MAKO Surgical

A surgical robotics system includes a robotic arm, a first cutting tool, a second cutting tool, and a computer. The computer is programmed to obtain a planned pose of an implant augment relative to a bone, the implant augment having a curved side and a flat side, determine whether the curved side or the flat side faces the bone, in response to a determination that the curved side faces the bone, control the robotic arm to guide the first cutting tool to prepare the bone to receive the implant augment, and in response to a determination that the flat side faces the bone, control the robotic arm to guide the second cutting tool to prepare the bone to receive the implant augment.

Surgical systems and methods involve a surgical robot configured to support and move a surgical tool, a tracking system configured to track a position of a surgical staff member, and one or more controllers coupled to the surgical robot and the tracking system. The controller(s) define a first virtual zone and a second virtual zone relative to the surgical robot, detect a positioning of the surgical staff member in the first virtual zone based on tracked position data, and in response, trigger a first control mode for the surgical robot. The controller(s) further detect a positioning of the surgical staff member in the second virtual zone and, in response, trigger a second control mode for the surgical robot that is different from the first control mode.

Disclosed herein is a system for machine learning assisted surgical planning. The system can include a data acquisition module configured to collect preoperative data, intraoperative data, and postoperative data. The preoperative data can include any of imaging data, patient-reported outcome measures and functional metrics. The intraoperative data can include kinematic assessment of a knee joint. The postoperative data can include any of functional recovery metrics, radiographic data, and adverse event tracking. The system can include a machine learning model configured to process the preoperative data, intraoperative data, and postoperative data to identify patterns and relationships between surgical planning attributes and patient-specific outcomes, and generate predictive outputs including recommendations for the surgical planning attributes.

Surgical or medical systems and methods involve a manipulator to facilitate collaborative interaction with a human. A control system is coupled to the manipulator and is configured to acquire robotic data from the manipulator during the collaborative interaction. The control system implements a machine learning model that is configured to receive and process the robotic data to determine an interaction style of the human in collaborating with the manipulator. The control system customizes a physical feel of the manipulator based on the interaction style.

A registration system including a bone pin guide and a bone pin clamp. The bone pin guide may include a guide body, a first guide including a first guide through-hole having a first longitudinal axis, and a second guide including a second guide through-hole having a second longitudinal axis. The bone pin guide may guide first and second bone pins into a bone via the first and second guides. The bone pin clamp may include a clamp body, first, second, and third clamp through-holes extending through the clamp body, a plurality of registration indents defined on the clamp body, and a clamping mechanism including at least one adjustable fastener. The bone pin clamp may receive the first and second bone pins in the first and third clamp through-holes and guide a third bone pin into the bone via the second clamp through-hole.

An interlocking collet system (304, 404) comprises a housing (314, 414) configured to extend along an axis (A) between first and second ends (316, 318; 416, 418) and an outer surface (330, 430) defining a first attachment surface (310A, 410A) and a second attachment surface (310B, 410B), and a slider (354, 454) defining a bore (320, 420) for receiving the first and second locking members (424) disposed within the bore (320, 420) of the slider (354, 454) and each being moveable along the axis (A). The first attachment surface (310A, 410A) and the second attachment surface (310B, 410B) each comprise a first portion (311A, 311B; 411A, 411B) and a second portion (313A, 313B, 413A, 413B) defining a recess (336A, 336B; 436A, 436B) in the outer surface (330, 430) of the housing (314, 414). The first portion (311A, 311B; 411A, 411B) of the first attachment surface (310A, 410A) and the second attachment surface (310B, 410B) is oriented at a first slope relative to the outer surface (330, 430), and the second portion (313A, 313B, 413A, 413B) of the first attachment surface (310A, 410A) and the second attachment surface (310B, 410B) is oriented at a second slope relative to the outer surface (330, 430).

Robotic surgical systems and methods involve a tool to manipulate a surgical site and a manipulator to support and move the tool. Controller(s) control the manipulator to facilitate movement of the tool along a tool path for treating the surgical site. During movement of the tool along the tool path, the controller(s) detect a reorientation of the tool and record a location at which the reorientation occurred. The controller(s) generate virtual constraint(s) which cause the manipulator to reorient the tool in response to the tool revisiting the recorded location. In some instances, the controller(s) predictively detect, relative to the tool path, the location at which the tool should be re-orientated, and in response to the tool reaching the predictively detected location, the controller(s) utilize the virtual constraint(s) to cause the manipulator to re-orient the tool.

A surgical system (20) for removing material from a target bone (TS) during a surgical procedure, wherein a retractor (162) is located near the target bone (TS), comprises a robotic manipulator (66) configured to support and move a surgical instrument (30) to remove material from the target bone (TS), a vision device (72) attached to one of the robotic manipulator (66) or the surgical instrument (30) such that the vision device (72) is movable with the robotic manipulator (66) in a plurality of degrees of freedom, wherein the vision device (72) is configured to capture vision data sets of the target bone (TS) and the retractor (162) from multiple perspectives based on movement of the robotic manipulator (66), and a computing system (62) being in communication with the robotic manipulator (66) and the vision device (72). The computing system (62) is configured to detect the retractor (162) based on one or more features of the retractor (162) that are identifiable in the vision data sets, associate a virtual object (162) with the retractor (162) based on the one or more features of the retractor (162) identifiable in the vision data sets, track movement of the surgical instrument (30) relative to the virtual object (162), and, based on the tracked movement, enable manipulator movement of the surgical instrument (30) to prevent collision of the surgical instrument (30) with the retractor (162).

Systems and methods for optimizing tracking an object in a surgical workspace. A tracker is disposed relative to the object that includes a predefined geometry of markers for tracking a pose of the tracker in the surgical workspace. A localizer camera cooperates with the tracker to generate image data indicating a blob for each of the markers generated from a light signal received from the marker. A characteristic of each blob is acquired, and the acquired characteristics are compared to an optimal characteristic. Based on the comparison, the operation of the trackers, the localizer, or both are adjusted to optimize the blobs generated from the markers.

Surgical systems and methods involving machine learning model(s) to characterize tool interactions. The tool may be coupled to a robotic manipulator and configured to manipulate a tissue. A sensing system measures displacements of the tool, velocities of the tool, and interaction forces applied to the tool. A control system controls the manipulator to move the tool to interact with the tissue. Responsive to interactions of the tool with the tissue over time, the control system obtains measured values of the displacements, velocities, and interaction forces, from the sensing system. The control system implements the machine learning model to receive and process the measured values to estimate stiffness/damping parameters of the tissue and evaluate changes in the estimated stiffness/damping parameters to generate a characterization about the tissue or the tool's interaction with the tissue. The control system controls the manipulator and/or the tool based on the characterization.