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 .
Status of the Claims
The claims 1 and 4-16 are currently pending and have been examined. Applicant amended claims 1, 4, 5, 10, 13-16, and cancelled claims 2 and 3.
Response to Arguments/Amendments
The amendment filed July 2, 2026 has been entered. Claims 1 and 4-16 are currently pending in the Application. Applicant’s amendments to the claims have overcome the claim objections and 35 U.S.C. 101 rejections previously set forth in the Non-Final Rejection.
Applicant’s arguments with respect to claim(s) 1, 5-9, 11, and 13-16 under 35 U.S.C. 102 have been considered but are moot because the new ground of rejection does not rely on any reference applied in the prior rejection of record for any teaching or matter specifically challenged in the argument.
Applicant’s arguments with respect to claims 1 and 4-16 under 35 U.S.C. 103 have been fully considered but they are not persuasive.
Applicant argues that although Sane describes a “forgetting rate” as a decrement value applied to occupancy probability, the meaning of the forgetting rate in Sane is different from the forgetting rate of amended claim 1, which applicant characterizes as relating to information regarding an obstacle detected in the past. Applicant additionally argues Sane is directed to updating occupancy confidence of a sensor shadow region derived from LIDAR scan results, while amended claim 1 addresses the problem of retaining obstacle information outside a viewing angle of an imaging unit, where current changes in obstacles cannot be observed. Applicant further argues that obstacle information is more quickly forgotten inside the viewing angle, where current obstacle information can be obtained from a captured image, and that claim 1 as amended is directed to field-of-view dependent retention and the forgetting of past obstacle information, while Sane relates to sensor-shadow occupancy confidence updating (See Applicant’s Remarks, pages 23-25).
The Examiner respectfully disagrees. Applicant’s arguments consider the teachings of Sane individually rather than the combined teachings of Nishino and Sane. As set forth in the rejection, Nishino is relied upon for teaching the limitations of claim 1 concerning the accumulation and forgetting of information regarding previously detected obstacles. Sane is relied upon for teaching the additional limitations concerning the relationship between the predetermined forgetting rates inside and outside the viewing angle. In particular, Sane at paragraph [0038] teaches that the grid cells falling within the current sensor scanning range may be reduced in confidence by a higher “forgetting rate”, while current grid cells that do not fall within the current sensor scanning range may be reduced in confidence by a lower “forgetting rate.” As previously explained, the sensor scanning range corresponds to the claimed viewing angle and the regions inside and outside the scanning range correspond to regions inside and outside the viewing angle. Thus, the combined teachings of Nishino and Sane teach or suggest the claimed predetermined forgetting rate being different between inside and outside the viewing angle, with the forgetting rate inside the viewing angle being higher than the forgetting rate outside the viewing angle. Applicant’s characterization of Sane as being directed to sensor-shadow occupancy confidence updating does not overcome the rejection. Sane is relied upon for the above described relationship between the forgetting rates within and outside the sensor scanning range, while Nishino supplies the underlying limitations concerning accumulated information regarding previously detected obstacles. Further, Applicant’s stated advantages concerning retaining obstacle information where current changes cannot be observed and quickly forgetting obstacle information where current information can be obtained do not distinguish the claimed subject matter to the extent such advantages are not positively recited as additional limitations of the claims. The previously articulated motivation for combining Nishino and Sane therefore remains applicable. Accordingly, the rejections under 35 U.S.C. 103 are maintained.
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.
The factual inquiries for establishing a background for determining obviousness under 35 U.S.C. 103 are summarized as follows:
1. Determining the scope and contents of the prior art.
2. Ascertaining the differences between the prior art and the claims at issue.
3. Resolving the level of ordinary skill in the pertinent art.
4. Considering objective evidence present in the application indicating obviousness or nonobviousness.
This application currently names joint inventors. In considering patentability of the claims the examiner presumes that the subject matter of the various claims was commonly owned as of the effective filing date of the claimed invention(s) absent any evidence to the contrary. Applicant is advised of the obligation under 37 CFR 1.56 to point out the inventor and effective filing dates of each claim that was not commonly owned as of the effective filing date of the later invention in order for the examiner to consider the applicability of 35 U.S.C. 102(b)(2)(C) for any potential 35 U.S.C. 102(a)(2) prior art against the later invention.
Claim(s) 1 and 4-16 is/are rejected under 35 U.S.C. 103 as being unpatentable over NISHINO (JP 2022046408 A) in view of Sane (US 20160216377 A1).
Regarding Claim 1, NISHINO teaches A moving object control system comprising: an imaging unit (See at least paragraph [0014], “The detection device 8 senses the environment and outputs the data to the information processing device 2. That is, the detection device 8 is a sensor that detects a space or an object around the autonomous mobile robot, and generates sensor data necessary for generating and updating an obstacle map. The detection device 8 is, for example, a left and right camera (stereo camera). The detection device 8 generates sensor data including left and right camera data captured by the stereo camera for each frame, and sequentially outputs the sensor data to the information processing device 2. It is assumed that the sensor data is accompanied by time information. Further, the detection device 8 is also simply referred to as a camera.”); a storage device that stores instructions (See at least paragraph [0063], “Returning to FIG. 1, the main storage device 33 is a storage device that stores instructions executed by the processor 31, various data, and the like, and the information stored in the main storage device 33 is read out by the processor 31. The auxiliary storage device 35 is a storage device other than the main storage device 33. The certainty grid map for each category, the obstacle map for each category, the characteristic curve for each category, the sensor data, and the like are stored in the main storage device 33 and the auxiliary storage device 35.”); and at least processor that executes the instructions to: accumulate information on an obstacle detected in a past for each divided region obtained by dividing peripheral regions of a moving object (See at least paragraph [0010], “The information processing apparatus 2 executes an obstacle map generation / update process and an obstacle map-based motion path generation process for the autonomous mobile robot. In particular, the information processing apparatus 2 uses the sensor data to execute an obstacle map update process including a forgetting process for each category that classifies objects (for example, obstacles) existing in the environment (for example, in the office). Further, the information processing apparatus 2 executes the movement route generation using the updated obstacle map”, paragraph [0011], “Here, the obstacle map is information used to generate a movement path of an autonomous moving body and showing the spatial distribution of the existence probability of an object in the environment around the autonomous moving body. The obstacle map is, for example, a grid map held in an OGM (Occupied Grid Map) format in which the existence probability of an object is set for each section divided in a grid pattern in a camera image as sensor data. In the present embodiment, in order to make the explanation concrete, a case where the obstacle map is a grid map will be described as an example”, and paragraph [0078], “The information processing apparatus 2 according to the present embodiment described above includes an acquisition function 31b as an acquisition unit, an update function 31d as a forgetting processing unit and an update unit, and a generation function 31e as a generation unit. The acquisition function 31b acquires sensor data regarding the environment in which the autonomous mobile body moves.” The system repeatedly acquires sensor data and updates the obstacle map, therefore accumulating obstacle information from past detections.); cause information on the obstacle accumulated by the accumulating means to be forgotten in accordance with a predetermined forgetting rate allocated to each divided region (See at least paragraph [0055], “Further, the update function 31d executes the forgetting process regarding the obstacle map of each category by using the characteristic function. Here, the oblivion process for the obstacle map of each category reduces the existence probability of the target for each position of the obstacle map for each category of the obstacle map to a different degree depending on the category. More specifically, the oblivion process for the obstacle map of each category is a process of reducing the probability in each grid of the current obstacle map to the extent according to the category according to the elapsed time. Further, the characteristic function is a function showing the relationship between the existence probability that an object exists at the position and the time, and can be defined for each category, for example. That is, by defining the characteristic function for each category, it is possible to execute the forgetting process using the forgetting rate and the forgetting time different for each category.” The system reduces the existence probability for each grid over time using a forgetting rate, therefore forgetting information for each divided region.); acquire, by the imaging unit, a captured image (See at least paragraph [0014], “The detection device 8 senses the environment and outputs the data to the information processing device 2. That is, the detection device 8 is a sensor that detects a space or an object around the autonomous mobile robot, and generates sensor data necessary for generating and updating an obstacle map. The detection device 8 is, for example, a left and right camera (stereo camera). The detection device 8 generates sensor data including left and right camera data captured by the stereo camera for each frame, and sequentially outputs the sensor data to the information processing device 2. It is assumed that the sensor data is accompanied by time information. Further, the detection device 8 is also simply referred to as a camera.” The camera data is captured by a stereo camera for each frame, therefore acquiring a captured image.); detect an obstacle included in the captured image (See at least paragraph [0027], “For example, the recognition function 31c recognizes each object included in the sensor data using the sensor data from the acquisition function 31b, and calculates the degree of confidence (Confidence) indicating the degree to which each object belongs to each category for each category. .. In the present embodiment, the case where a plurality of categories are five categories 1 to 5 is taken as an example. That is, in the recognition function 31c, each pixel on the image is "category 1", "category 2", "category 3", "category 4" by the object recognition process using the image which is the sensor data from the acquisition function 31b. , "Category 5" certainty is calculated for each category.” The system recognizes objects in the image, therefore detecting obstacles, as obstacles are objects in the environment.); generate an occupancy map indicating occupancy of an obstacle for each divided region in accordance with information on the accumulated obstacle and the detected obstacle for a current peripheral region of the moving object (See at least paragraph [0010], “The information processing apparatus 2 executes an obstacle map generation / update process and an obstacle map-based motion path generation process for the autonomous mobile robot. In particular, the information processing apparatus 2 uses the sensor data to execute an obstacle map update process including a forgetting process for each category that classifies objects (for example, obstacles) existing in the environment (for example, in the office). Further, the information processing apparatus 2 executes the movement route generation using the updated obstacle map”, paragraph [0011], “Here, the obstacle map is information used to generate a movement path of an autonomous moving body and showing the spatial distribution of the existence probability of an object in the environment around the autonomous moving body. The obstacle map is, for example, a grid map held in an OGM (Occupied Grid Map) format in which the existence probability of an object is set for each section divided in a grid pattern in a camera image as sensor data. In the present embodiment, in order to make the explanation concrete, a case where the obstacle map is a grid map will be described as an example”, and paragraph [0027], “For example, the recognition function 31c recognizes each object included in the sensor data using the sensor data from the acquisition function 31b, and calculates the degree of confidence (Confidence) indicating the degree to which each object belongs to each category for each category. .. In the present embodiment, the case where a plurality of categories are five categories 1 to 5 is taken as an example. That is, in the recognition function 31c, each pixel on the image is "category 1", "category 2", "category 3", "category 4" by the object recognition process using the image which is the sensor data from the acquisition function 31b. , "Category 5" certainty is calculated for each category.” The obstacle map is generated and updated based on sensor data, which are current detections, and previously stored map information, therefore combining accumulated obstacle information with currently detected obstacles for each divided region.); and control traveling of the mobile object in accordance with a route generated using the occupancy map (See at least paragraph [0075], “The generation function 31 e uses the updated obstacle map to generate a movement path of the autonomous mobile robot (step SS)” and paragraph [0076], “The control function 3 la outputs the movement path generated by the generation function 3 le to, for example, the control unit of the autonomous mobile robot (step S9).”).
NISHINO does not explicitly disclose, however, Sane, in the same field of endeavor, teaches wherein the predetermined forgetting rate is different between inside and outside a viewing angle of the imaging unit (See at least paragraph [0038], “In case the region is represented in the form of a grid, the grid cells that fall within the current sensor scanning range, but do not fall under the current sensor shadow volume, can be reduced in confidence by a higher “forgetting rate,” such as ΔP.sub.delete. The grid cells that do not fall within the current sensor scanning range, can be reduced in confidence by a lower “forgetting rate” ΔP.sub.forget. The grid cells that fall within the current sensor scanning range and fall under the C.sup.+ are incremented in confidence by ΔP.sub.increase.” The sensor scanning range corresponds to a viewing angle of the imaging unit, such that the regions inside and outside the scanning range correspond to regions inside and outside the viewing angle.), and the forgetting rate inside the viewing angle is higher than the forgetting rate outside the viewing angle (See at least paragraph [0038], “In case the region is represented in the form of a grid, the grid cells that fall within the current sensor scanning range, but do not fall under the current sensor shadow volume, can be reduced in confidence by a higher “forgetting rate,” such as ΔP.sub.delete. The grid cells that do not fall within the current sensor scanning range, can be reduced in confidence by a lower “forgetting rate” ΔP.sub.forget. The grid cells that fall within the current sensor scanning range and fall under the C.sup.+ are incremented in confidence by ΔP.sub.increase.” The sensor scanning range corresponds to a viewing angle of the imaging unit, such that the regions inside and outside the scanning range correspond to regions inside and outside the viewing angle.).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine the invention of NISHINO with the teachings of Sane such that the information processing system of NISHINO is further configured to utilize the predetermined forgetting rate being different between inside and outside a viewing angle of the imaging unit and the forgetting rate inside the viewing angle being higher than the forgetting rate outside the viewing angle, as taught by Sane (See paragraph [0038].), with a reasonable expectation of success. The motivation for doing so would be optimizing estimation of obstacles, as taught by Sane (See paragraph [0003].).
With respect to claim 14, please see the rejection above with respect to claim 1, which is commensurate in scope to claim 14, with claim 1 being drawn to a moving object control system and claim 14 being drawn to a corresponding method.
With respect to claim 16, please see the rejection above with respect to claim 1, which is commensurate in scope to claim 16, with claim 1 being drawn to a moving object control system and claim 16 being drawn to a corresponding moving object.
Regarding Claim 5, NISHINO and Sane teach The moving object control system according to claim 1, as set forth in the obviousness rejection above. NISHINO teaches wherein the at least one processor further executes instructions in the storage device to discriminate a type of the detected obstacle, wherein the predetermined forgetting rate is set for each type of the obstacle (See at least paragraph [0027], “For example, the recognition function 31c recognizes each object included in the sensor data using the sensor data from the acquisition function 31b, and calculates the degree of confidence (Confidence) indicating the degree to which each object belongs to each category for each category. .. In the present embodiment, the case where a plurality of categories are five categories 1 to 5 is taken as an example. That is, in the recognition function 31c, each pixel on the image is "category 1", "category 2", "category 3", "category 4" by the object recognition process using the image which is the sensor data from the acquisition function 31b. , "Category 5" certainty is calculated for each category”, paragraph [0055], “Further, the update function 31d executes the forgetting process regarding the obstacle map of each category by using the characteristic function. Here, the oblivion process for the obstacle map of each category reduces the existence probability of the target for each position of the obstacle map for each category of the obstacle map to a different degree depending on the category. More specifically, the oblivion process for the obstacle map of each category is a process of reducing the probability in each grid of the current obstacle map to the extent according to the category according to the elapsed time. Further, the characteristic function is a function showing the relationship between the existence probability that an object exists at the position and the time, and can be defined for each category, for example. That is, by defining the characteristic function for each category, it is possible to execute the forgetting process using the forgetting rate and the forgetting time different for each category”, and paragraph [0063], “Returning to FIG. 1, the main storage device 33 is a storage device that stores instructions executed by the processor 31, various data, and the like, and the information stored in the main storage device 33 is read out by the processor 31. The auxiliary storage device 35 is a storage device other than the main storage device 33. The certainty grid map for each category, the obstacle map for each category, the characteristic curve for each category, the sensor data, and the like are stored in the main storage device 33 and the auxiliary storage device 35.” The recognition function recognizes each object and calculates a category for each object, therefore discriminating a type of the detected obstacle. The oblivion process applies a forgetting rate that is different for each category, therefore setting a predetermined forgetting rate for each type of obstacle.).
Regarding Claim 6, NISHINO and Sane teach The moving object control system according to claim 5, as set forth in the obviousness rejection above. NISHINO teaches wherein the type of the obstacle includes at least a dynamic obstacle accompanied by movement and a static obstacle not accompanied by movement (See at least paragraph [0028], “Here, "category 1" is a category meaning that the recognized object is a fixed object such as a wall and does not move even after a lapse of time. "Category 2" is a category meaning that the recognized object is a movable object such as a desk, a chair, or a mobile partition, and is an object that may move over time. "Category 3" is a category meaning that the recognized object is a moving object such as a person or a car in principle. "Category 4" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is in a movable area. The "category 5" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is a movable area but needs attention for its movement.”).
Regarding Claim 7, NISHINO and Sane teach The moving object control system according to claim 6, as set forth in the obviousness rejection above. NISHINO teaches wherein a forgetting rate set to the dynamic obstacle is higher than a forgetting rate set to the static obstacle (See at least paragraph [0061], “Here, Fc is, for example, a damping factor according to the characteristic function exp (−dt / Tn). Tn is a forgetting time constant, and means a forgetting time determined for each category (for example, 3 [s] in category 3, 120 [s] in category 1, etc.). dt [s] means the forgetting processing cycle and can be set arbitrarily. dt [s] is, for example, dt = 100 [ms] (that is, 10 Hz). Further, Pr is a prior probability indicating the existence probability of the category when an infinite amount of time has passed, and 0 ⟨Pnr ⟨1.” The forgetting time is set to 3 seconds for category 3 (moving object) and 120 seconds for category 1 (fixed object). A shorter forgetting time corresponds to a faster decay of the existence probability; a higher forgetting rate. Accordingly, the forgetting rate for dynamic obstacles is higher than for static obstacles.).
Regarding Claim 8, NISHINO and Sane teach The moving object control system according to claim 6, as set forth in the obviousness rejection above. NISHINO teaches wherein the dynamic obstacle is a vehicle or another traffic participant (See at least paragraph [0028], “Here, "category 1" is a category meaning that the recognized object is a fixed object such as a wall and does not move even after a lapse of time. "Category 2" is a category meaning that the recognized object is a movable object such as a desk, a chair, or a mobile partition, and is an object that may move over time. "Category 3" is a category meaning that the recognized object is a moving object such as a person or a car in principle. "Category 4" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is in a movable area. The "category 5" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is a movable area but needs attention for its movement.”).
Regarding Claim 9, NISHINO and Sane teach The moving object control system according to claim 6, as set forth in the obviousness rejection above. NISHINO teaches wherein the static obstacle is an obstacle that does not move by itself (See at least paragraph [0028], “Here, "category 1" is a category meaning that the recognized object is a fixed object such as a wall and does not move even after a lapse of time. "Category 2" is a category meaning that the recognized object is a movable object such as a desk, a chair, or a mobile partition, and is an object that may move over time. "Category 3" is a category meaning that the recognized object is a moving object such as a person or a car in principle. "Category 4" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is in a movable area. The "category 5" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is a movable area but needs attention for its movement.”).
Regarding Claim 11, NISHINO and Sane teach The moving object control system according to claim 1, as set forth in the obviousness rejection above. NISHINO teaches wherein a forgetting rate is set to be higher as the number of obstacles is larger (See at least paragraph [0027], “For example, the recognition function 31c recognizes each object included in the sensor data using the sensor data from the acquisition function 31b, and calculates the degree of confidence (Confidence) indicating the degree to which each object belongs to each category for each category. .. In the present embodiment, the case where a plurality of categories are five categories 1 to 5 is taken as an example. That is, in the recognition function 31c, each pixel on the image is "category 1", "category 2", "category 3", "category 4" by the object recognition process using the image which is the sensor data from the acquisition function 31b. , "Category 5" certainty is calculated for each category”, paragraph [0028], “Here, "category 1" is a category meaning that the recognized object is a fixed object such as a wall and does not move even after a lapse of time. "Category 2" is a category meaning that the recognized object is a movable object such as a desk, a chair, or a mobile partition, and is an object that may move over time. "Category 3" is a category meaning that the recognized object is a moving object such as a person or a car in principle. "Category 4" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is in a movable area. The "category 5" is a category meaning that there is no obstacle in the recognized target (area) and the autonomous mobile robot is a movable area but needs attention for its movement”, paragraph [0055], “Further, the update function 31d executes the forgetting process regarding the obstacle map of each category by using the characteristic function. Here, the oblivion process for the obstacle map of each category reduces the existence probability of the target for each position of the obstacle map for each category of the obstacle map to a different degree depending on the category. More specifically, the oblivion process for the obstacle map of each category is a process of reducing the probability in each grid of the current obstacle map to the extent according to the category according to the elapsed time. Further, the characteristic function is a function showing the relationship between the existence probability that an object exists at the position and the time, and can be defined for each category, for example. That is, by defining the characteristic function for each category, it is possible to execute the forgetting process using the forgetting rate and the forgetting time different for each category”, and paragraph [0061], “Here, Fc is, for example, a damping factor according to the characteristic function exp (−dt / Tn). Tn is a forgetting time constant, and means a forgetting time determined for each category (for example, 3 [s] in category 3, 120 [s] in category 1, etc.). dt [s] means the forgetting processing cycle and can be set arbitrarily. dt [s] is, for example, dt = 100 [ms] (that is, 10 Hz). Further, Pr is a prior probability indicating the existence probability of the category when an infinite amount of time has passed, and 0 ⟨Pnr ⟨1.” The system classifies detected obstacles into categories, including moving and non-moving objects, and applies different forgetting rates depending on the category. The forgetting process reduces existence probability at different rates based on the category, where categories associated with shorter forgetting time constants are reduced more rapidly than others, corresponding to higher forgetting rates for certain types of obstacles. As the number of obstacles increases, a greater number of obstacles are subject to the higher forgetting rate.).
Regarding Claim 13, NISHINO and Sane teach The moving object control system according to any one of claim 1, as set forth in the obviousness rejection above. NISHINO teaches wherein the at least one processor further executes instructions in the storage device to: divide a region around the moving object into grid cells, and generate an occupancy grid map indicating occupancy of a detected obstacle for each of the grid cells as the occupancy map (See at least paragraph [0010], “The information processing apparatus 2 executes an obstacle map generation / update process and an obstacle map-based motion path generation process for the autonomous mobile robot. In particular, the information processing apparatus 2 uses the sensor data to execute an obstacle map update process including a forgetting process for each category that classifies objects (for example, obstacles) existing in the environment (for example, in the office). Further, the information processing apparatus 2 executes the movement route generation using the updated obstacle map”, paragraph [0011], “Here, the obstacle map is information used to generate a movement path of an autonomous moving body and showing the spatial distribution of the existence probability of an object in the environment around the autonomous moving body. The obstacle map is, for example, a grid map held in an OGM (Occupied Grid Map) format in which the existence probability of an object is set for each section divided in a grid pattern in a camera image as sensor data. In the present embodiment, in order to make the explanation concrete, a case where the obstacle map is a grid map will be described as an example”, paragraph [0063], “Returning to FIG. 1, the main storage device 33 is a storage device that stores instructions executed by the processor 31, various data, and the like, and the information stored in the main storage device 33 is read out by the processor 31. The auxiliary storage device 35 is a storage device other than the main storage device 33. The certainty grid map for each category, the obstacle map for each category, the characteristic curve for each category, the sensor data, and the like are stored in the main storage device 33 and the auxiliary storage device 35.” The grid pattern corresponds to dividing the region into grid cells, and the existence probability for each section corresponds to occupancy of an obstacle for each grid cell.).
Regarding Claim 15, NISHINO teaches A non-transitory storage medium storing a program for causing a computer to perform each step of a control method of a moving object control system, comprising: accumulating information on an obstacle detected in a past for each divided region obtained by dividing peripheral regions of a moving object (See at least paragraph [0010], “The information processing apparatus 2 executes an obstacle map generation / update process and an obstacle map-based motion path generation process for the autonomous mobile robot. In particular, the information processing apparatus 2 uses the sensor data to execute an obstacle map update process including a forgetting process for each category that classifies objects (for example, obstacles) existing in the environment (for example, in the office). Further, the information processing apparatus 2 executes the movement route generation using the updated obstacle map”, paragraph [0011], “Here, the obstacle map is information used to generate a movement path of an autonomous moving body and showing the spatial distribution of the existence probability of an object in the environment around the autonomous moving body. The obstacle map is, for example, a grid map held in an OGM (Occupied Grid Map) format in which the existence probability of an object is set for each section divided in a grid pattern in a camera image as sensor data. In the present embodiment, in order to make the explanation concrete, a case where the obstacle map is a grid map will be described as an example”, paragraph [0022], “Each function of the processor 31 is stored in the main storage device 33 in the form of a program that can be executed by a computer, for example. That is, the processor 31 realizes the function corresponding to each program by reading the program from the main storage device 33 and executing the program. In other words, the processor 31 in the state where each program is read has each function shown in the processor 31 of FIG.”, and paragraph [0078], “The information processing apparatus 2 according to the present embodiment described above includes an acquisition function 31b as an acquisition unit, an update function 31d as a forgetting processing unit and an update unit, and a generation function 31e as a generation unit. The acquisition function 31b acquires sensor data regarding the environment in which the autonomous mobile body moves.” The system repeatedly acquires sensor data and updates the obstacle map, therefore accumulating obstacle information from past detections.); causing information on the obstacle accumulated by the accumulating means to be forgotten in accordance with a predetermined forgetting rate allocated to each divided region (See at least paragraph [0055], “Further, the update function 31d executes the forgetting process regarding the obstacle map of each category by using the characteristic function. Here, the oblivion process for the obstacle map of each category reduces the existence probability of the target for each position of the obstacle map for each category of the obstacle map to a different degree depending on the category. More specifically, the oblivion process for the obstacle map of each category is a process of reducing the probability in each grid of the current obstacle map to the extent according to the category according to the elapsed time. Further, the characteristic function is a function showing the relationship between the existence probability that an object exists at the position and the time, and can be defined for each category, for example. That is, by defining the characteristic function for each category, it is possible to execute the forgetting process using the forgetting rate and the forgetting time different for each category.” The system reduces the existence probability for each grid over time using a forgetting rate, therefore forgetting information for each divided region.); acquiring, using an imaging unit provided in the mobile object, a captured image (See at least paragraph [0014], “The detection device 8 senses the environment and outputs the data to the information processing device 2. That is, the detection device 8 is a sensor that detects a space or an object around the autonomous mobile robot, and generates sensor data necessary for generating and updating an obstacle map. The detection device 8 is, for example, a left and right camera (stereo camera). The detection device 8 generates sensor data including left and right camera data captured by the stereo camera for each frame, and sequentially outputs the sensor data to the information processing device 2. It is assumed that the sensor data is accompanied by time information. Further, the detection device 8 is also simply referred to as a camera.” The camera data is captured by a stereo camera for each frame, therefore acquiring a captured image.); detecting an obstacle included in the captured image (See at least paragraph [0027], “For example, the recognition function 31c recognizes each object included in the sensor data using the sensor data from the acquisition function 31b, and calculates the degree of confidence (Confidence) indicating the degree to which each object belongs to each category for each category. .. In the present embodiment, the case where a plurality of categories are five categories 1 to 5 is taken as an example. That is, in the recognition function 31c, each pixel on the image is "category 1", "category 2", "category 3", "category 4" by the object recognition process using the image which is the sensor data from the acquisition function 31b. , "Category 5" certainty is calculated for each category.” The system recognizes objects in the image, therefore detecting obstacles, as obstacles are objects in the environment.); generating an occupancy map indicating occupancy of an obstacle for each divided region in accordance with information on the obstacle accumulated by the accumulating unit and the obstacle detected by the detecting unit for a current peripheral region of the moving object (See at least paragraph [0010], “The information processing apparatus 2 executes an obstacle map generation / update process and an obstacle map-based motion path generation process for the autonomous mobile robot. In particular, the information processing apparatus 2 uses the sensor data to execute an obstacle map update process including a forgetting process for each category that classifies objects (for example, obstacles) existing in the environment (for example, in the office). Further, the information processing apparatus 2 executes the movement route generation using the updated obstacle map”, paragraph [0011], “Here, the obstacle map is information used to generate a movement path of an autonomous moving body and showing the spatial distribution of the existence probability of an object in the environment around the autonomous moving body. The obstacle map is, for example, a grid map held in an OGM (Occupied Grid Map) format in which the existence probability of an object is set for each section divided in a grid pattern in a camera image as sensor data. In the present embodiment, in order to make the explanation concrete, a case where the obstacle map is a grid map will be described as an example”, and paragraph [0027], “For example, the recognition function 31c recognizes each object included in the sensor data using the sensor data from the acquisition function 31b, and calculates the degree of confidence (Confidence) indicating the degree to which each object belongs to each category for each category. .. In the present embodiment, the case where a plurality of categories are five categories 1 to 5 is taken as an example. That is, in the recognition function 31c, each pixel on the image is "category 1", "category 2", "category 3", "category 4" by the object recognition process using the image which is the sensor data from the acquisition function 31b. , "Category 5" certainty is calculated for each category.” The obstacle map is generated and updated based on sensor data, which are current detections, and previously stored map information, therefore combining accumulated obstacle information with currently detected obstacles for each divided region.); and controlling traveling of the mobile object in accordance with a route generated using the occupancy map (See at least paragraph [0075], “The generation function 31 e uses the updated obstacle map to generate a movement path of the autonomous mobile robot (step SS)” and paragraph [0076], “The control function 3 la outputs the movement path generated by the generation function 3 le to, for example, the control unit of the autonomous mobile robot (step S9).”).
NISHINO does not explicitly disclose, however, Sane, in the same field of endeavor, teaches wherein the predetermined forgetting rate is different between inside and outside a viewing angle of the imaging unit (See at least paragraph [0038], “In case the region is represented in the form of a grid, the grid cells that fall within the current sensor scanning range, but do not fall under the current sensor shadow volume, can be reduced in confidence by a higher “forgetting rate,” such as ΔP.sub.delete. The grid cells that do not fall within the current sensor scanning range, can be reduced in confidence by a lower “forgetting rate” ΔP.sub.forget. The grid cells that fall within the current sensor scanning range and fall under the C.sup.+ are incremented in confidence by ΔP.sub.increase.” The sensor scanning range corresponds to a viewing angle of the imaging unit, such that the regions inside and outside the scanning range correspond to regions inside and outside the viewing angle.), and the forgetting rate inside the viewing angle is higher than the forgetting rate outside the viewing angle (See at least paragraph [0038], “In case the region is represented in the form of a grid, the grid cells that fall within the current sensor scanning range, but do not fall under the current sensor shadow volume, can be reduced in confidence by a higher “forgetting rate,” such as ΔP.sub.delete. The grid cells that do not fall within the current sensor scanning range, can be reduced in confidence by a lower “forgetting rate” ΔP.sub.forget. The grid cells that fall within the current sensor scanning range and fall under the C.sup.+ are incremented in confidence by ΔP.sub.increase.” The sensor scanning range corresponds to a viewing angle of the imaging unit, such that the regions inside and outside the scanning range correspond to regions inside and outside the viewing angle.).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine the invention of NISHINO with the teachings of Sane such that the information processing system of NISHINO is further configured to utilize the predetermined forgetting rate being different between inside and outside a viewing angle of the imaging unit and the forgetting rate inside the viewing angle being higher than the forgetting rate outside the viewing angle, as taught by Sane (See paragraph [0038].), with a reasonable expectation of success. The motivation for doing so would be optimizing estimation of obstacles, as taught by Sane (See paragraph [0003].).
Regarding Claim 10, NISHINO teaches The moving object control system according to claim 1, as set forth in the obviousness rejection above. NISHINO does not explicitly disclose, however, Sane, in the same field of endeavor, teaches wherein a forgetting rate of a region including a shadow that lowers detection accuracy of an obstacle in the captured image is higher than a forgetting rate of a region not including the shadow in the captured image (See at least paragraph [0038], “In case the region is represented in the form of a grid, the grid cells that fall within the current sensor scanning range, but do not fall under the current sensor shadow volume, can be reduced in confidence by a higher “forgetting rate,” such as ΔP.sub.delete. The grid cells that do not fall within the current sensor scanning range, can be reduced in confidence by a lower “forgetting rate” ΔP.sub.forget. The grid cells that fall within the current sensor scanning range and fall under the C.sup.+ are incremented in confidence by ΔP.sub.increase.” The system applies different forgetting rates based on sensor visibility, including regions affected by shadow. Regions affected by shadow correspond to reduced sensing reliability and lower detection accuracy of an obstacle, and are reduced in confidence, resulting in a higher forgetting rate than regions not including a shadow.).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine the invention of NISHINO with the teachings of Sane such that the information processing system of NISHINO is further configured to utilize a forgetting rate of a region including a shadow that lowers detection accuracy of an obstacle in the captured image is higher than a forgetting rate of a region not including the shadow in the captured image, as taught by Sane (See paragraph [0038].), with a reasonable expectation of success. The motivation for doing so would be optimizing estimation of obstacles, as taught by Sane (See paragraph [0003].).
Claim(s) 4 is/are rejected under 35 U.S.C. 103 as being unpatentable over NISHINO (JP 2022046408 A) in view of Sane (US 20160216377 A1) and Katz (US 20130163879 A1).
Regarding Claim 4, NISHINO and Sane teach The moving object control system according to claim 1, as set forth in the obviousness rejection above. NISHINO and Sane do not explicitly disclose, however, Katz, in the same field of endeavor, teaches wherein a region inside the viewing angle is set to be broader than an imaging range of the imaging unit determined by performance of the imaging unit (See at least paragraph [0188], “Specifically, passively obtained 3D information, particularly information pertaining to regions which are beyond the maximal attainable distance of the range imaging system, can be transmitted to the range imaging system, thereby increasing the attainable range without modification of the frequency modulation and/or without contributing to the wraparound errors.” The use of information pertaining to regions beyond the maximal attainable imaging distance corresponds to setting a region that is broader than the imaging range determined by performance of the imaging unit.).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine the invention of NISHINO with the teachings of Sane and Katz such that the information processing system of NISHINO is further configured to utilize the predetermined forgetting rate being different between inside and outside a viewing angle of the imaging unit and the forgetting rate inside the viewing angle being higher than the forgetting rate outside the viewing angle, as taught by Sane (See paragraph [0038].), and a region inside the viewing angle is set to be broader than an imaging range of the imaging unit determined by performance of the imaging unit, as taught by Katz (See paragraph [0188].), with a reasonable expectation of success. The motivation for doing so would be optimizing estimation of obstacles, as taught by Sane (See paragraph [0003].). The motivation for doing so would be improving tracking of motion and environmental awareness in regions not directly observable, as taught by Katz (See paragraph [0004].).
Claim(s) 12 is/are rejected under 35 U.S.C. 103 as being unpatentable over NISHINO (JP 2022046408 A) in view of Sane (US 20160216377 A1) and CHEN (US 20030165193 A1).
Regarding Claim 12, NISHINO and Sane teach The moving object control system according to claim 1, as set forth in the obviousness rejection above. NISHINO teaches wherein a forgetting rate is set to be higher (See at least paragraph [0055], “Further, the update function 31d executes the forgetting process regarding the obstacle map of each category by using the characteristic function. Here, the oblivion process for the obstacle map of each category reduces the existence probability of the target for each position of the obstacle map for each category of the obstacle map to a different degree depending on the category. More specifically, the oblivion process for the obstacle map of each category is a process of reducing the probability in each grid of the current obstacle map to the extent according to the category according to the elapsed time. Further, the characteristic function is a function showing the relationship between the existence probability that an object exists at the position and the time, and can be defined for each category, for example. That is, by defining the characteristic function for each category, it is possible to execute the forgetting process using the forgetting rate and the forgetting time different for each category.” The system applies forgetting to obstacle regions using different degrees of reduction depending on the category, including different forgetting rates. Accordingly, higher forgetting rates are applied to certain obstacle regions.).
NISHINO and Sane do not explicitly disclose, however, CHEN, in the same field of endeavor, teaches as the number of divided regions occupied by the obstacle is larger (See at least paragraph [0064], “Each second contour 62a, 62b, 62c, 62d, 62e, 62f include the plurality of difference pixels…The range (a number of pixels) of each thick line is greater than that of the corresponding fine line.” The contours correspond to the divided regions occupied by obstacles, and each contour includes a plurality of pixels such that a greater range corresponds to a great number of divided regions. Accordingly, the forgetting rates are applied to the divided regions, such that a greater number of regions are subject to the higher forgetting rate.).
Thus, it would have been obvious to one of ordinary skill in the art before the effective filing date to combine the invention of NISHINO with the teachings of Sane and CHEN such that the information processing system of NISHINO is further configured to utilize the predetermined forgetting rate being different between inside and outside a viewing angle of the imaging unit and the forgetting rate inside the viewing angle being higher than the forgetting rate outside the viewing angle, as taught by Sane (See paragraph [0038].), and the number of divided regions occupied by the obstacle being larger, as taught by CHEN (See paragraph [0064].), with a reasonable expectation of success. The motivation for doing so would be optimizing estimation of obstacles, as taught by Sane (See paragraph [0003].). The motivation for doing so would be increasing detection accuracy, as taught by CHEN (See paragraph [0008].).
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 JEWEL ASHLEY KUNTZ whose telephone number is (571)270-5542. The examiner can normally be reached M-F 8:30am-5:30pm.
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, Anne Antonucci can be reached at (313) 446-6519. 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.
/JEWEL A KUNTZ/Examiner, Art Unit 3666
/ANNE MARIE ANTONUCCI/Supervisory Patent Examiner, Art Unit 3666
Prosecution Insights