Palo Alto Research Center Inc.

Rios Intelligent Machines, Inc.

The Procter Gamble Company

Xerox Corporation

Palo Alto Research Corporation Incorporated

Rioa Intelligent Machines, Inc.

Christopher A Paulson

Bernard D Casse

Patrick Yasuo Maeda

Ashish V Pattekar

Clinton J Smith

Christopher Lalau Keraly

Matthew E Shaffer

Raj B Apte

Erik John Hasenoehrl

Ramkumar Abhishek

Steven E Ready

George Daniel

Robert Anthony Street

Philipp Helmut Schmaelzle

Janos Veres

Jonathan Rivnay

David Kalman Biegelsen

Lars Erik Swartz

Nicholas L Choi

Leo Keselman

Laura Stelzner

Eric Peeters

Armin R Volkel

David Mathew Johnson

Gregory Lewis Whiting

Eric Saund

Alan G Bell

Jessica Louis Baker Rivest

Gregory J Kovacs

Scott J Limb

Bhaskar Saha

Martin Sheridan

Gregory Joseph Kovacs

Krishnan Thyagarajan

Vedasri Vedharathinam

Gregory Burton

Jianer Bao

Erica Ronchetto

Laura L Sullivan

Kent A Evans

Anthony Canalungo

Shane Patrick Ahern

Ellen Isaacs

Erick John Hasenoehrl

A work cell and method for automatically separating objects disposed in 3D clusters includes dispensing the objects onto a horizontal conveying surface to form a 2D array, reforming the 2D array into a 1D stream in which the objects move in single-file in a predefined moving direction, utilizing a vision-based or other stationary sensing system to identify a selected target object in the 1D stream as the target object passes through an image capture (sensing) region, calculating trajectory data defining the target object's time-based position in the 1D stream, and then utilizing the trajectory data to control a robot arm or other object removal mechanism such that only the selected object is forcibly removed (e.g., swiped or picked-up) from the horizontal conveying surface. A continuous-loop-type conveying mechanism includes two parallel conveyor-belt-type conveying structures and associated belt-switching structures. An AI-powered vision system identifies new object shapes during preliminary learning phases.

Automatically individually separating bulk objects

A human-like tactile perception apparatus for providing enhanced tactile information (feedback data) from an end-effector/gripper to the control circuit of an arm-type robotic system. The apparatus's base structure is attached to the gripper's finger and includes a flat/planar support plate that presses a pressure sensor array against a target object during operable interactions. The pressure sensor array generates pressure sensor data that indicates portions of the array contacted by surface features of the target object. A sensor data processing circuit generates tactile information in response to the pressure sensor data, and then transmits the tactile information to the robotic system's control circuit. An optional mezzanine connector extends through an opening in the support plate to pass pressure sensor data to the processing circuit. An encapsulating layer covers the pressure sensor array and transmits pressure waves generated by slipping objects to enhance the tactile information.

Tactile perception apparatus for robotic systems

An automated food production work cell includes a robotic system that utilizes a food-grade robotic gripper to transfer individual food items. The robotic gripper is constructed using food-grade materials and includes finger structures that are linearly movably connected by linear bearings to parallel guide rods and are independently driven by a non-contact actuating system to grasp targeted food items disposed on a first work surface, to hold the targeted food items while the robotic system moves the gripper to a second work surface, and to release the targeted food items onto the second work surface. Encoding and external sensing systems facilitate fully automated food transfer processes. Optional sensor arrays are disposed on tip portions of the finger structures to provide feedback data (e.g., grasping force/pressure). Two or more pairs of independently controlled finger structures are provided to facilitate the transfer of multiple food items during each transfer process.

Food-grade robotic gripper for automated production work cell

A robotic gripper (end effector) for an arm-type robotic system includes a hierarchical sensor architecture that utilizes a central data processing circuit to generate rich sensory tactile data in response to pressure, temperature, vibration and/or proximity sensor data generated by finger-mounted sensor groups in response to interactions between the robotic gripper and a target object during robotic system operations. The rich sensory tactile data is used to generate feedback signals that directly control finger actuators and/or tactile information that is supplied to the robotic system's control circuit. Sensor data processing circuits are configured to receive single-sensor data signals in parallel from the sensor groups, and to transmit corresponding finger-level sensor data signal on a serial bus/signal line to the central data processing circuit. Each sensor group and an associated sensor data processing circuit are disposed on a PCB structure and mounted on a contact portion of an associated gripper finger.

Robotic gripper with integrated tactile sensor arrays

A neuromodulator includes one or more coil sets. Each of the coil sets has three coils aligned to produce magnetic and electric fields in three different directions. A plurality of conductors couple the coils of the one or more coil sets to one or more input signals such that each of the coils is independently activated via an individually selectable current applied through the conductors. The individual activation creates a resultant field that is a combination of the magnetic and electric fields in three different directions for each of the coil sets.

Three-dimensional coil set used for neuromodulation

A flex-rigid sensor apparatus for providing sensor data from sensors disposed on an end-effector/gripper to the control circuit of an arm-type robotic system. The apparatus includes piezo-type pressure sensors sandwiched between lower and upper PCB stack-up structures respectively fabricated using rigid PCB (e.g., FR-4) and flexible PCB (e.g., polyimide) manufacturing processes. Additional (e.g., temperature and proximity) sensors are mounted on the upper/flexible stack-up structure. A spacer structure is disposed between the two stack-up structures and includes an insulating material layer defining openings that accommodate the pressure sensors. Copper film layers are configured to provide Faraday cages around each pressure sensor. The pressure sensors, additional sensors and Faraday cages are connected to sensor data processing and control circuitry (e.g., analog-to-digital converter circuits) by way of signal traces formed in the lower and upper stack-up structures and in the spacer structure. An encapsulation layer is formed on the upper PCB stack-up structure.

Flex-rigid sensor array structure for robotic systems

A robotic network includes multiple work cells that communicate with a cloud server using a network bus (e.g., the Internet). Each work cell includes an interface computer and a robotic system including a robot mechanism and a control circuit. Each robot mechanism includes an end effector/gripper having integral multimodal sensor arrays that measure physical parameter values (sensor data) during interactions between the end effector/gripper and target objects. The cloud server collects and correlates sensor data from all of the work cells to facilitate efficient diagnosis of problematic robotic operations (e.g., accidents/failures), and then automatically updates each work cell with improved operating system versions or AI models (e.g., including indicator parameter value sets and associated secondary robot control signals that may be used by each robot system to detect potential imminent robot accidents/failures during subsequent robot operations.

Robotic work cell and network

A multimodal sensing architecture utilizes an array of single sensor or multi-sensor groups (superpixels) to facilitate advanced object-manipulation and recognition tasks performed by mechanical end effectors in robotic systems. The single-sensors/superpixels are spatially arrayed over contact surfaces of the end effector fingers and include, e.g., pressure sensors and vibration sensors that facilitate the simultaneous detection of both static and dynamic events occurring on the end effector, and optionally include proximity sensors and/or temperature sensors. A readout circuit receives the sensor data from the superpixels and transmits the sensor data onto a shared sensor data bus. An optional multimodal control generator receives and processes the sensor data and generates multimodal control signals that cause the robot system's control circuit to adjust control operations performed by the end effector or other portions of the robot mechanism and when the sensor data indicates non-standard operating conditions.

Multimodal sensor array for robotic systems

A device includes at least one stress-engineered portion and at least one second portion. The stress-engineered portion includes at least one tensile stress layer having a residual tensile stress and at least one compressive stress layer having a residual compressive stress. The tensile stress layer and the compressive stress layer are mechanically coupled such that the at least one tensile stress layer and the at least one compressive stress layer are self-equilibrating. The stress-engineered portion is configured to fracture due to propagating cracks generated in response to energy applied to the stress-engineered portion. Fracture of the stress-engineered portion changes functionality of the device from a first function to a second function, different from the first function.

Functionality change based on stress-engineered components

An electrochemical metal alloy identification device employing electrolytes to measure and identify different potentials of alloys is presented. This includes physical structure, disposables, electrical systems, control circuitry, and algorithms to identify alloys.

Alloy identification device

A passive sensor tag system including a passive electronic sensor tag and an external readout. The passive electronic sensor tag including a sensor element configured to sense data in a local environment and to cause a shift in a fundamental electrical resonance frequency characteristic of a sensor circuit based on the sensed data. The external readout including an external readout circuit that is configured to generate a signal having a frequency and a voltage and to transmit the signal through an output antenna. The transmitted signal coupling the sensor circuit and the external readout circuit. The external readout determining a fundamental electrical resonance frequency characteristic of the sensor circuit based on the impedance of the coupled sensor circuit and external readout circuit. The external readout determining the sensed data based the fundamental electrical resonance frequency characteristic of the sensor circuit.

Passive sensor tag system

An implantable neural probe includes a flexible substrate having a first surface and an opposing second surface. The probe has an elongated three dimensional shape with an exterior surface and an interior surface such that the exterior surface of the probe includes at least a portion of first surface of the flexible substrate and the interior surface of the probe includes at least a portion of the second surface of the flexible substrate. The probe may include an array of one or more neural stimulators disposed on the flexible substrate and configured to stimulate neurons. The probe may alternatively or additionally include an array of one or more neural sensors configured to sense brain neurons.

Implantable neural probe

An implantable subsystem includes multiple implantable neural probes disposed on a flexible substrate. Each neural probe is configured to magnetically stimulate brain neurons. Each probe includes an array of magnetic neural stimulators that magnetically stimulate neurons. Each probe also includes neural probe activation circuitry comprising thin film switches disposed on the flexible substrate. The thin film switches are electrically coupled to row and column activation lines and selectively activate the magnetic neural stimulators in response to neural stimulation activation signals carried on the activation lines.

Implantable neural modulation device

A neural modulation system includes neural encoder in a patient-external device. The neural encoder converts input signals into a neural stimulation pattern and wirelessly transmits the neural stimulation pattern to a patient-internal device. The patient internal device includes a flexible substrate and a two dimensional array of neural probes disposed on the flexible substrate. Each neural probe includes an array of magnetic neural stimulators and/or an array of neural sensors along with probe addressing circuitry that allow for addressing the magnetic neural stimualtors and/or neural sensors. Control circuitry in the implantable device controls activation of the magnetic neural stimulators and/or neural sensors according to the neural stimulation pattern via the probe addressing circuitry.

Neural modulation system

A method of generating a representation of a structure includes providing an ad hoc mesh network having at least two nodes associated with the structure, obtaining time of flight data for each node in the network, and using the time of flight data to generate the representation of the structure. A method of generating a three-dimensional representation of a structure includes providing an ad hoc mesh network having at least three nodes associated with the structure, wherein at least one node is a mobile node that moves around the structure, obtaining time of flight data for each pair of nodes in the network, and using the time of flight data to generate the three-dimensional representation of the structure.

Home network of connected consumer devices

Growing community of inventors

Redwood City, CA, United States of America

Christopher A Paulson