Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

Devices, systems, and methods for avoiding collisions between a manipulator arm and an outer patient surface by moving the manipulator within a null-space. In response to a determination that distance between an avoidance geometry and obstacle surface, corresponding to a manipulator-to-patient distance is less than desired, the system calculates movement of one or more joints or links of the manipulator within a null-space of the Jacobian to increase this distance. The joints are driven according to the reconfiguration command and calculated movement so as to maintain a desired state of the end effector. In one aspect, the joints are also driven according to a calculated end effector displacing movement within a null-perpendicular-space of the Jacobian to effect a desired movement of the end effector or remote center while concurrently avoiding arm-to-patient collisions by moving the joints within the null-space.

Generating a robot control policy that regulates both motion control and interaction with an environment and/or includes a learned potential function and/or dissipative field. Some implementations relate to resampling temporally distributed data points to generate spatially distributed data points, and generating the control policy using the spatially distributed data points. Some implementations additionally or alternatively relate to automatically determining a potential gradient for data points, and generating the control policy using the automatically determined potential gradient. Some implementations additionally or alternatively relate to determining and assigning a prior weight to each of the data points of multiple groups, and generating the control policy using the weights. Some implementations additionally or alternatively relate to defining and using non-uniform smoothness parameters at each data point, defining and using d parameters for stiffness and/or damping at each data point, and/or obviating the need to utilize virtual data points in generating the control policy.

Devices, systems, and methods for avoiding collisions between a manipulator arm and an outer patient surface by moving the manipulator within a null-space. In response to a determination that distance between an avoidance geometry and obstacle surface, corresponding to a manipulator-to-patient distance is less than desired, the system calculates movement of one or more joints or links of the manipulator within a null-space of the Jacobian to increase this distance. The joints are driven according to the reconfiguration command and calculated movement so as to maintain a desired state of the end effector. In one aspect, the joints are also driven according to a calculated end effector displacing movement within a null-perpendicular-space of the Jacobian to effect a desired movement of the end effector or remote center while concurrently avoiding arm-to-patient collisions by moving the joints within the null-space.

Devices, systems, and methods for avoiding collisions between a manipulator arm and an outer patient surface by moving the manipulator within a null-space. In response to a determination that distance between an avoidance geometry and obstacle surface, corresponding to a manipulator-to-patient distance is less than desired, the system calculates movement of one or more joints or links of the manipulator within a null-space of the Jacobian to increase this distance. The joints are driven according to the reconfiguration command and calculated movement so as to maintain a desired state of the end effector. In one aspect, the joints are also driven according to a calculated end effector displacing movement within a null-perpendicular-space of the Jacobian to effect a desired movement of the end effector or remote center while concurrently avoiding arm-to-patient collisions by moving the joints within the null-space.

Devices, systems, and methods for avoiding collisions between a manipulator arm and an outer patient surface by moving the manipulator within a null-space. In response to a determination that distance between an avoidance geometry and obstacle surface, corresponding to a manipulator-to-patient distance is less than desired, the system calculates movement of one or more joints or links of the manipulator within a null-space of the Jacobian to increase this distance. The joints are driven according to the reconfiguration command and calculated movement so as to maintain a desired state of the end effector. In one aspect, the joints are also driven according to a calculated end effector displacing movement within a null-perpendicular-space of the Jacobian to effect a desired movement of the end effector or remote center while concurrently avoiding arm-to-patient collisions by moving the joints within the null-space.