System and method for automatically determining robot base position via accessibility map of trocar

Abstract

The present teachings relate to automatic determination of robot base position. An instrument access map about a surgical instrument for performing a surgical procedure on an organ is obtained, the instrument access map defining a surface area on the organ having cutting points forming a surgical trajectory. Information about the robot and the surgical environment is received and used to generate a robot access map having a plurality of robot base positions. The robot is used for controlling the surgical instrument to perform surgical operation along the surgical trajectory. Robot base positions are selected based on evaluation parameters derived for each robot base position. Control signals are generated for configuring the robot at the selected robot base position to facilitate the surgical procedure.

Description

CROSS-REFERENCE TO RELATED APPLICATIONS

[0001] This application claims priority to U.S. Patent Application No. 18 / 163,665, entitled "System and Method for Automatically Determining Robotic Base Position Via a Trocar's Accessibility Map," which is incorporated herein by reference in its entirety.

[0002] This application is related to U.S. patent application Ser. No. 18 / 163,686, entitled “System and Method for Automatically Determining the Position of a Trocar and a Robotic Base” (Attorney Docket No. 140551.569674), International Application Ser. No. ___, entitled “System and Method for Automatically Determining the Position of a Trocar and a Robotic Base” (Attorney Docket No. 140551.589818), U.S. patent application Ser. No. 18 / 163,703, entitled “System and Method for Automatically and Simultaneously Determining the Position of a Trocar and a Robotic Base” (Attorney Docket No. 140551.574360), and International Application Ser. No. ____, entitled “System and Method for Automatically and Simultaneously Determining the Position of a Trocar and a Robotic Base” (Attorney Docket No. 140551.589804), all of which are incorporated herein by reference in their entirety. Background Art 1. Technical Field

[0003] The present teachings generally relate to computers. More specifically, the present teachings relate to signal processing. 2. Background Technology

[0004] Over the past few decades, robots have been deployed in a variety of situations, including industrial settings, such as on assembly lines that assemble products around the clock, as well as in other types of environments, such as transporting goods in warehouses or assisting surgeons in performing different types of surgical procedures. For example, robotic surgery has become widely accepted for liver resections due to the unparalleled precision, reach, and dexterity of robots in tasks that are more difficult for humans to perform. An added benefit of surgical robots is that their performance does not degrade over time, unlike humans who get tired, need to eat and sleep, and have distractions.

[0005] In robotic-assisted surgery, a robot can be deployed to perform certain designated actions alongside a doctor or nurse, and can be positioned at a specific location in the operating room. Traditionally, robot placement in the operating room is done manually by humans, based on, for example, experience with good locations in the room relative to the robot's intended actions, the location of the tools the robot will manipulate, and the nature of the actions. Given this, if the robot's placement turns out to be inappropriate, it must be moved during surgery, which can be problematic.

[0006] Therefore, there is a need to develop solutions that address the shortcomings of the current state of the art. Summary of the Invention

[0007] The teachings disclosed herein relate to methods, systems, and programming for information management. More specifically, the teachings relate to methods, systems, and programming related to hash tables and storage management using hash tables.

[0008] In one example, a method is implemented on a machine having at least one processor, a storage device, and a communication platform capable of connecting to a network for automated robot base position determination. An instrument access map is obtained for surgical instruments used to perform a surgical procedure on an organ, the instrument access map defining surface areas on the organ having cutting points that form a surgical trajectory. Information about a robot and a surgical environment is received and used to generate a robot access map having a plurality of robot base positions. The robot is used to control the surgical instruments to perform the surgical procedure along the surgical trajectory. A robot base position is selected based on evaluation parameters derived for each robot base position. A control signal is generated to configure the robot at the selected robot base position to facilitate the surgical procedure.

[0009] In various examples, a system for automated robot base position determination is disclosed. The system includes a robot base position optimizer implemented by a processor and configured to select a robot base position. An instrument access map is obtained for a surgical instrument used to perform a surgical procedure on an organ, the instrument access map defining surface areas on the organ having cutting points forming a surgical trajectory. Information about a robot and a surgical environment is received and used to generate a robot access map having a plurality of robot base positions. The robot is used to control the surgical instrument to perform the surgical procedure along the surgical trajectory. A robot base position is selected based on evaluation parameters derived for each robot base position. A control signal is generated to configure the robot at the selected robot base position to facilitate the surgical procedure.

[0010] Other concepts relate to software for implementing the present teachings. A software product according to this concept includes at least one machine-readable non-transitory medium and information carried by the medium. The information carried by the medium can be executable program code data, parameters associated with the executable program code, and / or information related to a user, a request, content, or other additional information.

[0011] Another example is a machine-readable, non-transitory, tangible medium having recorded thereon information for automated robot base position determination. When read by a machine, the information causes the machine to perform various steps. An instrument access map for surgical instruments used to perform a surgical procedure on an organ is obtained, the instrument access map defining surface areas on the organ having cutting points forming a surgical trajectory. Information about a robot and a surgical environment is received and used to generate a robot access map having a plurality of robot base positions. The robot is used to control the surgical instruments to perform the surgical procedure along the surgical trajectory. A robot base position is selected based on evaluation parameters derived for each robot base position. A control signal is generated to configure the robot at the selected robot base position to facilitate the surgical procedure.

[0012] Additional advantages and novel features will be set forth in part in the following description and in part will be apparent to those skilled in the art upon examination of the following and accompanying drawings, or may be learned by production or operation of the examples. The advantages of the present teachings may be realized and obtained by practice or use of various aspects of the methods, tools, and combinations set forth in the detailed examples discussed below. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The methods, systems, and / or programs described herein will be further described by way of exemplary embodiments. These exemplary embodiments will be described in detail with reference to the accompanying drawings. These embodiments are non-limiting exemplary embodiments, in which like reference numerals denote similar structures throughout the several views of the drawings, and in which:

[0014] Figure 1 shows a surgical environment where robots are deployed to handle some aspects of the surgery;

[0015] Figure 2 shows a surgical instrument inserted into a patient's body via a trocar point that generates a corresponding access map on an organ to be operated on, according to an embodiment of the present teachings;

[0016] Figure 3A illustrates that different manipulations are required to enable surgical instruments inserted from different trocar positions to reach areas on an organ according to embodiments of the present teachings;

[0017] Figure 3B illustrates different considerations in evaluating candidate trocar points according to an embodiment of the present teachings;

[0018] Figure 4A Depicts a surgical environment in which a robot can be placed in different base positions according to an embodiment of the present teachings;

[0019] Figure 4Bshows different robot base positions around a surgical table organized as an operating space grid, according to an embodiment of the present teachings;

[0020] Figure 4C shows different considerations when evaluating the robot base position according to an embodiment of the present teachings;

[0021] Figure 5A depicts an exemplary high-level system diagram of a sequential optimization scheme for determining trocar and robot base positions in a surgical environment according to an embodiment of the present teachings;

[0022] Figure 5B is a flow chart of an exemplary process for determining a sequential optimization solution for trocar and robot base positions in a surgical environment according to an embodiment of the present teachings;

[0023] Figure 6A is an exemplary high-level system diagram of a trocar insertion position optimizer according to an embodiment of the present teachings;

[0024] Figure 6B is a flow chart of an exemplary process of a trocar insertion position optimizer according to an embodiment of the present teachings;

[0025] Figure 7A depicts an exemplary high-level system diagram of a robotic base position optimizer according to an embodiment of the present teachings;

[0026] Figure 7B is a flow chart of an exemplary process of a robot base position optimizer according to an embodiment of the present teachings;

[0027] Figure 7C shows an exemplary classification of robot base positions organized into an operating space grid according to an embodiment of the present teachings;

[0028] Figure 8A depicts an exemplary high-level system diagram for a simultaneous optimization scheme for determining optimal trocar and robot base positions in a surgical environment according to an embodiment of the present teachings;

[0029] Figure 8B is a flow chart of an exemplary process for simultaneously optimizing a solution for determining optimal trocar and robot base positions in a surgical environment according to an embodiment of the present teachings;

[0030] Figure 9A An exemplary matrix illustrating all combinations of possible trocar and base positions for simultaneous optimization according to an embodiment of the present teachings is shown;

[0031] Figure 9B shows exemplary feature vectors for each pair of trocar and robot base positions according to an embodiment of the present teachings;

[0032] Figure 9C An exemplary weight vector according to an embodiment of the present teachings is shown, wherein the weights correspond to the respective features in the feature vector;

[0033] Figure 10A depicts an exemplary high-level system diagram of an optimal trocar / robot combination selector according to an embodiment of the present teachings;

[0034] Figure 10B is a flow chart of an exemplary process of an optimal trocar / robot combination selector according to an embodiment of the present teachings;

[0035] Figure 11A depicts another exemplary high-level system diagram of an optimal trocar / robot combination selector according to an embodiment of the present teachings;

[0036] Figure 11B is a flow chart of an exemplary process for another implementation of an optimal trocar / robot combination selector according to an embodiment of the present teachings;

[0037] Figure 12 depicts an exemplary high-level system diagram for a machine learning mechanism to train different models for use in sequential or simultaneous optimization of trocar / base positions according to an embodiment of the present teachings;

[0038] Figure 13 is a schematic diagram of an exemplary mobile device architecture that can be used to implement a dedicated system for implementing the present teachings in accordance with various embodiments; and

[0039] Figure 14 is a schematic diagram of an exemplary computing device architecture that can be used to implement a special-purpose system for implementing the present teachings in accordance with various embodiments. DETAILED DESCRIPTION

[0040] In the following detailed description, numerous specific details are set forth by way of example in order to facilitate a thorough understanding of the relevant teachings. However, it should be apparent to one skilled in the art that the present teachings may be practiced without these details. In other instances, well-known methods, processes, components, and / or systems have been described at a relatively high level, without detail, in order to avoid unnecessarily obscuring aspects of the present teachings.

[0041] The present teachings disclose, individually or in combination, exemplary methods, systems, and embodiments for automatically optimizing surgical instrument insertion locations and robot base positions. In a robotic-assisted surgery environment, it can include a robot that is deployed to perform certain functions during surgery and a number of surgical instruments that are inserted into the patient's body to perform some intended operation. The insertion of the instruments can be performed at different locations on the patient's skin to reach the target location on the organ to be operated on. The surgical instruments can be inserted into the skin at so-called trocar points. Different trocar points may affect the performance of the operation. For example, depending on the location of the organ to be operated on and the precise cutting location to remove a portion of the organ, some trocar points may collide with other anatomical structures while other trocar points may not.

[0042] When a robot is deployed in a surgical environment, the robot can be used to assist in certain actions, such as controlling the movement of a surgical instrument to a specified target location on an organ, such as a cutting point on the organ. To this end, the robot can be positioned at a base position from which the robot can be configured to perform the intended function accordingly. The base position of the robot may also affect the operation of the robot and thereby the quality of the surgery. For example, when the robot's arm is extended too far to reach the surgical instrument, the performance of the robot may be at risk. Certain base positions of the robot may cause the robot to operate too close to its singularity point (a position where the robot may be trapped in an inoperable situation due to, for example, mechanical limitations). Therefore, both the insertion position of the surgical instrument (trocar point) and the base position of the robot may be selected to avoid problems in the operation. The present teachings disclose methods and systems for automatically optimizing selected surgical instrument insertion positions and the base position of the robot to minimize the risks of robot-assisted surgery.

[0043] Optimization according to the present teachings is directed to determining one or both of an insertion position for a surgical instrument and a base position for a robot. With respect to trocar point optimization, candidate trocar positions can be evaluated based on various criteria. Examples include the goal of the potential surgery (e.g., liver resection), the extent of the surgery (e.g., how many lobes of the liver are to be removed), the role of the instrument in the surgery (e.g., a surgical instrument with a cutter at the tip to make cuts on an organ), the spatial configuration between the surgical instrument and the target organ, and potential collisions between the insertion position and the target organ location. Candidate robot base positions can also be evaluated based on criteria such as the function(s) the robot is expected to perform (e.g., moving a surgical instrument to various specified 3D coordinates in a workspace), the kinematic configuration that enables the robot to perform the desired function, the spatial relationship between the robot and the surgical instrument, the proximity of the robot's singularity points, or whether the robot at the candidate base position is likely to interfere with other equipment in the operating room, etc. Depending on the specific application, the criteria used to evaluate each candidate insertion position and base position may be different.

[0044] In some embodiments of the present teachings, the trocar position and the base position are optimized sequentially, i.e., one is optimized first, and then the other is optimized relative to the first optimization result. For example, the trocar position can be optimized first. Once the insertion position of the surgical instrument is obtained, the base position of the robot can then be optimized relative to the optimized insertion position of the surgical instrument. Alternatively, the base position of the robot can be optimized first, and then the trocar position of the surgical instrument can be optimized relative to the fixed robot base position.

[0045] In some embodiments of the present teachings, the trocar position of the surgical instrument and the base position of the robot can be optimized simultaneously. That is, what is optimized is a combination of two positions, one for the insertion of the surgical instrument and the other for the positioning of the robot in the workspace. When optimizing the combination, a feature vector can be obtained for each possible position pair to create a matrix with each row of the candidate pair and a column of the eigenvalues ​​of the eigenvector of the candidate pair. In some implementations, the best combination can be selected as the optimization result based on the evaluation score associated with the candidate pair. In some embodiments, the evaluation score of the candidate pair can be determined based on the weighted sum of all eigenvalues ​​of the corresponding eigenvector. The weights of the different features in the feature vector can be learned via machine learning based on training data and performance evaluation results from past surgeries. In this optimization scheme, the best combination of insertion position and base position can correspond to the combination that produces the maximum evaluation score or the highest weighted sum.

[0046] In some embodiments, a model-based approach can be applied instead of optimizing the combination by selecting one of the discrete weighted sums of the individual combinations. The model can be represented by embedded model parameters, and the embedding of the model can be learned via machine learning based on training data collected from historical data related to operating room configurations with assessments of the performance of the relevant surgery. The assessment can be presented as a vector, a score, etc., and can include various parameters designed to measure the success of the medical operation. Examples of such parameters include, for example, whether any of the trocar points of the robot base position were adjusted during the surgery, the length of the surgery, the accident rate during the surgery (e.g., whether the surgical instrument accidentally collided with other anatomical structures, the surgeon's satisfaction with the setup, the patient's recovery time, etc.). Such ground truth values ​​can be used for training so that the trained embedding includes knowledge related to what configurations of surgical instrument insertion positions and robot base positions work well in different types of surgeries and settings. Details of different aspects of the present teaching and various embodiments are disclosed below with reference to different figures.

[0047] Figure 1A workspace in a surgical environment is shown, in which a robot 160 is deployed to handle certain aspects of the surgery. Within the workspace, there is a surgical table 100, a surgical instrument 120 having a rigid body with a tip 130 inserted into the body of a patient on the surgical table. A tracking mechanism is deployed within the workspace, which includes sensors, such as a camera 150 configured to monitor a tracking device 140 attached to one end of the surgical instrument 120, which is located outside the patient's body. Assuming the sensor 150 is calibrated within the workspace, when the sensor 150 observes the tracking device, the tracking mechanism can determine the 3D coordinates of the surgical instrument in a coordinate system defined relative to the workspace. Since the surgical instrument is a rigid body (including the body 120 and the tip portion 130), the 3D coordinates of the tip 130 of the surgical instrument can also be determined accordingly through detection by the tracking device.

[0048] In this exemplary surgical environment, the robot 160 can have a base 170 so that the robot can be moved by moving the base 170 to different positions. The surgical robot can be deployed to, for example, handle some aspects of the operation during surgery. For example, the robot 160 can be used to control the surgical instrument 120 to move in a manner such that the tip 130 of the instrument reaches some specified 3D coordinates in the workspace (e.g., a specific cutting point on the patient's organ). Such control can be achieved by configuring the kinematic parameters of the robot so that such control can control the instrument to travel along a path from the current position of the tip 130 to the specified 3D coordinates. Depending on the base position of the robot 160, the robot needs to be configured differently to achieve this goal. As discussed herein, some base positions may produce better or more convenient performance, while some may not.

[0049] The configuration required to enable robot 160 to perform the desired function may vary relative to the insertion location, or trocar point, of the surgical instrument on the patient's skin. The location of the trocar point is also important from the perspective of the accessibility of the trocar point to various target points. For example, surgical instrument 120 may be used to remove a portion of an organ, such that the tip of the surgical instrument must reach a series of cutting points on the organ from the trocar point. Figure 2 The surgical instrument, i.e., cannula 210, is shown. The cannula 210 is inserted into the patient's skin 230 via a trocar point 220. The trocar point 220 generates a corresponding access map 240 on the target organ 250 to be operated on. In order to operate on the target organ, a series of cutting points can be pre-planned before the operation, such as Figure 2260. To ensure that the cannula 210 can reach all pre-planned cut points in 260, the access map 240 associated with the trocar point 220 must enclose all cut points. Thus, a minimum condition for determining a trocar point may be that the access map associated with the trocar point must have all cut points included therein.

[0050] Often, more than one trocar point location satisfies this minimum requirement. However, to reach the cutting point, surgical instruments inserted from different trocar points may take different paths to the cutting point, some of which may be more problematic than others. For example, starting from a certain trocar point, the surgical instrument may collide with other anatomical structures before reaching the cutting point and may need to move around to avoid collisions, making it more difficult and less efficient. Figure 3A It is shown that although multiple trocar points 310-1, 320-1, 330-1, and 340-1 all produce satisfactory access maps 310-2, 320-2, 330-2, and 340-2 to cover the pre-planned cutting points on organ 250, surgical instruments inserted at different trocar points must be manipulated differently to access each of the cutting points. For example, because trocar points 310-1 and 340-1 have longer distances to some cutting points, the surgical instrument is more likely to encounter other anatomical structures. Furthermore, from these trocar points, the tip of the surgical instrument may not be able to cut the organ at the cutting point in a direction substantially perpendicular to the surface of the organ, making it more likely to have undesirable performance during operation. Therefore, given various considerations, it is necessary to determine the appropriate or optimal trocar point to select.

[0051] Figure 3B Exemplary considerations for evaluating each trocar point according to an embodiment of the present teachings are shown. As shown, the considerations may include the average distance to the cut point, the angle of arrival at the selected cut point (e.g., the midpoint of the cut point), the percentage of cut points included in the visit map, ..., whether there are collisions relative to other objects, and whether there are any collisions when arriving at the cut point. Additional or different evaluation criteria may also be used. Figure 3AAs can be seen in , trocar points that are not directly above the target organ may have a larger average distance to the cutting point and may have a larger tilt angle relative to, for example, the average surface normal of the target organ and therefore relative to the cutting point. The more tilted the angle of the trocar point, the more likely it is that a surgical instrument inserted from the trocar point will collide with other anatomical structures along the path to reach different cutting points. In addition, as the trocar point is further away from the target organ, its access map is more likely to fail to cover certain cutting points, either due to collision or because the distance is too large for the surgical instrument to reach certain cutting points. With this in mind, it is not only important to select candidate trocar points that produce an access map that can cover all cutting points, but also to select the trocar points that are most feasible in terms of risk-free, efficiency and operability.

[0052] Regarding the configuration of the surgical operating room, the robot's base position is also important for achieving efficient operation. Similar to the trocar point position, although the robot 160 can be placed in any of a number of base positions in the operating room, some base positions result in better performance or efficiency than others. The present teachings disclose different embodiments for determining feasible base positions based on different considerations and their optimization in different situations. Figure 4A A surgical environment according to an embodiment of the present teachings is shown in which a robot 160 can be placed in different base positions. As shown, the robot 160 and its base can be located in one of a plurality of positions (e.g., 400-1, 400-2, 400-3, 400-4, 400-5, ... and 400-6) around a surgical bed.

[0053] There may be more pedestal locations available around the surgical table, e.g. Figure 4B, where the operating space around the surgical bed 100 can provide an exemplary plurality of possible base locations 410 on three sides. In this illustration, the operating space can be divided into different zones on each side of the surgical bed 100, each of which can correspond to a candidate base location. As shown, along one side 410-1 of the surgical bed 100, the available base locations form a grid of rows and columns of possible base locations. On the other side 410-3, there can also be rows and columns of sub-zones, each corresponding to an available base location. The third side 410-2 similarly depicts the available base locations for deploying the robot 160. While the base locations are arranged as a grid of rows and columns in this example, other arrangements are possible. The manner in which the available base locations are determined can be determined based on the application requirements. For example, depending on whether other equipment components also need to be placed near the surgical bed, the available area for placing the robot may be limited, and such candidate locations may not be adjacent to each other. Similar to trocar position, base position may also need to be evaluated based on certain criteria in order to maximize the performance and / or efficiency of the robot 160 relative to its intended function.

[0054] While robot 160 may be able to perform its intended function at different base positions, different base positions may produce different performance or results. For example, robot 160 may be used to move a surgical instrument that is inserted into a patient via a trocar point in a manner that allows tip 130 to reach different cutting points on a target organ. In such cases, the robot may have a harder time completing its work at some base positions than at other base positions. At some base positions, it may be undesirable for robot 160 to operate in a space too close to its singularity point. To evaluate different base positions, different criteria may be considered regarding the robot's intended function and the robot's own operating parameters.

[0055] Figure 4CVarious exemplary considerations for evaluating robot base positions according to embodiments of the present teachings are presented. In this illustration, exemplary considerations are provided based on the assumption that a robot is deployed to control the motion of a surgical instrument to perform surgery on a target organ at a specific cutting point. Considerations for evaluating candidate robot base positions may include various features. Some examples may include the kinematic feasibility of the robot arm relative to the surgical tool's access map. The robot's access map can be determined based on the kinematic feasibility, and the robot's access map can be generated by combining robot base positions with complete robot kinematic feasibility. Other features that may be considered in the evaluation may include the distance from the trocar to the robot base position, the proximity of singularities, and the minimum distance between the robot and other robots, instruments, or obstacles. In some embodiments, additional features may also be evaluated, including the angle between the arm and the surgical instrument relative to a reference, such as the surface normal at the trocar point, and the percentage of cutting points that the surgical instrument can reach based on the robot's access map. It should be noted that these are exemplary features to be considered during the evaluation and are provided for illustration only and are not limiting. Other criteria may also be applicable and are within the scope of the present teachings. For example, if the intended function of the robot is different, a different set of criteria may be developed for evaluating the appropriateness of different base positions for that intended function.

[0056] Another aspect of the problem is the interplay between the trocar point location and the robot's base position. The appropriateness of selecting one is not independent of the other. Therefore, proper setup of the surgical environment requires consideration of both. As discussed herein, there are different solutions to finding the optimal combination of trocar and base positions, including sequential or simultaneous solutions, each of which can be implemented via different embodiments. Below, exemplary solutions and embodiments are disclosed with reference to the corresponding figures.

[0057] Figure 5A An exemplary high-level system diagram of a sequential optimization framework 500 for determining trocar and robot base positions in a surgical environment in accordance with an embodiment of the present teachings is depicted. In this optimization scheme, an optimal trocar position and an optimal base position of the robot are determined sequentially, i.e., the trocar point position is optimized first, and then the robot base position is optimized based on the optimized trocar point position. Thus, the illustrative sequential optimization framework 500 includes a trocar insertion position optimizer 510, a robot base position optimizer 520, and a surgical setup configuration unit 530. The trocar insertion position optimizer 510 is used to determine an optimal position on the patient's skin as a trocar entry point, and may be determined based on various considerations, some of which may be factors such as Figure 3BAs shown. The robot base position optimizer 520 is used to determine the optimal base position of the robot given the optimal trocar position from the trocar insertion position optimizer 510. As described herein, different considerations may also be applied to determine the optimal base position of the robot, some of which are as follows: Figure 4C As shown. When both the optimal trocar insertion position and the base position are determined, the surgical setting configuration unit 530 uses the two to configure the surgical setting in the 3D real-life setting, such as the 3D coordinates of the optimal position, which surgical setting may include a mark. For example, the marked 3D coordinates of the optimized trocar insertion position can provide guidance on the position where the surgical instrument will be inserted. If the user is to insert the surgical instrument, the mark on the patient's skin helps the user see the position. If a robot is to be used to insert the surgical instrument, the surgical setting configuration unit 530 can determine the path for the robot arm to reach the surgical instrument and the kinematic parameters required to control the robot operation to achieve the path. Such control signals can then be output to the robot to perform the action.

[0058] Figure 5B is a flow chart of an exemplary process for a sequential optimization framework 500 for determining trocar and robot base positions in a surgical environment, according to an embodiment of the present teachings. Prior to performing the optimization, various inputs are received at 540, including, for example, the type of surgery (e.g., liver resection), a 3D model of the organ involved (e.g., a 3D model of the liver with information about the resection trajectory), and a description of the robot to be used (e.g., the type of robot, operating range, singularities, etc.). These inputs are important because the optimization is performed within the constraints imposed by such inputs. Using relevant inputs such as the type of surgery and the 3D model with information about the surgical path, the trocar insertion position optimizer 510 identifies an optimal trocar insertion position at 550 and sends it to the robot base position optimizer 520 at 560. Upon receiving the optimized trocar insertion position, the robot base position optimizer 520 proceeds to identify an optimized base position relative to the optimized trocar position at 570. Then, at 580, both the optimized trocar insertion position and the robot base position are sent to the surgical setup configuration unit 530 to generate respective control signals at 590 for placing the surgical instrument at the optimized trocar point and the robot at the optimized base position.

[0059] Figure 6A is an exemplary high-level system diagram of a trocar insertion location optimizer 510 according to an embodiment of the present teachings. In the illustrated embodiment, the trocar insertion location optimizer 510 includes a candidate trocar location identifier 600, a candidate visit map generator 620, an evaluation feature determiner 640, and a trocar location optimizer 660. Figure 6Bis a flow chart of an exemplary process of the trocar insertion location optimizer 510 according to an embodiment of the present teachings. In operation, at 605, candidate trocar locations may be identified by the candidate trocar location identifier 600. There are various methods for determining such candidate locations. For example, using input of a 3D model of the organ and information about the surgical trajectory contained therein, candidate trocar locations may be determined based on, for example, the average surface normal along a cut point on the surgical trajectory, or along each of the surface normals along a number of cut points selected at intervals along the surgical trajectory. The cut points may be selected by the user based on visual information captured by sensors within the patient's body in a 2D video displaying the organ. The identified candidate trocar insertion locations are then saved at 610 and used by the candidate access map generator 620 at 615 to determine an access map for each of the candidate trocar insertion locations. The access maps thus generated for the candidate trocar insertion locations are then saved at 630.

[0060] To facilitate optimization, for each of the candidate trocar insertion locations, various evaluation features may be determined at 625 for evaluation, such as Figure 3B As shown. For example, the kinematic reachability of the robot's access map to the surgical tool, the coverage of the access map of each candidate trocar insertion position on the cutting point on the surgical trajectory (specified by the 3D model), the average angle and distance from the trocar point to the cutting point, etc. can be determined by the evaluation feature determiner 640 and saved as position-based evaluation parameters 650. Based on such evaluation parameters for each of the candidate trocar insertion positions, the trocar position optimizer 660 can then access the optimization model 670 at 635 and accordingly select an optimized trocar insertion position based on the optimization model 670 at 645. In some embodiments, the optimization model can be obtained via machine learning based on the relationship between historical surgical setup information and surgical performance. Such optimized trocar insertion position can then be output as an optimization result at 655.

[0061] Figure 7A An exemplary high-level system diagram of a robot base position optimizer 520 according to an embodiment of the present teachings is depicted. In this illustration, the robot base position optimizer 520 includes a robot operating space determiner 700, a grid resolution determiner 710, an operating space grid generator 720, a grid-based evaluation parameter generator 740, a robot configuration unit 750, and an optimal base position selector 760. As discussed herein, in a sequential optimization scheme, the optimization of the robot base position is performed relative to the optimized trocar insertion position. Thus, candidate base positions for the robot can be determined relative to the input optimized trocar insertion position, and the evaluation of each grid base position can be based on a visit map of the optimized trocar insertion position.

[0062] In operation, the robot base position optimizer 520 can first identify an operating space in which the robot can perform its intended function given an optimized trocar insertion point. The operating space includes a plurality of feasible base positions as candidate base positions. For optimization, each of the candidate positions can be evaluated individually, and the results of such evaluations can then be used to identify the optimal position. To obtain the candidate base positions, the robot's operating space is divided into grids according to a resolution specified as an optimization parameter. Each grid corresponds to a candidate base position. Each grid in the operating space is then evaluated based on the robot's operation relative to the optimized trocar insertion position and the intended function to be performed by the robot. For example, it can be evaluated whether the robot at the base position is able to cover the access map of the optimal trocar insertion point. Some evaluation criteria for the robot base position are as follows: Figure 4C The optimized base position is selected based on the evaluation results.

[0063] Figure 7B is a flow chart of an exemplary process of the robot base position optimizer 520 according to an embodiment of the present teachings. In operation, upon receiving an optimized trocar insertion position with an access map, the robot operating space determiner 700 determines the robot's operating space relative to the optimized trocar insertion position at 705 (the robot's operable space relative to the trocar insertion position). For optimization, each possible candidate base position is evaluated. In the illustrated embodiment, the operating space is divided into a grid, with each grid corresponding to a candidate base position. To this end, the grid resolution determiner 710 first determines, at 715, a resolution to be used to divide the operating space into different grids. For example, the grid resolution can be set based on the size of the robot base.

[0064] Based on the grid resolution, the operating space grid generator 720 creates an operating space grid 730 at 725 with candidate base positions corresponding to each grid. Based on the operating space grid 730, the grid-based evaluation parameter generator 740 determines evaluation parameters for each of the candidate base positions in the operating space grid at 735 based on inputs such as the optimized trocar insertion position and its access map, as well as the desired robot configuration. The evaluation results for each candidate base position are saved at 750 and used by the optimal base position selector 760 to select the optimal base position at 745. The selection can be performed based on a robot base optimization model 770. In some embodiments, the robot base optimization model 770 can provide, for example, specified discrete optimal ranges for different evaluation criteria. In some embodiments, the robot base optimization model 770 can correspond to a machine learning model trained based on, for example, historical data collected from different surgeries with setup configuration information, performance ratings of the surgeries, and surgical event evaluation data. Using the machine-learned robot base optimization model 770, grid-based evaluation parameters for all candidate base positions can be input to the model, and the output can correspond to the selected base position as the best choice. The best base position is then output at 755 as the optimization result of the robot base position.

[0065] Figure 7C An exemplary classification of robot base positions in an operating space grid according to an embodiment of the present teachings is shown. In this example, the operating space grid includes multiple grids on three sides of the surgical bed 100. Each base position in the grid is classified and represented using a different type of texture. For example, base positions in the grid with gray (765) are classified as base positions that are not feasible given the surgical setting. For example, the robot may not be able to reach, for example, surgical instruments from those base positions marked in gray. In addition, there are base positions in the grid without texture markings (775) that are classified as base positions that the robot cannot cover all areas of the access map associated with the cannula needle point. In addition, there are base positions in the grid marked with textures (785 including, for example, base positions 785-1 and 785-2 on both sides of the surgical bed) to represent base positions that the robot can cover the entire access map associated with the cannula needle insertion point. That is, each base position in 785 qualifies as a candidate base position. As discussed herein, such candidate robot base positions can be combined to form the robot's access map (785). Through optimization, one of the base positions in category 785 may be selected as the optimal base position 795 based on the evaluation results.

[0066] As discussed herein, another mode of optimization according to the present teachings is to simultaneously optimize a combination of trocar insertion and robot base position. Figure 8AAn exemplary high-level system diagram depicts a simultaneous optimization framework 800 for determining optimal trocar and robot base positions in a surgical environment, according to an embodiment of the present teachings. In this embodiment, simultaneous optimization framework 800 includes a candidate trocar position generator 810, a robot operating space grid generator 820, an optimal trocar / robot combination selector 830, and a surgical setup configuration unit 840. In this framework, both candidate trocar position generator 810 and robot operating space grid generator 820 are used to determine candidate positions for trocar insertion and robot without selection. All candidates for trocar and robot positions are sent to optimal trocar / robot combination selector 830, where combinations of trocar and robot positions are considered and the best combination is selected as the optimized combination. The optimized combined trocar insertion position and robot position are then sent to surgical setup configuration unit 840, which performs the same functions as described with respect to step 530.

[0067] Figure 8B 8 is a flow chart of an exemplary process for simultaneously optimizing a solution 800 for determining optimal positions of a trocar and a robot base in a surgical environment, according to an embodiment of the present teachings. Based on input information, a candidate trocar position generator 810 determines candidate trocar insertion positions at 805 and sends such candidates to an optimal trocar / robot combination selector 830. Similarly, a robot operating space grid generator 820 determines a robot operating space grid at 815, where each grid represents a candidate robot base position. The generated robot operating space grid is sent to the optimal trocar / robot position selector 830 as a candidate base position. Upon receiving the candidate trocar insertion positions and the candidate robot base positions, the optimal trocar / robot combination selector 830 processes all combinations of trocar / base positions at 825 and determines the optimal combination of trocar insertion and robot base positions at 835. The optimal combination of such selections is then sent to the surgical setting configuration unit 840, which generates a configuration control signal based on the received optimal trocar insertion position and robot base position at 845. The control signal is then output at 855 so that the operating room can be configured according to the optimization result.

[0068] When optimizing the combination of trocar and robot base positions, each combination must be evaluated. If there are M candidate trocar insertion positions and N robot base positions, the number of combinations to consider is MxN. Figure 9A As shown in Figure 9AAn exemplary combination matrix 900 for simultaneously optimizing trocar and robot base position combinations according to an embodiment of the present teachings is shown. In this exemplary matrix, each row corresponds to a candidate trocar insertion position, and each column represents a candidate robot base position. Optimization is the selection of a unit, such as Figure 9A 910, shown in FIG, represents a specific combination of trocar insertion position and robot base position.

[0069] In order to be able to choose Figure 9A Each combination in the combination matrix 900 must be evaluated. As described herein, for each trocar insertion position and / or robot base position, there may be individual criteria to be applied, such as Figure 3B and Figure 4C When considering the position of the trocar and the robot base in combination, additional considerations can be added, such as the spatial relationship between the two, including the distance between the two and the angle formed by the two positions. The features included in the evaluation combination can be organized into a feature vector, such as Figure 9B , wherein an exemplary feature vector 920 is shown representing a pair of trocar positions and robot base positions according to an embodiment of the present teachings. In this example, Figure 9B The feature vector 920 in

[0065] may include a number of features related to candidate trocar insertion positions, candidate base position information, and features indicating their spatial relationship. For example, feature 920-1 may be the location of a candidate trocar point, feature 920-2 may be a candidate base position, feature 920-3 or D(I, B) may represent the distance between the two locations, feature 920-4 or A(I, B) may correspond to the angle formed by the two locations relative to some reference, ..., insertion position evaluation parameters 920-i, ..., and base position evaluation parameters 920-k, .... That is, each cell representing a combination in combination matrix 900 is associated with a feature vector that will be used by the optimal trocar / base combination selector 830 for evaluation.

[0070] The optimal trocar / base combination selector 830 can be implemented in different ways to select the optimal combination. In some embodiments, a weighted sum based approach can be employed that can evaluate different combinations based on their weighted feature vector values. Figure 9CAn exemplary weight vector 930 is shown according to an embodiment of the present teachings, wherein the weights correspond to the individual features in the combined feature vector. Exemplary weights in the vector include W1, W2, ...Wi, ..., Wm, ..., Wn, each of which is used to weight the feature values ​​in the feature vector 920 to obtain a weighted sum of each feature vector. The selection of the best combination can then be based on the weighted sum value. In some embodiments, the weights Wi (1 < i <= n) can be trained via machine learning based on, for example, historical data collected from different surgeries, as discussed herein.

[0071] Figure 10A An exemplary high-level system diagram of an optimal trocar / robot position combination selector 830 based on a weighted sum approach according to an embodiment of the present teachings is depicted. In the illustrated implementation, the optimal trocar / robot combination selector 830 includes a trocar position evaluation feature determiner 1000, a robot base position evaluation feature determiner 1010, a combination feature vector constructor 1030, a combined weighted sum score generator 1050, and an optimal combination selector 1070. Figure 10B is a flow chart of an exemplary process of the optimal trocar / robot combination selector 830 according to an embodiment of the present teachings. In operation, when the combination matrix 900 is received as an input with all combinations, for each combination of trocar / base positions (corresponding to Figure 9A For example, the insertion position evaluation parameter 920-i ( Figure 9B ) may be determined by the trocar position assessment feature determiner 1000 at 1005 and stored at 1012. Similarly, the base position evaluation parameter 920-k ( Figure 9B ) may be determined by the robot base position estimation feature determiner 1010 at 1015 and stored at 1022. The estimation parameters for all trocar positions in all combinations are stored at 1012. The estimation parameters for all robot base positions in all combinations are stored at 1022.

[0072] Based on the evaluation parameters calculated in 1012 and 1022, a combination feature vector constructor 1030 calculates a feature vector for each combination in the combination matrix 900 (input), the feature vector including the evaluation parameters for both the trocar position and the robot base position in the combination, as well as other features. That is, for each cell in the combination matrix 900, a feature vector exists such that, at 1025, the combination feature vector constructor 1030 constructs a trocar / robot combination feature matrix 1040 for all combinations. Then, at 1035, a combination weighted sum score generator 1050 determines a weighted sum score for each combination based on the learned weights of the different features stored in 1060. Based on the weighted sum of the combinations, an optimal combination selector 1070 selects the optimal combination according to the score at 1045 and outputs the selected optimal combination at 1055.

[0073] Other implementations may also be used to select the best combination. For example, the feature vectors can be ranked according to some specified criteria. In some embodiments, the ranking can be achieved by ranking the feature vectors based on some sorting criteria, which can indicate the order of some of the features in the feature vectors. For example, the sorting criteria can indicate that the feature vectors are sorted by using the ascending order of the distance between the cannula needle position and the base position, the ascending order of the angle between the two, ..., the descending order of the features related to the evaluation score, ..., etc. The goal can be to rank the feature vectors according to the desirability of the features through such sorting, so that the best combination can be selected from some of the top-ranked feature vectors. In some embodiments, the highest-ranked combination can be selected. In other embodiments, the best combination can be selected from the top-ranked combinations based on some other additional considerations.

[0074] As discussed herein, different operational models for simultaneously optimizing trocar insertion and robot base position are implemented via a model-based approach. Figure 11A An exemplary high-level system diagram depicts various implementations of the optimal trocar / robot combination selector 830 according to various embodiments of the present teachings. In this mode of operation, the feature vectors of all candidate combinations in the combination matrix 900 are simultaneously considered by a machine-trained model to identify the optimal combination. In this embodiment, the optimal trocar / robot combination selector 830 includes a feature matrix information processor 1100 and a model-based optimal combination generator 1130.

[0075] Figure 11B1 is a flow chart of an exemplary process of the optimal trocar / robot combination selector 830 according to various embodiments of the present teachings. In operation, the feature matrix information processor 1100 receives the feature vectors in the trocar / robot base feature matrix 1040 as input at 1140 and processes these input feature vectors at 1150 to generate processed feature vectors. The processing that can be applied to the feature vectors can include, for example, converting non-numeric feature values ​​to numeric values, converting feature values ​​to a specific range, or normalizing feature values. Then, at 1160, the processed feature vectors can be sent to the machine-trained combination selection model 1120 so that the model can simultaneously consider the processed feature vectors. The combination selection model 1120 can then generate an output corresponding to the optimal combination selected from the input processed feature vectors at 1170.

[0076] In some cases, when the number of combinations is too high and the combination selector model 1120 may have a limit of fewer input feature vectors than the actual number of combinations, the feature matrix information processor 1100 and the model-based optimal combination generator 1130 may collaborate to operate in batch processing mode. In batch mode, the feature matrix information processor 1100 sends batches of feature vectors to the model 1120 at a time. The feature matrix information processor 1100 may inform the model-based optimal combination generator 1130 of the total number and size of feature vectors for each batch. If the former is greater than the latter, the model-based optimal combination generator 1130 calculates the batches required to reach the final optimal combination selection. Upon receiving the optimal combination selected from the batch, the model-based optimal combination generator 1130 determines whether the received selection corresponds to the selected final optimal combination. If not, the received suboptimal combinations may be saved until all suboptimal combinations are received. The suboptimal combinations are then used to inform the feature matrix information processor 1100 to generate a new final batch containing feature vectors corresponding to the selected suboptimal combinations, allowing the combination selection model 1120 to select the final optimal combination. When the model-based best combination generator 1130 receives the final best combination selection, it outputs the selected best combination at 1180 .

[0077] Various aspects of the present teachings have been disclosed. In various embodiments, models trained via machine learning can be used to perform various tasks, including the trocar position optimization model 670 and the robot base optimization model 770 used in a sequential optimization mode of operation, and the model 1060 and the combination selection model 1120 used to learn weights in a simultaneous optimization mode of operation. As discussed herein, these models can be trained via machine learning based on training data generated from historical surgical setup information and its evaluation. Historical data can be collected based on recorded surgical setups, and some of the historical data can be collected automatically and some can be collected manually. Records of surgical operating room setups can be combined with recorded information related to ratings of doctors and nurses who participated in the surgery.

[0078] Evaluations of each surgical setting can also be collected to guide the learning system to learn what is good and what is not so good based on the surgical results and feedback from the people who participated in the surgery. The evaluation can be directed to different aspects related to the surgery, including evaluation of the surgery itself, such as the level of satisfaction of the medical team performing the surgery, the level of events caused by or related to the setting, the extent to which the surgery was prolonged due to changes in the setting, the ratio of the length of the surgery to the average length of the same type of surgery, etc. The evaluation can also be directed to the patient's recovery, including, for example, the speed at which the surgery was performed, whether there were any postoperative problems, such as infection, etc. Such evaluations can be quantified numerically and can be combined to derive an overall numerical score within a predetermined range (e.g., 1-10). Such an overall score without reference to performance can be used as a ground truth in the training data, for example, together with the classification evaluation.

[0079] Figure 12 Depicts an exemplary high-level system diagram for a machine learning mechanism to train different models for use in sequential or simultaneous optimization of trocar / base positions according to an embodiment of the present teachings. In this exemplary embodiment, as Figure 12 The illustrated machine learning mechanism includes a training data collection unit 1200, a training data generation unit 1210, and a training mechanism 1230. In 1240, the training mechanism 1230 may use the training data thus collected and generated (appropriately obtained based on the needs of the learning) to generate a training model in learning.

[0080] In this embodiment, the training mechanism 1230 may include multiple learning engines, each of which may be dedicated to training a corresponding type of model. Figure 12As shown in FIG, the training mechanism 1230 includes a trocar position optimization model training engine 1230-1, a base position optimization model training engine 1230-3, and an optimal combination model training engine 1230-2. The trocar position optimization model training engine 1230-1 can be provided for deriving the trocar position optimization model 670 used in the sequential optimization mode as described herein. The base position optimization model training engine 1230-3 can be provided for deriving the trocar position optimization model 670 and the robotic base optimization model 770 used in the sequential optimization model. The optimal combination model training engine 1230-2 can be provided for deriving learned feature weights 1060 used in the simultaneous optimization scheme based on the weighted sum scheme and the combination selection model 1120 in the simultaneous optimization mode of operation.

[0081] Figure 13 is a schematic diagram of an exemplary mobile device architecture that may be used to implement a dedicated system for implementing the present teachings in accordance with various embodiments. In this example, the user device on which the present teachings may be implemented corresponds to mobile device 1300, including but not limited to smartphones, tablet computers, music players, handheld game consoles, global positioning system (GPS) receivers, and wearable computing devices, or in any other form factor. Mobile device 1300 may include one or more central processing units ("CPUs") 1340, one or more graphics processing units ("GPUs") 1330, a display 1320, memory 1360, a communication platform 1310 (such as a wireless communication module), storage 1390, and one or more input / output (I / O) devices 1350. Any other suitable components, including but not limited to a system bus or controller (not shown), may also be included in mobile device 1300. As Figure 13 As shown, a mobile operating system 1370 (e.g., iOS, Android, Windows Phone, etc.) and one or more applications 1380 can be loaded from storage 1390 into memory 1360 for execution by CPU 1340. Application 1380 can include, at least in part, a user interface for information analysis and management according to the present teachings or any other suitable mobile application on mobile device 1300. User interaction, if any, can be implemented via I / O device 1350 and provided to various components connected via network(s).

[0082] In order to realize each module, unit and function thereof described in the present disclosure, computer hardware platform can be used as (one or more) hardware platform of one or more elements described herein.The hardware components, operating system and programming language of this type of computer are conventional in nature, and it is assumed that those skilled in the art are fully familiar with to adapt these technologies to the appropriate settings described herein.The computer with user interface element can be used to realize personal computer (PC) or other types of workstations or terminal equipment, but if suitable programming, computer can also serve as server.It is believed that those skilled in the art are familiar with the structure, programming and general operation of this type of computer equipment, so accompanying drawing should be self-explanatory.

[0083] Figure 14 1 is a schematic diagram of an exemplary computing device architecture that can be used to implement a dedicated system for implementing the present teachings according to various embodiments. Such a dedicated system in conjunction with the present teachings has a functional block diagram of a hardware platform including user interface elements. The computer can be a general-purpose computer or a special-purpose computer. Both can be used to implement a dedicated system for the present teachings. The computer 800 can be used to implement any component or aspect of the framework disclosed herein. For example, the information analysis and management methods and systems disclosed herein can be implemented on a computer such as computer 1400 via the computer's hardware, software program, firmware, or a combination thereof. Although only one such computer is shown for convenience, the computer functions described herein in connection with the present teachings can be implemented in a distributed manner on several similar platforms to distribute the processing load.

[0084] The computer 1400 includes, for example, a COM port 1450 that is connected to and from a network connected to the COM port 1450 to facilitate data communications. The computer 1400 also includes a central processing unit (CPU) 1420 in the form of one or more processors for executing program instructions. The exemplary computer platform includes an internal communication bus 1410, various forms of program storage and data storage (e.g., disk 1470, read-only memory (ROM) 1430, or random access memory (RAM) 1440) for various data files to be processed and / or transferred by the computer 1400 and possibly program instructions to be executed by the CPU 1420. The computer 1400 also includes an I / O component 1460 that supports input / output flows between the computer and other components in the computer (such as user interface elements 1480). The computer 1400 can also receive programming and data via network communications.

[0085] Thus, as described above, aspects of the information analysis and management methods and / or other processes may be embodied in programming. The programmatic aspects of the technology may be considered to be a "product" or "article of manufacture" typically in the form of executable code and / or associated data executed on or implemented in some type of machine-readable medium. Tangible, non-transitory "storage" type media include any or all of memory or other storage for a computer, processor, or the like, or its associated modules (such as various semiconductor memories, tape drives, disk drives, etc.) that may provide storage for software programming at any time.

[0086] All or part of the software may sometimes be delivered over a network, such as the Internet or various other telecommunication networks. Such communications, for example, may enable software to be loaded from one computer or processor to another, for example, in connection with information analysis and management. Thus, another type of medium that may carry software elements includes optical, electrical, and electromagnetic waves, such as used across physical interfaces between local devices, through wired and optical ground networks, and through various air links. Physical elements that carry such waves, such as wired or wireless links, optical links, or the like, may also be considered to be the medium that carries the software. As used herein, unless limited to tangible "storage" media, terms such as computer or machine "readable media" refer to any medium that participates in providing instructions to a processor for execution.

[0087] Thus, a machine-readable medium can take many forms, including but not limited to tangible storage media, carrier media, or physical transmission media. Non-volatile storage media include, for example, optical or magnetic disks that can be used to implement the system shown in the accompanying drawings or any of the components of the system, such as any of the storage devices or the like in any (one or more) computers. Volatile storage media include dynamic memory, such as the main memory of such a computer platform. Tangible transmission media include coaxial cables; copper wire and optical fiber, including the wires that form a bus within a computer system. Carrier transmission media can take the form of electrical or electromagnetic signals, or acoustic or light waves, such as those generated during radio frequency (RF) and infrared (IR) data communications. Thus, common forms of computer-readable media include, for example, a floppy disk, a flexible disk, a hard disk, magnetic tape, any other magnetic medium, a CD-ROM, a DVD or DVD-ROM, any other optical medium, punched card stock tape, any other physical storage medium with a pattern of holes, RAM, PROM and EPROM, FLASH-EPROM, any other memory chip or cassette, a carrier wave that transports data or instructions, a cable or link that transports such a carrier wave, or any other medium from which a computer can read programming code and / or data. Many of these forms of computer-readable media may be involved in carrying one or more sequences of one or more instructions to a physical processor for execution.

[0088] Those skilled in the art will recognize that the teachings herein are amenable to various modifications and / or enhancements. For example, while the implementation of the various components described above may be embodied in a hardware device, it may also be implemented as a software-only solution, for example, installed on an existing server. Additionally, the technology disclosed herein may be implemented as firmware, a firmware / software combination, a firmware / hardware combination, or a hardware / firmware / software combination.

[0089] Although the foregoing has described what is considered to constitute the present teachings and / or other examples, it should be understood that various modifications may be made thereto, and the subject matter disclosed herein may be implemented in various forms and examples, and the teachings may be applied to many applications, only some of which have been described herein. It is intended that the appended claims claim any and all applications, modifications, and variations that fall within the true scope of the present teachings.

Claims

1. A method implemented on at least one processor, memory, and communication platform, the method comprising: obtaining an instrument access map for a surgical instrument used to perform a surgical procedure on an organ, wherein the instrument access map defines a surface area on the organ having a plurality of cutting points representing a surgical trajectory; acquiring information related to a robot to be deployed for controlling the surgical instrument to perform the surgical operation along the surgical trajectory and a surgical environment in which the surgical operation is to be performed; generating a robot access map comprising one or more robot base locations based on the information, from which a robot is to be deployed to control the surgical instrument to reach the instrument access map; selecting one of the robot base locations from the robot visit map based on an evaluation parameter determined with respect to each of the robot base locations; Control signals are generated for automatically configuring deployment of the robot at a selected robot base position to facilitate the surgical procedure.

2. The method according to claim 1, characterized in that The information includes at least one of the following: the size of the robot; kinematic parameters associated with the robot; Spatial information related to the surgical environment; and A resolution for determining the position of the one or more robot bases.

3. The method according to claim 2, characterized in that The steps of generating the robot access map include: deriving a plurality of candidate robot base positions based on the spatial information and the resolution of the surgical environment; For each of the candidate robot base positions, determining whether the robot can control the surgical instrument to reach the instrument access map based on the kinematic feasibility of the robot, the kinematic feasibility of the robot being determined based on the kinematic parameters; and The robot access map is created by merging those candidate robot base positions of the candidate robot base positions at which the robot can control the surgical instrument to reach the entire instrument access map.

4. The method according to claim 3, characterized in that The ability of the surgical instrument to reach the instrument access map indicates that the tip of the surgical instrument is able to reach the plurality of cutting points included in the instrument access map.

5. The method according to claim 1, wherein The step of selecting one of said robot base positions comprises: For each of said robot base positions, obtaining an evaluation according to a set of evaluation parameters; and The selected robot base position is determined based on the evaluation parameter obtained for each of the robot base positions in the robot visit map.

6. The method according to claim 5, characterized in that The set of evaluation parameters includes at least one of the following: an actual visit map, the actual visit map specifying a sub-area in the instrument visit map that the robot deployed at the robot base position can control the surgical instrument to reach; an overlay indicating a portion of the instrument visit map that overlaps with the actual visit map; the distance from the robot base position to the position of the surgical instrument; an angle between a surface normal at the location of the surgical instrument and a line formed between the robot and the location of the surgical instrument at the location of the robot base; as well as The robot's proximity to a singular point is determined based on a configuration of kinematic parameters required for the robot to control the surgical instrument to reach the plurality of cutting points.

7. The method according to claim 5, characterized in that The step of determining the selected robot base position is based on a robot base position optimization model obtained via machine learning based on training data collected from past historical surgical data.

8. A machine-readable and non-transitory medium having information recorded thereon, wherein: The information, when read by the machine, causes the machine to perform the following steps: obtaining an instrument access map for a surgical instrument used to perform a surgical procedure on an organ, wherein the instrument access map defines a surface area on the organ having a plurality of cutting points representing a surgical trajectory; acquiring information related to a robot to be deployed for controlling the surgical instrument to perform the surgical operation along the surgical trajectory and a surgical environment in which the surgical operation is to be performed; generating a robot access map comprising one or more robot base locations based on the information, from which a robot is to be deployed to control the surgical instrument to reach the instrument access map; selecting one of the robot base locations from the robot visit map based on an evaluation parameter determined with respect to each of the robot base locations; Control signals are generated for automatically configuring deployment of the robot at a selected robot base position to facilitate the surgical procedure.

9. The medium according to claim 8, characterized in that The information includes at least one of the following: the size of the robot; kinematic parameters associated with the robot; Spatial information related to the surgical environment; and A resolution for determining the position of the one or more robot bases.

10. The medium according to claim 9, characterized in that The steps of generating the robot access map include: deriving a plurality of candidate robot base positions based on the spatial information and the resolution of the surgical environment; For each of the candidate robot base positions, determining whether the robot can control the surgical instrument to reach the instrument access map based on the kinematic feasibility of the robot, the kinematic feasibility of the robot being determined based on the kinematic parameters; and The robot access map is created by merging those candidate robot base positions of the candidate robot base positions at which the robot can control the surgical instrument to reach the entire instrument access map.

11. The medium according to claim 10, characterized in that The ability of the surgical instrument to reach the instrument access map indicates that the tip of the surgical instrument is able to reach the plurality of cutting points included in the instrument access map.

12. The medium according to claim 8, characterized in that The step of selecting one of said robot base positions comprises: For each of said robot base positions, obtaining an evaluation according to a set of evaluation parameters; and The selected robot base position is determined based on the evaluation parameter obtained for each of the robot base positions in the robot visit map.

13. The medium according to claim 12, characterized in that The set of evaluation parameters includes at least one of the following: an actual visit map, the actual visit map specifying a sub-area in the instrument visit map that the robot deployed at the robot base position can control the surgical instrument to reach; an overlay indicating a portion of the instrument visit map that overlaps with the actual visit map; the distance from the robot base position to the position of the surgical instrument; an angle between a surface normal at the location of the surgical instrument and a line formed between the robot and the location of the surgical instrument at the location of the robot base; as well as The robot's proximity to a singular point is determined based on a configuration of kinematic parameters required for the robot to control the surgical instrument to reach the plurality of cutting points.

14. The medium according to claim 12, wherein The step of determining the selected robot base position is based on a robot base position optimization model obtained via machine learning based on training data collected from past historical surgical data.

15. A system comprising a robot base position optimizer implemented by a processor and configured to: obtaining an instrument access map for a surgical instrument used to perform a surgical procedure on an organ, wherein the instrument access map defines a surface area on the organ having a plurality of cutting points representing a surgical trajectory; acquiring information related to a robot to be deployed for controlling the surgical instrument to perform the surgical operation along the surgical trajectory and a surgical environment in which the surgical operation is to be performed; generating a robot access map comprising one or more robot base locations based on the information, from which a robot is to be deployed to control the surgical instrument to reach the instrument access map; selecting one of the robot base locations from the robot visit map based on an evaluation parameter determined with respect to each of the robot base locations; Control signals are generated for automatically configuring deployment of the robot at a selected robot base position to facilitate the surgical procedure.

16. The system according to claim 15, wherein: The information includes at least one of the following: the size of the robot; kinematic parameters associated with the robot; Spatial information related to the surgical environment; and A resolution for determining the position of the one or more robot bases.

17. The system according to claim 16, wherein: The steps of generating the robot access map include: deriving a plurality of candidate robot base positions based on the spatial information and the resolution of the surgical environment; For each of the candidate robot base positions, determining whether the robot can control the surgical instrument to reach the instrument access map based on the kinematic feasibility of the robot, the kinematic feasibility of the robot being determined based on the kinematic parameters; and The robot access map is created by merging those candidate robot base positions of the candidate robot base positions at which the robot can control the surgical instrument to reach the entire instrument access map.

18. The system according to claim 17, wherein: The ability of the surgical instrument to reach the instrument access map indicates that the tip of the surgical instrument is able to reach the plurality of cutting points included in the instrument access map.

19. The system according to claim 15, wherein: The step of selecting one of said robot base positions comprises: For each of said robot base positions, obtaining an evaluation according to a set of evaluation parameters; and The selected robot base position is determined based on the evaluation parameter obtained for each of the robot base positions in the robot visit map.

20. The system according to claim 19, wherein: The set of evaluation parameters includes at least one of the following: an actual visit map, the actual visit map specifying a sub-area in the instrument visit map that the robot deployed at the robot base position can control the surgical instrument to reach; an overlay indicating a portion of the instrument visit map that overlaps with the actual visit map; the distance from the robot base position to the position of the surgical instrument; an angle between a surface normal at the location of the surgical instrument and a line formed between the robot and the location of the surgical instrument at the location of the robot base; as well as The robot's proximity to a singular point is determined based on a configuration of kinematic parameters required for the robot to control the surgical instrument to reach the plurality of cutting points.

21. The system according to claim 19, wherein: The step of determining the selected robot base position is based on a robot base position optimization model obtained via machine learning based on training data collected from past historical surgical data.

Images