A differentiable simulator for simulating the cutting of soft materials by a cutting instrument is provided. In accordance with one aspect of the disclosure, a method for simulating a cutting operation includes: receiving a mesh for an object, modifying the mesh to add virtual nodes associated with a predefined cutting plane, optimizing a set of parameters associated with a simulator based on ground-truth data, and running a simulation via the simulator to generate outputs that include trajectories associated with a cutting instrument. Optimizing the set of parameters can include performing inference based on a set of ground-truth trajectories captured using sensors to measure real-world cutting operations. The inference techniques can employ stochastic gradient descent, stochastic gradient Langevin dynamics, or a Bayesian approach. In an embodiment, the simulator can be utilized to generate control signals for a robot based on the simulated trajectories.

An automated container cutting system for cutting a container includes a cutting platform and a cutting tool held by the cutting platform. The cutting tool is configured to cut the container. The automated container cutting system includes a force feedback sensor operatively connected to the cutting tool such that the force feedback sensor is configured to measure resistive force exerted on the cutting tool. The automated container cutting system includes at least one processor communicatively coupled to the force feedback sensor. The processor is configured to receive resistive force data from the force feedback sensor. The resistive force data represents resistive force exerted on the cutting tool as the cutting tool pierces a wall of the container. The at least one processor is configured to determine whether the cutting tool has penetrated through the wall of the container using the received resistive force data.

An automated container cutting system for cutting a container includes a cutting platform and a cutting tool held by the cutting platform. The cutting tool is configured to cut the container. The automated container cutting system includes a force feedback sensor operatively connected to the cutting tool such that the force feedback sensor is configured to measure resistive force exerted on the cutting tool. The automated container cutting system includes at least one processor communicatively coupled to the force feedback sensor. The processor is configured to receive resistive force data from the force feedback sensor. The resistive force data represents resistive force exerted on the cutting tool as the cutting tool pierces a wall of the container. The at least one processor is configured to determine whether the cutting tool has penetrated through the wall of the container using the received resistive force data.

A spearing end effector for a robotic spearing device capturing and sorting a selected item from a mass of items and having a robotic manipulator with the spearing end effector mounted at an end thereof. The robotic spearing device comprises: a spearing end effector body; a spike; a linear actuator having the spike mounted thereon; and a propeller. The spike is configurable between a retracted configuration where it is entirely located inside the spearing end effector body and an extended configuration where it extends outwardly from therefrom. The spike is engageable to the selected item when configured in the extended configuration. The linear actuator is movable to configure the spike between the retracted configuration and the extended configuration. The propeller is selectively activatable to propel the selected item in a propelling direction during an ejection of the selected item from the spearing end effector.

A method and system for micro-force guided cooperative control that assists the operator in manipulating tissue in the direction of least resistance. A tool holder receives a surgical tool adapted to be held by a robot and a surgeon. A first sensor measures interaction forces between a tip of the surgical tool and tissue of a region of interest. A second sensor measures interaction forces between the surgeon and a handle to the surgical tool. A data processor is configured to perform an algorithm to actively guide the surgical tool by creating a bias towards a path of least resistance and limit directional tool forces of the surgical tool as a function of handle input forces and tip forces. This function offers assistance to challenging retinal membrane peeling procedures that require a surgeon to delicately delaminate fragile tissue that is susceptible to hemorrhage and tearing due to undesirable forces.