Sanctuary Cognitive Systems Corporation

A software compensated robotic system makes use of recurrent neural networks and image processing to control operation and/or movement of an end effector. Images are used to compensate for variations in the response of the robotic system to command signals. This compensation allows for the use of components having lower reproducibility, precision and/or accuracy that would otherwise be practical.

Provided is a process that includes obtaining data indicative of state of a dynamic mechanical system and an environment of the dynamic mechanical system, the data comprising a plurality of channels of data from a plurality of different sensors including a plurality of cameras and other sensors indicative of state of actuators of the dynamic mechanical system; forming a training set from the obtained data by segmenting the data by time and grouping segments from the different channels by time to form units of training data that span different channels among the plurality of channels; training a metric learning model to encode inputs corresponding to the plurality of channels as vectors in an embedding space with self-supervised learning based on the training set; and using the trained metric learning model to control the dynamic mechanical system or another dynamic mechanical system.

Provided are systems and methods for a touch sensor system for a robot end effector using a time-of-fight (TOF) system. A robot end effector includes a digit, and a tactile sensor system coupled to the digit. The tactile sensor system includes a set of fiber optic cables carried by the digit, wherein each fiber optic cable has a respective length and a first end of each fiber optic cable is at a distal end of the digit. A TOF sensor is coupled to a second end of each fiber optic cable, wherein the TOF sensor emits light through the set of fiber optic cables and receives light reflected by an object at or proximate the distal end of the digit through the set of fiber optic cables. A distance to the at least one object is calculated from a TOF path including the length(s) of the cable(s).

Systems, methods, and computer program products for managing and populating environment models are described. An environment model is accessed which represents an environment, and the environment model is populated with instances of object models. Locations where the instances of object models should be positioned in the environment model are identified, by determining where in the environment model a respective size of each instance when viewed from a vantage point at the environment model matches a size of the object represented by the respective instance when viewed from a corresponding vantage point at the environment.

Systems, methods, and computer program products for managing and populating environment models are described. An environment model is accessed which represents an environment, and the environment model is populated with instances of object models. Locations where the instances of object models should be positioned in the environment model are identified, by determining where in the environment model a respective size of each instance when viewed from a vantage point at the environment model matches a size of the object represented by the respective instance when viewed from a corresponding vantage point at the environment.

A linear actuator includes a coupling stack having a shaft coupling, a first thrust bearing adjacent to a first end face of the shaft coupling, and a second thrust bearing adjacent to a second end face of the shaft coupling. The first thrust bearing and the second thrust bearing support axial loads applied to the shaft coupling. A ball screw includes a ball screw shaft extending through a bore of the first thrust bearing and rigidly coupled to the shaft coupling. A motor includes a motor shaft extending through a bore of the second thrust bearing and rigidly coupled to the shaft coupling. The shaft coupling, the ball screw shaft, and the motor shaft are axially aligned with a longitudinal axis of the actuator. The motor is operable to apply a torque to the motor shaft that is transmitted to the ball screw shaft through the shaft coupling.

A dynamic system controller includes a first error detection unit that determines a first error between a joint state and a joint state target. The joint state describes an actual state of a set of joints in a dynamic body. The set of joints has one or more degrees of freedom that are controlled by a set of actuators. An impedance controller generates an impedance torque or force based on the first error. A first neural network accepts the joint state target and outputs an estimated actuation force. A second error detection unit determines a second error between an actual actuation force applied to the set of joints by the set of actuators at the joint state and a combination of the impedance torque or force and the estimated actuation force. A force controller generates a set of actuation commands based on the second error.

A compliant covering for a hand includes a sheath having an interior space to receive at least a part of the hand. The sheath includes an inner sheath layer having an inner surface defining a boundary of the interior space. The inner layer is formed of a first material. The sheath includes an outer sheath layer at least partially covering an exterior of the inner sheath layer. The outer sheath layer has an outer surface forming an exterior of the sheath. The outer sheath layer is formed of a second material having a higher abrasion resistance compared to the first material.

A tactile sensing system includes a compliant tactile sensor having a first compliant member and a sensing circuit arranged to detect and measure a response of the first compliant member to contact forces applied to the first compliant member. The tactile sensing system includes a sensor contact disposed adjacent to the first compliant member to mechanically engage and apply a first contact force to the first compliant member in response to a second contact force applied to the sensor contact.

Systems, methods, and computer program products for managing and populating environment models are described. An environment model is accessed which represents an environment, and the environment model is populated with instances of object models. Locations where the instances of object models should be positioned in the environment model are identified, by determining where in the environment model a respective size of each instance when viewed from a vantage point at the environment model matches a size of the object represented by the respective instance when viewed from a corresponding vantage point at the environment.