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 .
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.
Claims 1-4, 6-14 and 16-22 are rejected under 35 U.S.C. 103 as being unpatentable over Stentz (US 6,363,632 B1) in view of Sorin (US 2019/0163191A1) in view of Quirynen (US 2021/0221386A1).
Regarding claim 1, Stentz discloses A control system (see at least col. 5 ln. 54-58 of Stentz
which discloses “control system parameters, and determining desired loading locations. The sub-tasks may also monitor the progress of the task, and make adjustments accordingly if there are unforeseen changes or circumstances” and see at least col. 2 ln. 60-64 of Stentz which discloses “an autonomous excavation system 20 for autonomous control of earthmoving machinery 22”) for a construction machine (see at least col. 13 ln. 60-64 of Stentz which discloses “There are many other applications wherein the system 20 may be incorporated such as fork trucks, mining equipment, construction equipment, and agricultural equipment”), comprising: an environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 of Stentz which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”) configured to receive environment information and/or control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 of Stentz which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation” and see at least col. 10 ln. 47-50 of Stentz which discloses “The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force”, *The actuator-state information to corresponds to “control result information” under the broadest reasonable interpretation), output perception result information based on the environment information and/or the control result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”, *Examiner notes that this passage discloses that the perceptual algorithm processor 28 produces “the output or result” which is provided for use by the planning and control module 30, corresponding to perception result information. Stentz teaches that planning and control module 30 uses the output or result from perception algorithm processor 28. That output/result, particularly processed perceptual information, corresponds to perception result information), receive a system adjustment instruction (see at least col. 10 ln. 54-60 of Stentz which discloses “The sensor-motion planner 78 has a motion script which can be used to guide the scan pattern and scan rate for the sensor system 24 as a function of the earthmoving machinery's 22 progress during the work cycle. The sensor motion planner 78 may send position and/or velocity commands to the sensor system 24” and see at least col.7 ln. 10-13 of Stentz which discloses “the planning and control module 30 commands the left sensor 40 to pan toward the dump truck 206 to check for obstacles in the path of movement of the boom 200 and to determine the position and orientation of the dump truck”, *Examiner interprets these passages as illustrating the planning/control side commanding the sensor system to change position which corresponds to the system adjustment instruction), and adjust a state of the environment perception module based on the system adjustment instruction (see at least col. 5 ln. 55-58 of Stentz which discloses “The sub-tasks may also monitor the progress of the task, and make adjustments accordingly if there are unforeseen changes or circumstances” and see at least col. 6 ln. 44-47 of Stentz which discloses “the direction of scanning can be adjusted to provide information about a substantially vertical or horizontal plane depending upon the task and the location of the earthmoving environment 26” and see at least col. 7 ln. 20-25 of Stentz which discloses “the right sensor 42 retrogrades (i.e., pans in the opposite direction) to scan the dig face 204 to provide data for planning the next portion of the excavation”, *Examiner notes that the sensor’s pan direction (its state) changes in direct response to the commands identified above, i.e., the sensor system 24 physically retrogrades/pans pursuant to the planning and control module’s 30 commands); a decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”) configured to receive an operation task (see at least col. 5 ln. 46-50 of Stentz which discloses “An overall excavation task, such as “dig a site for a foundation in this location”, may be broken down into a series of sub-tasks”) and the perception result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy”), predict the motion trajectory (see at least col. 11 ln. 29-33 of Stentz which discloses “the obstacle detector 84 begins a simulation to predict the path of the various components. The obstacle detector 84 predicts the state of the earthmoving machinery 22 far enough in the future to detect any potential collision in order to halt the earthmoving machinery 22”, *Examiner interprets the prediction of the path of the various components as corresponding to predicting the motion trajectory) to obtain prediction result information (see at least col. 10 ln. 63-65 of Stentz which discloses “The obstacle detector 84 uses sensor data and a prediction of the earthmoving machinery's 22 future state to determine if there is an obstacle in the proposed path of motion”), receive feedback result information corresponding to the motion trajectory (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22, including the position and velocity of movable components, cylinder pressures, and the position and orientation of the machine 22, may be sent from the sensors 40 and 42 on the earthmoving machinery 22 to the machine controller interface 100”, *Examiner interprets that since the machine controller interface 100 is part of the planning and control module 30, this is real time execution feedback flowing back into the decision making module), and output the system adjustment instruction to the environment perception module based on the prediction result information (see at least col. 11 ln. 53-59 of Stentz which discloses “Predicting collisions requires that the elevation map contain data from the earthmoving environment 26 within which the earthmoving machinery 22 will be moving. TO ensure this, the sensor system 24 must pan far enough in advance or look ahead so that the simulation process has enough information or data to halt the earthmoving machinery 22” and see at least col. 12 ln. 2-5 of Stentz which discloses “After the obstacle detector 84 determines the swing command, the obstacle detector 84 then determines the lookahead and trigger angles from the lookup table. The scanning sensors 40 and 42 being panning to the angles provided from the lookup table”, *This corresponds to the sensor adjustment instruction driven by the prediction (the lookahead angle is explicitly tied to predicting how far ahead the machine will move) and a control performing module configured to receive the motion trajectory, perform the operation task based on the motion trajectory (see at least col. 4 ln. 1-8 of Stentz which discloses a “control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation. The planning and control module 30 is connected to one or more actuators 32 which are part of the earthmoving machinery“), obtain the feedback result information (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22, including the position and velocity of movable components, cylinder pressures, and the position and orientation of the machine 22, may be sent from the sensors 40 and 42 on the earthmoving machinery 22 to the machine controller interface 100”, *Examiner interprets that since the machine controller interface 100 is part of the planning and control module 30, this is real time execution feedback flowing back into the decision making module) and the control result information during the performing of the operation task (see at least col. 5 ln. 46-50 of Stentz which discloses “An overall excavation task, such as “dig a site for a foundation in this location”, may be broken down into a series of sub-tasks”), output the feedback result information to the decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”), and output the control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”) to the environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 within an earthmoving environment 26 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”).
Stentz may not explicitly disclose generate a motion trajectory based on the operation task
and the perception result information, output the motion trajectory.
However, Sorin discloses generating a motion trajectory based on the operation task and
the perception result information and outputting the motion trajectory (see at least para. [0006] of Sorin which discloses “The motion planning module receives perception data and sample trajectories from the plurality of detectors, adjusts a probability of collision along each edge in the planning graph that results in a collision with obstacles in the perception data to account for the sample trajectories, determines a path considering cost and probability of collision, and outputs the path to the computing system” and see at least para. [0054] of Sorin which discloses “the motion planning module determines the “shortest” path to a target location by considering cost and probability of collision. For example, the fastest way to get to a goal location may be to speed past a bicyclist going straight, but that path may have a 2% chance (e.g., estimate of collision) of knocking over the bicyclist, which is a high cost (poor/bad decision”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the decision making planning module of Stentz to generate a motion trajectory based on the operation task and the perception result information and output the motion trajectory, as taught in Sorin with a reasonable expectation of success in order to improve the efficiency and safety of Stentz’s excavation and loading operations by allowing the system to proactively weight path options against perceived obstacle risk before committing to a trajectory, instead of only reacting once it is clear that a collision will occur. See para. [0054] of Sorin for motivation.
Stentz, as modified by Sorin discloses receiving feedback result information corresponding
to the motion trajectory, as discussed above where actual machine state data is sent to machine controller interface 100 (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22 …may be sent … to the machine controller interface 100”). Stentz teaches that sensors 40 and 42 send information concerning the actual state of the machine 22, including positions and velocities of movable components, cylinder pressures and position and orientation of the machine and this information is sent to the machine controller interface (see col. 12 ln. 53-65 of Stentz as discussed above). Since interface 100 is included in the planning and control module 30, this actual machine state information corresponds to execution feedback received a the decision making planning module and corresponds to claimed feedback result information.
Stentz, as modified by Sorin, may not explicitly disclose outputting the system adjustment
instruction based on the feedback result information.
However, Quirynen discloses the system adjustment based on the feedback result
information (see at least para. [0013] of Quirynen which discloses “Some embodiments are based on the realization that the motion planner can utilize information about the particular current condition of the vehicle control algorithm. For instance, MPC is based on a constrained optimization method that includes obstacle avoidance inequality constraints. If the variance propagated from the motion planner to the MPC is relatively small, the MPC controller may activate the obstacle-avoidance constraints unnecessarily, resulting in non-smooth trajectories. To this end, in one embodiment of the invention, MPC informs the motion planner about the most current amount of constraint activations and/or constraint violations in the predicted state and control trajectories of MPC that can be used for adjusting the confidence, i.e., increasing or decreasing the variance for the distribution of trajectories in the motion planner” and see at least para. [0071] of Quirynen which discloses “the MPC controller solves a constrained dynamic optimization problem at each sampling time step and it uses the active set of constraints in each control solution to provide feedback to the probabilistic motion planner at each sampling time step”, *Quirynen teaches that data regarding the actual result of executing a planned trajectory can be used to make an adjustment to a planning side output which is specifically the MPC controller’s real-time constraint activation/violation data. This is a measure of how the machine’s actual tracked motion related to the planned trajectory is fed back to the motion planner to adjust its output). Stentz and Quirynen are analogous art directed to the same problem of a planning layer generating an output for execution and refining that output using information about how the execution proceeded.
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the system adjustment instruction output of Stentz, as modified by Sorin, to be based on the feedback result information as taught in Quirynen with a reasonable expectation of success in order to improve the accuracy of the sensor system’s lookahead and trigger angle positioning of Stentz. Stentz’s obstacle detector adjusts these angles based on a prediction of the machine’s future state but does not refine that adjustment using information regarding how the machine’s actual motion tracked the predicted trajectory during execution. Stentz teaches generating sensor control instructions based on predicted machine movement and using actual state sensor information during machine operation. Applying Quirynen’s feedback informed planning technique to Stentz’s sensor control output would compensate for deviations between actual and predicted earth moving machine motion, thereby improving timely obstacle detection and safe, efficient autonomous excavation/loading, so that the sensor positioning remains accurate even when the machine’s actual performance deviates from its predicted path. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the prediction-based sensor motion planning and obstacle detection operations of Stentz, as modified by Sorin, cush that the system adjustment instruction is determined based on both Stentz’s predicted future machine state/path information and actual machine state feedback information in view of Quirynen’s teaching that controller derived feedback is used to adjust planning output. See para. [0071] of Quirynen for motivation.
Regarding claim 2, Stentz, as modified by Sorin and Quirynen discloses wherein: the
environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”) is further configured to output (see at least col. 3 ln. 65 – col. 4 ln. 5 of Stentz which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation” and see at least col. 10 ln. 47-50 of Stentz which discloses “The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force”) the perception result information directly to the control performing module; and the control performing module is further configured to receive the perception result information (see at least col. 4 ln. 1-8 of Stentz which discloses a “control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation. The planning and control module 30 is connected to one or more actuators 32 which are part of the earthmoving machinery“) and perform an operation corresponding to the perception result information based on the perception result information (see at least col. 4 ln. 1-5 of Stenz which discloses “the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”).
Regarding claim 3, Stentz, as modified by Sorin and Quirynen discloses wherein: the
decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”) is configured to calculate and obtain an adjustment parameter based on the prediction result information (see at least col. 9 ln. 43-47 of Stentz which discloses “Various shapes may be chosen for template 358 and the height data may be preprogrammed in the digital computer or calculated interactively based on user input”) and the feedback result information, and output the system adjustment instruction based on the adjustment parameter, wherein the system adjustment instruction comprises the adjustment parameter, and the adjustment parameter is configured to adjust the state of the environment perception module (see at least col. 5 ln. 55-59 of Stentz which discloses “The Sub-tasks may also monitor the progress of the task, and make adjustments accordingly if there are unforeseen changes or circumstances”) ; and the environment perception module is configured to extract the adjustment parameter from the system adjustment instruction and adjust the state of the environment perception module based on the adjustment parameter (see at least col. 10 ln. 15-22 of Stentz which discloses “The parameters in the instructions can be modified to maximize the efficiency of the complex automated movement. Parameters can be included in instructions, e.g., to determine when to begin movement”).
Regarding claim 4, Stentz, as modified by Sorin and Quirynen discloses wherein: the
feedback result information comprises a reaction result of an operation object of the construction machine; and/or the perception result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”, *Examiner notes that this passage discloses that the perceptual algorithm processor 28 produces “the output or result” which is provided for use by the planning and control module 30, corresponding to perception result information. Stentz teaches that planning and control module 30 uses the output or result from perception algorithm processor 28. That output/result, particularly processed perceptual information, corresponds to perception result information) comprises the environment information, or the perception result information comprises a logical judgment result generated based on the environment information (see at least para. [0015] of Quirynen which discloses “the image of the environment to produce a sequence of parametric probability distributions over a sequence of target states defining a motion plan for the vehicle, wherein parameters of each parametric probability distribution define a first order moment and at least one higher order moment of the probability distribution, wherein the adaptive predictive controller is configured to optimize a cost function over a prediction horizon to produce a sequence of control commands to one or multiple actuators of the vehicle”) and/or the control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 of Stentz which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation” and see at least col. 10 ln. 47-50 of Stentz which discloses “The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force”, *The actuator-state information to corresponds to “control result information” under the broadest reasonable interpretation).
Regarding claim 6, Stentz, as modified by Sorin and Quirynen discloses wherein: the
environment perception module comprises an environment perception element (see at least para. [0006] of Sorin which discloses “The motion planning module receives perception data and sample trajectories from the plurality of detectors, adjusts a probability of collision along each edge in the planning graph that results in a collision with obstacles in the perception data to account for the sample trajectories“) and a multi-degree-of-freedom platform (see at least para. [0062] of Sorin which discloses “degrees of freedom for each joint” and see at least para. [0109] of Sorin which discloses “PRMs were generated of various sizes for the six degree-of freedom“), wherein the environment perception element is installed on the multi-degree-of-freedom platform (see at least col. 12 ln. 53-56 of Stentz which discloses “The machine controller interface 100 provides an interface between controllers operatively connected to movable components associated with the earthmoving machinery 22 and the planning and control module 30”); and the adjustment parameter (see at least col. 9 ln. 43-47 of Stentz which discloses “Various shapes may be chosen for template 358 and the height data may be preprogrammed in the digital computer or calculated interactively based on user input”) comprises an internal parameter value of the environment perception element and/or a parameter of the multi-degree-of-freedom platform (see at least col. 10 ln. 40-46) of Stentz which discloses “The non-linear response of the actuators 32 may be modeled using a look-up table that is a function of internal variables of the actuators 32 and the hydraulic system. The number of input variables that are supplied to the look-up table is proportional to the number of the actuators 32 being driven by a single pump. The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force. These variables are used to index the tables containing data that represents a constraint surface associated with each of the actuators 32. The constraint surfaces are predetermined and are dependent on the state of the other actuators driven by the same pump”).
Regarding claim 7, Stentz, as modified by Sorin and Quirynen discloses wherein: the
environment perception module is further configured to transmit the environment information to the decision-making planning module (see at least para. [0042] of Sorin which discloses “Environmental information captured from the sensor(s) in the environment can be transmitted to the robot (and/or the object detector 202 and/or object tracker 203) via wired or wireless means”), wherein the environment information is first data information with an element coordinate system of the environment perception module as a coordinate system (see at least col. 4 ln. 40-50 of Stentz which discloses “The scanline processors 54 and 58 convert data received from the sensor interfaces 46 and 50 from spherical coordinates into Cartesian coordinates using corresponding data provided from the position system 44. This information which may take the form of three-dimensional range points may be made available to other components within the system 20 for further use or processing”); and the decision-making planning module is further configured to convert the first data information into second data information with a reference coordinate system of the construction machine (see at least col. 4 ln. 40-50 of Stentz which discloses “The scanline processors 54 and 58 convert data received from the sensor interfaces 46 and 50 from spherical coordinates into Cartesian coordinates using corresponding data provided from the position system 44. This information which may take the form of three-dimensional range points may be made available to other components within the system 20 for further use or processing. The scanline processors 54 and 58 are connected to the position system 44 over the leads 62 and 64”) as a coordinate system based on a transformation matrix between the element coordinate system and the reference coordinate system, and generate the motion trajectory based on the operation task and the second data information (see at least para. [0051] of Quirynen which discloses “the reference motion 105 can be represented by a reference trajectory of state and/or output values and the confidence bounds can be represented by covariance matrices that define the uncertainty around the reference trajectory of state and/or output values. In some embodiments of the invention, the command 101 is computed by a probabilistic motion planner and the reference motion 105 corresponds to the first moment and the confidence 106 corresponds to the second or higher order moments of the statistics for the motion plan”).
Regarding claim 8, Stentz, as modified by Sorin and Quirynen discloses wherein: the
decision-making planning module is further configured to adjust the motion trajectory based on the perception result information of the environment perception module, and output the motion trajectory adjusted to the control performing module; and the control performing module is further configured to control motion of the construction machine based on the motion trajectory adjusted (see at least para. [0071] of Quirynen which discloses “the probabilistic motion planner 311 is configured to adjust the higher order moments of the probabilistic distribution based on the type and/or number of the active constraints in the MPC controller 340. This can be beneficial, for instance, when the behavior of the motion planner needs to be adjusted to environmental changes that have not or not yet been detected by the motion planner, in order to improve the overall behavior of the autonomous or semi-autonomous vehicle”).
Regarding claim 9, Stentz, as modified by Sorin and Quirynen discloses wherein: the
decision-making planning module is further configured to adjust the motion trajectory based on the feedback result information of the control performing module, and output the motion trajectory adjusted to the control performing module; and the control performing module is further configured to control motion of the construction machine based on the motion trajectory adjusted (see at least para. [0071] of Quirynen which discloses “the probabilistic motion planner 311 is configured to adjust the higher order moments of the probabilistic distribution based on the type and/or number of the active constraints in the MPC controller 340. This can be beneficial, for instance, when the behavior of the motion planner needs to be adjusted to environmental changes that have not or not yet been detected by the motion planner, in order to improve the overall behavior of the autonomous or semi-autonomous vehicle”).
Regarding claim 10, Stentz, as modified by Sorin and Quirynen discloses wherein: the
decision-making planning module is further configured to send a control instruction to the control performing module (see at least col. 9 ln. 62 – col. 10 ln. 5 of Stentz which discloses “The loading motion planner 80 controls complex automated movement of the earthmoving machinery 22 using pre-stored instructions, including at least one parameter, that generally defines the complex automated movement. The loading motion planner 80 determines a value for each parameter during the execution of the pre-stored instructions and may include a learning algorithm which modifies the parameters based on the results of previous work cycles so that the performance of the earthmoving machine 22 more closely matches the desired results”) to control an operational state or operational speed of the control performing module to make the operational state or operational speed of the control performing module match an adjusted state of the environment perception module (see at least col. 7 ln. 13-18 of Stentz which discloses “After completing the loading cycle the scan speed of the sensors 40 and 42 are coordinated with the pivotal rotation of the excavator 202 as it returns the boom 200 toward the dig face 204 to detect obstacles far enough in advance to allow the excavator 202 adequate time to respond or stop”).
Regarding claim 11, Stentz discloses a construction machine (see at least col. 13 ln. 60-64 of
Stentz which discloses “There are many other applications wherein the system 20 may be incorporated such as fork trucks, mining equipment, construction equipment, and agricultural equipment”), comprising: receiving (see at least col. 7 ln. 52-55 of Stentz which discloses “The perception algorithm processor 28, which is connected to the sensor system 24, receives information from the sensor system 24 and uses this information”), by an environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”), environment information and/or control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation” and see at least col. 10 ln. 47-50 of Stentz which discloses “The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force”, *The actuator-state information to corresponds to “control result information” under the broadest reasonable interpretation), and outputting perception result information based on the environment information and/or the control result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”, *Examiner notes that this passage discloses that the perceptual algorithm processor 28 produces “the output or result” which is provided for use by the planning and control module 30, corresponding to perception result information. Stentz teaches that planning and control module 30 uses the output or result from perception algorithm processor 28. That output/result, particularly processed perceptual information, corresponds to perception result information); receiving, by a decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”), an operation task (see at least col. 5 ln. 46-50 of Stentz which discloses “An overall excavation task, such as “dig a site for a foundation in this location”, may be broken down into a series of sub-tasks”) and the perception result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy”), and predicting the motion trajectory (see at least col. 11 ln. 29-33 of Stentz which discloses “the obstacle detector 84 begins a simulation to predict the path of the various components. The obstacle detector 84 predicts the state of the earthmoving machinery 22 far enough in the future to detect any potential collision in order to halt the earthmoving machinery 22”, *Examiner interprets the prediction of the path of the various components as corresponding to predicting the motion trajectory) to obtain predicting result information (see at least col. 10 ln. 63-65 of Stentz which discloses “The obstacle detector 84 uses sensor data and a prediction of the earthmoving machinery's 22 future state to determine if there is an obstacle in the proposed path of motion”); receiving, by a control performing module, the motion trajectory, performing the operation task based on the motion trajectory (see at least col. 4 ln. 1-8 of Stentz which discloses a “control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation. The planning and control module 30 is connected to one or more actuators 32 which are part of the earthmoving machinery“), obtaining feedback result information (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22, including the position and velocity of movable components, cylinder pressures, and the position and orientation of the machine 22, may be sent from the sensors 40 and 42 on the earthmoving machinery 22 to the machine controller interface 100”, *Examiner interprets that since the machine controller interface 100 is part of the planning and control module 30, this is real time execution feedback flowing back into the decision making module) and the control result information during the performing of the operation task (see at least col. 5 ln. 46-50 of Stentz which discloses “An overall excavation task, such as “dig a site for a foundation in this location”, may be broken down into a series of sub-tasks”), outputting the feedback result information to the decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”), and outputting the control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”) to the environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 within an earthmoving environment 26 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”); receiving, by the decision-making planning module, the feedback result information corresponding to the motion trajectory (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22, including the position and velocity of movable components, cylinder pressures, and the position and orientation of the machine 22, may be sent from the sensors 40 and 42 on the earthmoving machinery 22 to the machine controller interface 100”, *Examiner interprets that since the machine controller interface 100 is part of the planning and control module 30, this is real time execution feedback flowing back into the decision making module), and outputting a system adjustment instruction (see at least col. 10 ln. 54-60 of Stentz which discloses “The sensor-motion planner 78 has a motion script which can be used to guide the scan pattern and scan rate for the sensor system 24 as a function of the earthmoving machinery's 22 progress during the work cycle. The sensor motion planner 78 may send position and/or velocity commands to the sensor system 24” and see at least col.7 ln. 10-13 of Stentz which discloses “the planning and control module 30 commands the left sensor 40 to pan toward the dump truck 206 to check for obstacles in the path of movement of the boom 200 and to determine the position and orientation of the dump truck”, *Examiner interprets these passages as illustrating the planning/control side commanding the sensor system to change position which corresponds to the system adjustment instruction) to the environment perception module based on the prediction result information (see at least col. 11 ln. 53-59 of Stentz which discloses “Predicting collisions requires that the elevation map contain data from the earthmoving environment 26 within which the earthmoving machinery 22 will be moving. TO ensure this, the sensor system 24 must pan far enough in advance or look ahead so that the simulation process has enough information or data to halt the earthmoving machinery 22” and see at least col. 12 ln. 2-5 of Stentz which discloses “After the obstacle detector 84 determines the swing command, the obstacle detector 84 then determines the lookahead and trigger angles from the lookup table. The scanning sensors 40 and 42 being panning to the angles provided from the lookup table”, *This corresponds to the sensor adjustment instruction driven by the prediction (the lookahead angle is explicitly tied to predicting how far ahead the machine will move); and receiving, by the environment perception module, the system adjustment instruction (see at least col. 5 ln. 55-58 of Stentz which discloses “The sub-tasks may also monitor the progress of the task, and make adjustments accordingly if there are unforeseen changes or circumstances” and see at least col. 6 ln. 44-47 of Stentz which discloses “the direction of scanning can be adjusted to provide information about a substantially vertical or horizontal plane depending upon the task and the location of the earthmoving environment 26” and see at least col. 7 ln. 20-25 of Stentz which discloses “the right sensor 42 retrogrades (i.e., pans in the opposite direction) to scan the dig face 204 to provide data for planning the next portion of the excavation”, *Examiner notes that the sensor’s pan direction (its state) changes in direct response to the commands identified above, i.e., the sensor system 24 physically retrogrades/pans pursuant to the planning and control module’s 30 commands).
Stentz may not explicitly disclose generating a motion trajectory based on the operation
task and the perception result information, output the motion trajectory.
However, Sorin discloses generating a motion trajectory based on the operation task and
the perception result information and outputting the motion trajectory (see at least para. [0006] of Sorin which discloses “The motion planning module receives perception data and sample trajectories from the plurality of detectors, adjusts a probability of collision along each edge in the planning graph that results in a collision with obstacles in the perception data to account for the sample trajectories, determines a path considering cost and probability of collision, and outputs the path to the computing system” and see at least para. [0054] of Sorin which discloses “the motion planning module determines the “shortest” path to a target location by considering cost and probability of collision. For example, the fastest way to get to a goal location may be to speed past a bicyclist going straight, but that path may have a 2% chance (e.g., estimate of collision) of knocking over the bicyclist, which is a high cost (poor/bad decision”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the decision making planning module of Stentz to include generating a motion trajectory based on the operation task and the perception result information and output the motion trajectory, as taught in Sorin with a reasonable expectation of success in order to improve the efficiency and safety of Stentz’s excavation and loading operations by allowing the system to proactively weight path options against perceived obstacle risk before committing to a trajectory, instead of only reacting once it is clear that a collision will occur. See para. [0054] of Sorin for motivation.
Stentz, as modified by Sorin discloses receiving feedback result information corresponding
to the motion trajectory, as discussed above where actual machine state data is sent to machine controller interface 100 (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22 …may be sent … to the machine controller interface 100”). Stentz teaches that sensors 40 and 42 send information concerning the actual state of the machine 22, including positions and velocities of movable components, cylinder pressures and position and orientation of the machine and this information is sent to the machine controller interface (see col. 12 ln. 53-65 of Stentz as discussed above). Since interface 100 is included in the planning and control module 30, this actual machine state information corresponds to execution feedback received a the decision making planning module and corresponds to claimed feedback result information.
Stentz, as modified by Sorin, may not explicitly disclose outputting the system adjustment
instruction based on the feedback result information.
However, Quirynen discloses the system adjustment based on the feedback result
information (see at least para. [0013] of Quirynen which discloses “Some embodiments are based on the realization that the motion planner can utilize information about the particular current condition of the vehicle control algorithm. For instance, MPC is based on a constrained optimization method that includes obstacle avoidance inequality constraints. If the variance propagated from the motion planner to the MPC is relatively small, the MPC controller may activate the obstacle-avoidance constraints unnecessarily, resulting in non-smooth trajectories. To this end, in one embodiment of the invention, MPC informs the motion planner about the most current amount of constraint activations and/or constraint violations in the predicted state and control trajectories of MPC that can be used for adjusting the confidence, i.e., increasing or decreasing the variance for the distribution of trajectories in the motion planner” and see at least para. [0071] of Quirynen which discloses “the MPC controller solves a constrained dynamic optimization problem at each sampling time step and it uses the active set of constraints in each control solution to provide feedback to the probabilistic motion planner at each sampling time step”, *Quirynen teaches that data regarding the actual result of executing a planned trajectory can be used to make an adjustment to a planning side output which is specifically the MPC controller’s real-time constraint activation/violation data. This is a measure of how the machine’s actual tracked motion related to the planned trajectory is fed back to the motion planner to adjust its output). Stentz and Quirynen are analogous art directed to the same problem of a planning layer generating an output for execution and refining that output using information about how the execution proceeded.
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the system adjustment instruction output of Stentz, as modified by Sorin, to be based on the feedback result information as taught in Quirynen with a reasonable expectation of success in order to improve the accuracy of the sensor system’s lookahead and trigger angle positioning of Stentz. Stentz’s obstacle detector adjusts these angles based on a prediction of the machine’s future state but does not refine that adjustment using information regarding how the machine’s actual motion tracked the predicted trajectory during execution. Stentz teaches generating sensor control instructions based on predicted machine movement and using actual state sensor information during machine operation. Applying Quirynen’s feedback informed planning technique to Stentz’s sensor control output would compensate for deviations between actual and predicted earth moving machine motion, thereby improving timely obstacle detection and safe, efficient autonomous excavation/loading, so that the sensor positioning remains accurate even when the machine’s actual performance deviates from its predicted path. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the prediction-based sensor motion planning and obstacle detection operations of Stentz, as modified by Sorin, cush that the system adjustment instruction is determined based on both Stentz’s predicted future machine state/path information and actual machine state feedback information in view of Quirynen’s teaching that controller derived feedback is used to adjust planning output. See para. [0071] of Quirynen for motivation.
Regarding claim 12, Stentz, as modified by Sorin and Quirynen discloses further comprising:
outputting the perception result information directly to the control performing module by the environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”); and receiving, by the control performing module, the perception result information (see at least col. 4 ln. 1-8 of Stentz which discloses a “control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation. The planning and control module 30 is connected to one or more actuators 32 which are part of the earthmoving machinery“), and performing an operation corresponding to the perception result information based on the perception result information (see at least col. 4 ln. 1-5 of Stenz which discloses “the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”).
Regarding claim 13, Stentz, as modified by Sorin and Quirynen discloses wherein: the
outputting, by the decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”), the system adjustment instruction to the environment perception module based on the prediction result information and the feedback result information comprises: calculating and obtaining, by the decision-making planning module, an adjustment parameter based on the prediction result information (see at least col. 9 ln. 43-47 of Stentz which discloses “Various shapes may be chosen for template 358 and the height data may be preprogrammed in the digital computer or calculated interactively based on user input”) and the feedback result information, wherein the adjustment parameter is configured to adjust the state of the environment perception module (see at least col. 5 ln. 55-59 of Stentz which discloses “The Sub-tasks may also monitor the progress of the task, and make adjustments accordingly if there are unforeseen changes or circumstances”); and outputting, by the decision-making planning module, the system adjustment instruction based on the adjustment parameter, wherein the system adjustment instruction comprises the adjustment parameter; and the adjusting, by the environment perception module, the state of the environment perception module based on the system adjustment instruction comprises: extracting, by the environment perception module, the adjustment parameter from the system adjustment instruction; and adjusting, by the environment perception module, the state of the environment perception module based on the adjustment parameter (see at least col. 10 ln. 15-22 of Stentz which discloses “The parameters in the instructions can be modified to maximize the efficiency of the complex automated movement. Parameters can be included in instructions, e.g., to determine when to begin movement”).
Regarding claim 14, Stentz, as modified by Sorin and Quirynen discloses wherein: the
feedback result information comprises a reaction result of an operation object of the construction machine; and/or the perception result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”, *Examiner notes that this passage discloses that the perceptual algorithm processor 28 produces “the output or result” which is provided for use by the planning and control module 30, corresponding to perception result information. Stentz teaches that planning and control module 30 uses the output or result from perception algorithm processor 28. That output/result, particularly processed perceptual information, corresponds to perception result information) comprises the environment information, or the perception result information comprises a logical judgment result generated based on the environment information (see at least para. [0015] of Quirynen which discloses “the image of the environment to produce a sequence of parametric probability distributions over a sequence of target states defining a motion plan for the vehicle, wherein parameters of each parametric probability distribution define a first order moment and at least one higher order moment of the probability distribution, wherein the adaptive predictive controller is configured to optimize a cost function over a prediction horizon to produce a sequence of control commands to one or multiple actuators of the vehicle”) and/or the control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 of Stentz which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation” and see at least col. 10 ln. 47-50 of Stentz which discloses “The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force”, *The actuator-state information to corresponds to “control result information” under the broadest reasonable interpretation).
Regarding claim 16, Stentz, as modified by Sorin and Quirynen discloses further comprising:
transmitting the environment information to the decision-making planning module by the environment perception module (see at least para. [0042] of Sorin which discloses “Environmental information captured from the sensor(s) in the environment can be transmitted to the robot (and/or the object detector 202 and/or object tracker 203) via wired or wireless means”), wherein the environment information is first data information with an element coordinate system of the environment perception module as a coordinate system (see at least col. 4 ln. 40-50 of Stentz which discloses “The scanline processors 54 and 58 convert data received from the sensor interfaces 46 and 50 from spherical coordinates into Cartesian coordinates using corresponding data provided from the position system 44. This information which may take the form of three-dimensional range points may be made available to other components within the system 20 for further use or processing”); and converting, by the decision-making planning module, the first data information into second data information with a reference coordinate system of the construction machine (see at least col. 4 ln. 40-50 of Stentz which discloses “The scanline processors 54 and 58 convert data received from the sensor interfaces 46 and 50 from spherical coordinates into Cartesian coordinates using corresponding data provided from the position system 44. This information which may take the form of three-dimensional range points may be made available to other components within the system 20 for further use or processing. The scanline processors 54 and 58 are connected to the position system 44 over the leads 62 and 64”) as a coordinate system based on a transformation matrix between the element coordinate system and the reference coordinate system, and generating the motion trajectory based on the operation task and the second data information (see at least para. [0051] of Quirynen which discloses “the reference motion 105 can be represented by a reference trajectory of state and/or output values and the confidence bounds can be represented by covariance matrices that define the uncertainty around the reference trajectory of state and/or output values. In some embodiments of the invention, the command 101 is computed by a probabilistic motion planner and the reference motion 105 corresponds to the first moment and the confidence 106 corresponds to the second or higher order moments of the statistics for the motion plan”).
Regarding claim 17, Stentz, as modified by Sorin and Quirynen discloses adjusting, by the
decision-making planning module, the motion trajectory based on the perception result information of the environment perception module, and outputting the motion trajectory adjusted to the control performing module; and controlling, by the control performing module, motion of the construction machine based on the motion trajectory adjusted (see at least para. [0071] of Quirynen which discloses “the probabilistic motion planner 311 is configured to adjust the higher order moments of the probabilistic distribution based on the type and/or number of the active constraints in the MPC controller 340. This can be beneficial, for instance, when the behavior of the motion planner needs to be adjusted to environmental changes that have not or not yet been detected by the motion planner, in order to improve the overall behavior of the autonomous or semi-autonomous vehicle”).
Regarding claim 18, Stentz, as modified by Sorin and Quirynen discloses further comprising:
adjusting, by the decision-making planning module, the motion trajectory based on the feedback result information of the control performing module, and outputting the motion trajectory adjusted to the control performing module; and controlling, by the control performing module, motion of the construction machine based on the motion trajectory adjusted (see at least para. [0071] of Quirynen which discloses “the probabilistic motion planner 311 is configured to adjust the higher order moments of the probabilistic distribution based on the type and/or number of the active constraints in the MPC controller 340. This can be beneficial, for instance, when the behavior of the motion planner needs to be adjusted to environmental changes that have not or not yet been detected by the motion planner, in order to improve the overall behavior of the autonomous or semi-autonomous vehicle”).
Regarding claim 19, Stentz, as modified by Sorin and Quirynen discloses further comprising:
sending a control instruction to the control performing module by the decision- making planning module (see at least col. 9 ln. 62 – col. 10 ln. 5 of Stentz which discloses “The loading motion planner 80 controls complex automated movement of the earthmoving machinery 22 using pre-stored instructions, including at least one parameter, that generally defines the complex automated movement. The loading motion planner 80 determines a value for each parameter during the execution of the pre-stored instructions and may include a learning algorithm which modifies the parameters based on the results of previous work cycles so that the performance of the earthmoving machine 22 more closely matches the desired results”) to control an operational state or operational speed of the control performing module to make the operational state or operational speed of the control performing module match an adjusted state of the environment perception module (see at least col. 7 ln. 13-18 of Stentz which discloses “After completing the loading cycle the scan speed of the sensors 40 and 42 are coordinated with the pivotal rotation of the excavator 202 as it returns the boom 200 toward the dig face 204 to detect obstacles far enough in advance to allow the excavator 202 adequate time to respond or stop”).
Regarding claim 20, Stentz, as modified by Sorin and Quirynen discloses a memory; and a
processor coupled to the memory, wherein the processor is configured to, based on instructions stored in the memory, perform the control method according to claim 11 (see at least para. [0016] of Quirynen which discloses “processor coupled to a memory storing a probabilistic motion planner and an adaptive predictive controller, wherein the probabilistic motion planner is configured to accept the current state of the vehicle, the destination of the vehicle, and the image of the environment to produce a sequence of parametric probability distributions over a sequence of target states defining a motion plan for the vehicle“).
Regarding claim 21, Stentz, as modified by Sorin and Quirynen discloses A construction
machine, comprising: the control system according to claim 1 (see at least col. 13 ln. 59-64 of Stentz which discloses “The application of the present invention to excavators 202 and wheel loaders 220 for excavating and loading operations is illustrative of the utility of the present invention. There are many other applications wherein the system 20 may be incorporated such as fork trucks, mining equipment, construction equipment, and agricultural equipment”).
Regarding claim 22, Stentz discloses an environment perception module (Fig. 1, 24 and see
at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”), environment information and/or control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation” and see at least col. 10 ln. 47-50 of Stentz which discloses “The sensor system 24 provides data regarding the internal state of each of the actuators including variables such as spool valve position and cylinder force”, *The actuator-state information to corresponds to “control result information” under the broadest reasonable interpretation), and output perception result information based on the environment information and/or the control result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”, *Examiner notes that this passage discloses that the perceptual algorithm processor 28 produces “the output or result” which is provided for use by the planning and control module 30, corresponding to perception result information. Stentz teaches that planning and control module 30 uses the output or result from perception algorithm processor 28. That output/result, particularly processed perceptual information, corresponds to perception result information); receive, by a decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”), an operation task (see at least col. 5 ln. 46-50 of Stentz which discloses “An overall excavation task, such as “dig a site for a foundation in this location”, may be broken down into a series of sub-tasks”) and the perception result information (see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy”), and predict the motion trajectory (see at least col. 11 ln. 29-33 of Stentz which discloses “the obstacle detector 84 begins a simulation to predict the path of the various components. The obstacle detector 84 predicts the state of the earthmoving machinery 22 far enough in the future to detect any potential collision in order to halt the earthmoving machinery 22”, *Examiner interprets the prediction of the path of the various components as corresponding to predicting the motion trajectory) to obtain predicting result information (see at least col. 10 ln. 63-65 of Stentz which discloses “The obstacle detector 84 uses sensor data and a prediction of the earthmoving machinery's 22 future state to determine if there is an obstacle in the proposed path of motion”); receive, by a control performing module, the motion trajectory, perform the operation task based on the motion trajectory (see at least col. 4 ln. 1-8 of Stentz which discloses a “control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation. The planning and control module 30 is connected to one or more actuators 32 which are part of the earthmoving machinery“), obtain feedback result information (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22, including the position and velocity of movable components, cylinder pressures, and the position and orientation of the machine 22, may be sent from the sensors 40 and 42 on the earthmoving machinery 22 to the machine controller interface 100”, *Examiner interprets that since the machine controller interface 100 is part of the planning and control module 30, this is real time execution feedback flowing back into the decision making module) and the control result information during the performing of the operation task (see at least col. 5 ln. 46-50 of Stentz which discloses “An overall excavation task, such as “dig a site for a foundation in this location”, may be broken down into a series of sub-tasks”), output the feedback result information to the decision-making planning module (Fig. 1, 30 and see at least col. 4 ln. 1-5 of Stentz which discloses “a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”), and output the control result information (see at least col. 3 ln. 65 – col. 4 ln. 5 which discloses “The perception algorithm processor 28 also provides the processed perceptual information to the sensor system 24. Also connected to the sensor system 24 is a planning and control module 30 which uses the output or result from the perceptual algorithm processor 28 to determine an excavation strategy including where to excavate, where to load excavated materials, and how to move the earthmoving machinery 22 during an excavation operation”) to the environment perception module (Fig. 1, 24 and see at least col. 3 ln. 55-65 which discloses “a sensor system 24 which provides perceptual information regarding the earthmoving machinery 22 within an earthmoving environment 26 … The sensor system 24 is connected to a perception algorithm processor 28 which processes the perceptual information which is provided from the sensor system 24”); receive, by the decision-making planning module, the feedback result information corresponding to the motion trajectory (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22, including the position and velocity of movable components, cylinder pressures, and the position and orientation of the machine 22, may be sent from the sensors 40 and 42 on the earthmoving machinery 22 to the machine controller interface 100”, *Examiner interprets that since the machine controller interface 100 is part of the planning and control module 30, this is real time execution feedback flowing back into the decision making module), and output a system adjustment instruction (see at least col. 10 ln. 54-60 of Stentz which discloses “The sensor-motion planner 78 has a motion script which can be used to guide the scan pattern and scan rate for the sensor system 24 as a function of the earthmoving machinery's 22 progress during the work cycle. The sensor motion planner 78 may send position and/or velocity commands to the sensor system 24” and see at least col.7 ln. 10-13 of Stentz which discloses “the planning and control module 30 commands the left sensor 40 to pan toward the dump truck 206 to check for obstacles in the path of movement of the boom 200 and to determine the position and orientation of the dump truck”, *Examiner interprets these passages as illustrating the planning/control side commanding the sensor system to change position which corresponds to the system adjustment instruction) to the environment perception module based on the prediction result information (see at least col. 11 ln. 53-59 of Stentz which discloses “Predicting collisions requires that the elevation map contain data from the earthmoving environment 26 within which the earthmoving machinery 22 will be moving. TO ensure this, the sensor system 24 must pan far enough in advance or look ahead so that the simulation process has enough information or data to halt the earthmoving machinery 22” and see at least col. 12 ln. 2-5 of Stentz which discloses “After the obstacle detector 84 determines the swing command, the obstacle detector 84 then determines the lookahead and trigger angles from the lookup table. The scanning sensors 40 and 42 being panning to the angles provided from the lookup table”, *This corresponds to the sensor adjustment instruction driven by the prediction (the lookahead angle is explicitly tied to predicting how far ahead the machine will move) and the feedback result information; and receive, by the environment perception module, the system adjustment instruction, and adjust a state of the environment perception module based on the system adjustment instruction (see at least col. 5 ln. 55-58 of Stentz which discloses “The sub-tasks may also monitor the progress of the task, and make adjustments accordingly if there are unforeseen changes or circumstances” and see at least col. 6 ln. 44-47 of Stentz which discloses “the direction of scanning can be adjusted to provide information about a substantially vertical or horizontal plane depending upon the task and the location of the earthmoving environment 26” and see at least col. 7 ln. 20-25 of Stentz which discloses “the right sensor 42 retrogrades (i.e., pans in the opposite direction) to scan the dig face 204 to provide data for planning the next portion of the excavation”, *Examiner notes that the sensor’s pan direction (its state) changes in direct response to the commands identified above, i.e., the sensor system 24 physically retrogrades/pans pursuant to the planning and control module’s 30 commands).
Stentz may not explicitly disclose generating a motion trajectory based on the operation
task and the perception result information, output the motion trajectory.
However, Sorin discloses generating a motion trajectory based on the operation task and
the perception result information and outputting the motion trajectory (see at least para. [0006] of Sorin which discloses “The motion planning module receives perception data and sample trajectories from the plurality of detectors, adjusts a probability of collision along each edge in the planning graph that results in a collision with obstacles in the perception data to account for the sample trajectories, determines a path considering cost and probability of collision, and outputs the path to the computing system” and see at least para. [0054] of Sorin which discloses “the motion planning module determines the “shortest” path to a target location by considering cost and probability of collision. For example, the fastest way to get to a goal location may be to speed past a bicyclist going straight, but that path may have a 2% chance (e.g., estimate of collision) of knocking over the bicyclist, which is a high cost (poor/bad decision”).
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the decision making planning module of Stentz to generate a motion trajectory based on the operation task and the perception result information and output the motion trajectory, as taught in Sorin with a reasonable expectation of success in order to improve the efficiency and safety of Stentz’s excavation and loading operations by allowing the system to proactively weight path options against perceived obstacle risk before committing to a trajectory, instead of only reacting once it is clear that a collision will occur. See para. [0054] of Sorin for motivation.
Stentz, as modified by Sorin discloses receiving feedback result information corresponding
to the motion trajectory, as discussed above where actual machine state data is sent to machine controller interface 100 (see at least col. 12 ln. 59-65 of Stentz which discloses “Information regarding the actual state of the machine 22 …may be sent … to the machine controller interface 100”). Stentz teaches that sensors 40 and 42 send information concerning the actual state of the machine 22, including positions and velocities of movable components, cylinder pressures and position and orientation of the machine and this information is sent to the machine controller interface (see col. 12 ln. 53-65 of Stentz as discussed above). Since interface 100 is included in the planning and control module 30, this actual machine state information corresponds to execution feedback received a the decision making planning module and corresponds to claimed feedback result information.
Stentz, as modified by Sorin, may not explicitly disclose outputting the system adjustment
instruction based on the feedback result information.
However, Quirynen discloses A non-transitory computer-readable storage medium
comprising computer program instructions stored thereon and executed by a processor (see at least para. [0017] of Quirynen which discloses “a non-transitory computer readable storage medium embodied thereon a program executable by a processor for performing a method”) and the system adjustment based on the feedback result information (see at least para. [0013] of Quirynen which discloses “Some embodiments are based on the realization that the motion planner can utilize information about the particular current condition of the vehicle control algorithm. For instance, MPC is based on a constrained optimization method that includes obstacle avoidance inequality constraints. If the variance propagated from the motion planner to the MPC is relatively small, the MPC controller may activate the obstacle-avoidance constraints unnecessarily, resulting in non-smooth trajectories. To this end, in one embodiment of the invention, MPC informs the motion planner about the most current amount of constraint activations and/or constraint violations in the predicted state and control trajectories of MPC that can be used for adjusting the confidence, i.e., increasing or decreasing the variance for the distribution of trajectories in the motion planner” and see at least para. [0071] of Quirynen which discloses “the MPC controller solves a constrained dynamic optimization problem at each sampling time step and it uses the active set of constraints in each control solution to provide feedback to the probabilistic motion planner at each sampling time step”, *Quirynen teaches that data regarding the actual result of executing a planned trajectory can be used to make an adjustment to a planning side output which is specifically the MPC controller’s real-time constraint activation/violation data. This is a measure of how the machine’s actual tracked motion related to the planned trajectory is fed back to the motion planner to adjust its output). Stentz and Quirynen are analogous art directed to the same problem of a planning layer generating an output for execution and refining that output using information about how the execution proceeded.
It would have been obvious to one of ordinary skill in the art before the effective filing date
of the claimed invention to modify the system adjustment instruction output of Stentz, as modified by Sorin, to be based on the feedback result information as taught in Quirynen with a reasonable expectation of success in order to improve the accuracy of the sensor system’s lookahead and trigger angle positioning of Stentz. Stentz’s obstacle detector adjusts these angles based on a prediction of the machine’s future state but does not refine that adjustment using information regarding how the machine’s actual motion tracked the predicted trajectory during execution. Stentz teaches generating sensor control instructions based on predicted machine movement and using actual state sensor information during machine operation. Applying Quirynen’s feedback informed planning technique to Stentz’s sensor control output would compensate for deviations between actual and predicted earth moving machine motion, thereby improving timely obstacle detection and safe, efficient autonomous excavation/loading, so that the sensor positioning remains accurate even when the machine’s actual performance deviates from its predicted path. It would have been obvious to one of ordinary skill in the art before the effective filing date of the claimed invention to modify the prediction-based sensor motion planning and obstacle detection operations of Stentz, as modified by Sorin, cush that the system adjustment instruction is determined based on both Stentz’s predicted future machine state/path information and actual machine state feedback information in view of Quirynen’s teaching that controller derived feedback is used to adjust planning output. See para. [0071] of Quirynen for motivation.
Additional Prior Art
The prior art made of record and not relied upon is considered pertinent to applicant's disclosure. Wei (US 10,407,877) discloses a method for controlling a machine operating at a worksite is provided. The worksite includes a pit region having a crest node and a low wall. The low wall is an incline having a positive slope. The method includes identifying the location of the crest node and activating a low wall detection module at the location of the crest node as the machine moves past the crest node towards the pit region. The low wall detection module is operable within a defined low wall detection gap to detect the low wall. Rowe (US 6,076,030) discloses a motion planning algorithm is used to control an autonomous machine. The motion planning algorithm consists of a template or script which captures the general trends of the motion, while parameters in the script are filled in with the kinematic details for a specific machine and set of movements. A learning algorithm computes the script parameters by using feedback of how the machine performed during the preceding cycle with the current parameter set, and adjusting the parameters to improve the machine's performance during succeeding work cycles. The new parameters are evaluated by the learning algorithm using a predictive function approximator to test various performance criteria such as the time required to perform a task and the accuracy with which the task was performed. The performance criteria are weighted so that the prediction of the outcome of alternate motions places emphasis on the performance criteria that are considered most important. As data from repeated motions accumulates, the algorithm uses the history of the results of various motions to recompute and refine the parameters to improve performance.
Conclusion
Any inquiry concerning this communication or earlier communications from the examiner should be directed to DANA IVEY whose telephone number is (313)446-4896. The examiner can normally be reached 9-5:30 EST Monday-Friday.
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, Jelani Smith can be reached at 571-270-3969. 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.
/DANA D IVEY/Examiner, Art Unit 3662
/D.D.I/September 1, 2026
/JELANI A SMITH/Supervisory Patent Examiner, Art Unit 3662
Prosecution Insights