinary skill in the art would understand that both Benisch and Schildwaechter are in the field of driving models based on location. One would have been motivated to combine as this achieves a robust autonomous driving system (Schildwaechter – Paragraph 0005).
Claim 2
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 1 as seen above.
Benisch further teaches:
the road segment is a given road segment (Paragraphs 0031-0037, Fig. 1B);
the driving scenario is a given driving scenario (Paragraphs 0025-0030);
and the special- purpose decision making is associated with the given road segment (Paragraphs 0025-0037, Fig. 1B).
Claim 3
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 2 as seen above.
Benisch further teaches:
providing the special-purpose decision making that is associated with the given road segment, when the vehicle faces the given driving scenario and is at an equivalent road segment (Paragraph 0025);
the equivalent road segment differs by location from the given driving scenario (Paragraph 0025);
and is associated with a same behavioral data of drivers as the behavioral data of drivers captured along the given road segment (Paragraph 0025).
Claim 4
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 2 as seen above.
Benisch further teaches:
providing another special-purpose decision making that is ignorant to behavioral data of drivers captured along another road segment (Paragraph 0031-0032);
when the vehicle faces the given driving scenario (Paragraph 0031-0032);
and the autonomous driving application of the vehicle was not trained using special-purpose data that reflects behavioral data of drivers captured along the other road segment (Paragraph 0031-0032).
Claim 5
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 1 as seen above.
Benisch further teaches:
obtaining the road segment indication is by means of localization or involves interacting with a vehicle localization process (Paragraphs 0031-0037, 0075-0077).
Claim 7
Benisch teaches:
A non-transitory computer readable medium storing instructions that, when executable by at least one processing device, cause the device to (Benisch - Paragraphs 0101-0106, Fig. 11).
All of the other limitations have been examined with respect to claim 1. Please see the rejection above.
Claims 8-11
All of the limitations of these claims have been examined with respect to the claims 2-5. Please see the rejections above.
Claim 12
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 7 as seen above.
Benisch further teaches:
obtaining the road segment indication involves interacting with a vehicle localization process (Benisch - Paragraphs 0031-0037, 0075-0077).
Claim 14
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 1 as seen above.
Benisch further teaches:
training the artificial intelligence model in the scenario-level learning to provide the scenario- level decision in accordance with the driving scenario (Benisch - Paragraphs 0025-0028) “Generalized machine-learning models are trained based on many different environments where the majority of events/training data are not unusual features or events”
and training the artificial intelligence model in the special purpose learning by collecting special-purpose data relating directly to the road segment indication and reflecting behavioral data of drivers captured along the road segment (Benisch - Paragraphs 0025, 0031-0032, Fig. 1B) “separate localized machine-learning models can be trained for each road segment that a vehicle may travel”
Claim 15
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 14 as seen above.
Benisch further teaches:
performing an additional scenario-level learning of an additional artificial intelligence model by using sensed data captured in the environment of the vehicle, in accordance with an additional driving scenario (Benisch - Paragraphs 0025-0028);
and incorporating, in a training of the additional artificial intelligence model, the special-purpose learning of the additional artificial intelligence model with the additional scenario-level learning of the additional artificial intelligence model, to provide an additional special-purpose decision making that is adaptive to the road segment indication, in accordance with the additional driving scenario (Benisch - Paragraphs 0025-0035, Fig. 1B).
Claim 16
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 14 as seen above.
Benisch further teaches:
performing another special-purpose learning by collecting additional special-purpose data relating directly to an additional road segment indication of an additional road segment in the driving path of the vehicle, and feeding the artificial intelligence model with the additional collected special-purpose data, wherein the additional collected special-purpose data reflects behavioral data of drivers captured along the additional road segment (Benisch - Paragraphs 0025-0035, 0075-0077, Fig. 1B).
Claim 17
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 14 as seen above.
Benisch further teaches:
identifying an equivalent road segment that is associated with a same behavioral data of drivers as the behavioral data of drivers captured along the road segment (Benisch - Paragraph 0025);
and associating the equivalent road segment with the special-purpose learning related to the road segment (Benisch - Paragraph 0025-0032).
Claim 18
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 14 as seen above.
Benisch further teaches:
the incorporating of the special-purpose learning of the artificial intelligence model with the scenario- level learning involves (Benisch - Paragraph 0025-0035);
training at least a first head of a neural network implementing the artificial intelligence model to provide the scenario-level decision making in accordance with the driving scenario (Benisch - Paragraph 0025-0035);
and training at least a second head of the neural network to provide the special-purpose decision making that is adaptive to the road segment indication, in accordance with the driving scenario (Benisch - Paragraph 0025-0035).
Claim 19
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 14 as seen above.
Benisch further teaches:
training the artificial intelligence model to: provide the scenario-level decision making in accordance with the driving scenario when provided with a driving scenario indication (Benisch - Paragraph 0025-0031, 0075);
and providing the special-purpose decision making that is adaptive to the road segment indication, in accordance with the driving scenario, when provided with the driving scenario indication and the road segment indication (Benisch - Paragraph 0025-0035, 0075).
Claim 6 is rejected under 35 U.S.C. 103 as being unpatentable over Benisch and Schildwaechter, as applied to claim 1 above, and further in view of Zhang (US 20250103779 A1, cited in a previous office action).
Claim 6
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 1 as seen above.
Benisch does not teach:
the scenario is indicative of an aggressiveness of pedestrians and vehicle.
However, Zhang teaches:
the scenario is indicative of an aggressiveness of pedestrians and vehicle (Zhang - Paragraphs 0045) “The dynamic actor information may include route information for the actors, desired behaviors, or aggressiveness”.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Benisch with the scenario indicating an aggressiveness of pedestrians and vehicles of Zhang with a reasonable expectation of success. One of ordinary skill in the art would understand that both Benisch and Zhang are in the field of autonomous driving models. One would have been motivated to combine as this improves safety and comfort of vehicles (Zhang – Paragraph 0026, 0109).
Claim 20 is rejected under 35 U.S.C. 103 as being unpatentable over Benisch and Schildwaechter, as applied to claim 1 above, and further in view of Zhang 2 (US 20210323552 A1, cited in a previous office action).
Claim 20
The combination of Benisch and Schildwaechter teaches all of the limitations of claim 14 as seen above.
Benisch further teaches:
training the artificial intelligence model in the special purpose learning (Benisch - Paragraphs 0025, 0031-0032, Fig. 1B) “separate localized machine-learning models can be trained for each road segment that a vehicle may travel”
Benisch does not teach:
Training AI models only when there is at least a defined amount of data relating to the road segment.
However, Zhang 2 teaches:
only when there is at least a defined amount of special-purpose data relating directly to the road segment indication (Zhang 2 - Paragraphs 0071-0072) “After determining that the historical driving data reaches a certain amount, the initial longitudinal dynamics model may be trained”.
It would have been obvious to one of ordinary skill in the art before the effective filing date of the invention to modify the invention of Benisch with training AI models only when there is at least a defined amount of data relating to the road segment of Zhang 2 with a reasonable expectation of success. One of ordinary skill in the art would understand that Benisch and Zhang 2 are both in the field of autonomous driving models. One would have been motivated to combine as achieves an optimal driving model with reduced control errors (Zhang 2 – Paragraph 0077).
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner
should be directed to Matthew Ho whose telephone number is (571) 272-1388. The examiner can
normally be reached on Mon-Thurs 9:00-5:30 EST.
Examiner interviews are available via telephone, in-person, and video conferencing using a USPTO supplied web-based collaboration tool. To schedule an interview, applicant is encouraged to use the USPTO Automated Interview Request (AIR) at http://www.uspto.gov/interviewpractice.
If attempts to reach the examiner by telephone are unsuccessful, the examiner’s supervisor, Navid Z Mehdizadeh can be reached on (571)-272-7691. The fax phone number for the organization where this application or proceeding is assigned is 571-273-8300.
Information regarding the status of an application may be obtained from the Patent Application Information Retrieval (PAIR) system. Status information for published applications may be obtained from either Private PAIR or Public PAIR. Status information for unpublished applications are available through Private PAIR only. For more information about the PAIR system, see https://ppairmy.uspto.gov/pair/PrivatePair. Should you have questions on access to the Private PAIR system, contact the Electronic Business Center (EBC) at (866) 217-9197 (tollfree). If you would like assistance from a USPTO Customer Service Representative or access to the automated information system, call (800) 786-9199 (IN USA OR CANADA) or (571) 272-1000.
/MATTHEW HO/ Examiner, Art Unit 3669
/NAVID Z. MEHDIZADEH/Supervisory Patent Examiner, Art Unit 3669
Prosecution Insights