Systems and methods for work volume mapping to facilitate dynamic collision avoidance
A system according to at least one embodiment of the present disclosure includes a processor; and a memory coupled with the processor and including data stored thereon that, when processed by the processor, enables the processor to: predict, at a first time, a motion of an object during a surgical procedure and at a second time following the first time; and update, based on the predicted motion of the object, a surgical navigation path of a robotic arm.
1 . A system, comprising:
a processor; and
a memory coupled with the processor and comprising data stored thereon that, when processed by the processor, enables the processor to:
predict, at a first time, a motion of an object from a first location to a second location during a surgical procedure at a second time following the first time;
generate a three-dimensional (3D) map of a working volume in which a surgical tool performs at least a portion of the surgical procedure and that is proximate to at least one of a patient and a surgeon, wherein the 3D map comprises a heat map with at least one sub-volume to be avoided by a robotic arm, wherein the heat map comprises at least one error boundary that is defined based on a predetermined threshold distance around the predicted second location of the object at the second time, and wherein the robotic arm is positioned within the at least one error boundary of the predicted second location; and
update, based on the predicted motion of the object and the at least one error boundary, a surgical navigation path of the robotic arm, wherein the updating comprises generating a plurality of surgical navigation paths and selecting an alternative surgical navigation path of the plurality of surgical navigation paths that avoids passing through the at least one sub-volume, and wherein the alternative surgical navigation path moves the robotic arm out of the predicted second location.
2 . The system of claim 1 , wherein the predicted motion is based on one or more of a type of surgeon, a surgeon performing a surgery, a type of surgical procedure, a time of day, a patient position, a surgical room, and a duration of a surgery.
3 . The system of claim 1 , wherein the data comprises a machine learning model, and wherein the predicted motion is based on the machine learning model processing sensor input received during the surgical procedure.
4 . The system of claim 1 , wherein the at least one sub-volume is determined based on the predicted motion of the object.
5 . The system of claim 4 , wherein the at least one sub-volume comprises a high probability zone that is defined based on the predicted motion of the object.
6 . The system of claim 4 , wherein the surgical navigation path of the robotic arm at the first time passes through a first sub-volume of the at least one sub-volume, and wherein the updated surgical navigation path avoids passing through the first sub-volume at the second time.
7 . The system of claim 1 , wherein the predicted motion is based on sensor input received from at least one of an imaging sensor and a depth sensor.
8 . The system of claim 1 , wherein the working volume comprises an area occupied by both the surgeon and the robotic arm, and wherein the plurality of surgical navigation paths are generated based on at least one of a type of the surgical procedure and a duration of the surgical procedure.
9 . A method, comprising:
receiving, from a first sensor, data comprising information related to a motion of an object at a first time away from a first position;
predicting, at the first time, a second position of an object at a second time later than the first time;
generating a three-dimensional (3D) map of a working volume in which a surgical tool performs at least a portion of a surgical procedure and that is proximate at least one of a patient and a surgeon, wherein the 3D map comprises a heat map with at least one first sub-volume to be avoided by a robotic arm and a second sub-volume that the robotic arm passes through, wherein the heat map comprises at least one error boundary that is defined based on a predetermined threshold distance around the predicted second position of the object at the second time, and wherein the robotic arm is positioned within the at least one error boundary of the predicted second position; and
updating, based on the predicted motion of the object and the at least one error boundary, a surgical navigation path of the robotic arm, wherein the updating comprises generating a plurality of surgical navigation paths and selecting an alternative surgical navigation path of the plurality of surgical navigation paths that avoids passing through the at least one first sub-volume, and wherein the alternative surgical navigation path moves the robotic arm out of the predicted second position.
10 . The method of claim 9 , wherein the predicted motion is based on one or more of a type of surgery, a surgeon performing a surgery, a type of surgical procedure, a time of day, a patient position, a surgical room, and a duration of a surgery.
11 . The method of claim 9 , wherein the data comprises a machine learning model, and wherein the predicted motion of the object at the second time is based on the machine learning model processing the data from the first sensor.
12 . The method of claim 9 , wherein the first sub-volume is at least partially contained within the second sub-volume.
13 . The method of claim 9 , further comprising:
halting a movement of the robotic arm when the robotic arm is within a threshold distance of the first sub-volume.
14 . The method of claim 9 , wherein the first sub-volume is at least partially determined by the predicted motion of the object.
15 . The method of claim 9 , wherein the first sensor is at least one of an imaging sensor and a depth sensor.
16 . A system, comprising:
a processor;
a first robotic arm; and
a memory coupled with the processor and comprising data stored thereon that, when processed by the processor, enables the processor to:
determine, at a first time, a first position of an object during a surgical procedure;
predict, at the first time and based on the first position of the object, a second position of the object at a second time;
generate a three-dimensional (3D) map of a working volume in which a surgical tool performs at least a portion of the surgical procedure and that is proximate to at least one of a patient and a surgeon, wherein the 3D map comprises a heat map with at least one sub-volume to be avoided by the first robotic arm, wherein the heat map comprises at least one error boundary that is defined based on a predetermined threshold distance around the predicted second position of the object at the second time, and wherein the first robotic arm is positioned within the at least one error boundary of the predicted second position of the object; and
update, based on the predicted second position of the object and the at least one error boundary, a surgical navigation path of the first robotic arm, wherein the updating comprises generating a plurality of surgical navigation paths and selecting an alternative surgical navigation path of the plurality of surgical navigation paths that avoids passing through the at least one sub-volume, wherein the alternative surgical navigation path moves the first robotic arm out of the predicted second position of the object.
17 . The system of claim 16 , wherein the data further enables the processor to:
register one or more portions of the object to the first robotic arm.
18 . The system of claim 16 , wherein the at least one error boundary is further associated with the first position of the object.