Abstract: Apparatuses, systems, and techniques to control a real-world and/or virtual device (e.g., a robot). In at least one embodiment, the device is controlled based, at least in part on, for example, one or more neural networks. Parameter values for the neural network(s) may be obtained by training the neural network(s) to control movement of a first agent with respect to at least one first target while avoiding collision with at least one stationary first holder of the at least one first target, and updating the parameter values by training the neural network(s) to control movement of a second agent with respect to at least one second target while avoiding collision with at least one non-stationary second holder of the at least one second target.

Abstract: A surgical metal detection apparatus. The apparatus comprises an elongate, tubular cannula and a removable element, which may be a trocar, releasably engaged within the cannula. A metal detection coil is positioned within the removable element or, in some embodiments, within the cannula. The metal detection coil is connected to a metal detection circuit which is adapted to detect the presence of a metallic element proximate to the end of the removable element or cannula. When a metallic element has been detected, the removable element may be removed from the cannula to permit the passage of a removal tool, such as a screwdriver, through the cannula without removing or changing the position of the cannula.