Disney Enterprises, Inc.

Christian Gabriel Schumacher

Moritz Niklaus Bächer

Lars Espen Knoop

Stelian Coros

Alfredo Medina Ayala

Kyle Michael Cesare

Michael Anthony Hopkins

Sungjoon Choi

Tanner J Rinke

Venkata Krishna Tamminana

Jonas Alois Zehnder

A new controller for use in robots with kinematic loops as well as in most other types of robots (such as those with fully actuated kinematic trees). The controller includes an inverse kinematics (IK) module that implements a versatile IK formulation for retargeting of motions, including expressive motions, onto mechanical systems (i.e., robots with loops and/or without loops). Further, the controller is configured to support the precise control of the position and orientation of end effectors and the center of mass (CoM) (such as of walking robots). The formulation of the algorithms carried out by the IK module safeguards against a disassembly when IK targets are moved outside the workspace of the robot. A regularizer is included in the controller that smoothly circumvents kinematic singularities where velocities go to infinity.

Robot with an inverse kinematics (IK)-based controller for retargeting input motions

A robot control method, and associated robot controllers and robots operating with such methods and controllers, providing real-time vibration suppression. The control method involves learning to support real-time, vibration-suppressing control. The method uses state-of-the-art machine learning techniques in conjunction with a differentiable dynamics simulator to yield fast and accurate vibration suppression. Vibration suppression using offline simulation approaches that can be computationally expensive may be used to create training data for the controller, which may be provide by a variety of neural network configurations. In other cases, sensory feedback from sensors onboard the robot being controlled can be used to provide training data to account for wear of the robot's components.

Robotic systems using learning to provide real-time vibration-suppressing control

A 3D printer system with a structural optimization tool to generate 3D models optimized for build materials such as those used in binder jetting technology-based printers. The structural optimization tool uses a computational approach to optimize mechanical and mass properties of large-scale structures (i.e., objects to be 3D printed), and the computational approach is tailored for fabrication on binder jetting technologies. To spend a material budget for printing an object wisely, the inventors in designing the computational approach turned the Bresler-Pister failure criterion into an objective measuring the potential of failure of an object or structure. This involved modeling the difference in tensile and compressive strength of the build material. To optimize structures under worst-case loads, the computational approach unifies an optimization to identify worst-case loads with an optimization to minimize the resulting failure potential, nesting them with first-order optimality constraints.

Optimizing 3D printed large-scale structures under worst-case loads

Growing community of inventors

Zurich, Switzerland

Christian Gabriel Schumacher