Patents

System and method for user intent recognition

EP3576707A1

The disclosure includes a method of operating an exoskeleton system. The method includes determining a first state estimate for a current classification program being implemented by the exoskeleton system, determining a second state estimate for a reference classification program; determining that a difference between the first and second state estimate is greater than a classification program replacement threshold; generating an updated classification program; and replacing the current classification program with the updated classification program based at least in part on the determining that the difference between the first and second state estimates is greater than the classification program replacement threshold.


Exoskeleton fit evaluation system and method

CA3072504A1

A method of performing a fit test on an actuator unit coupled to a user. The method includes determining a first configuration of the actuator unit while the actuator unit is in an un-actuating state and while the user is in a fit test position; actuating the actuator unit; determining a second configuration of the actuator unit generated in response to the actuating the leg actuator unit; determining a change in configuration of the actuator unit based at least in part on the difference between the first and second configuration; and determining that the change in configuration corresponds to an improper fit of the actuator unit to the user.


Semi-supervised intent recognition system and method

US20190060156A1

A computer implemented method of semi-supervised intent recognition for an exoskeleton system. In one aspect, the method includes, in response to a state transition intention input, changing the exoskeleton system from operating in a first mode with sensitivity to detecting state transitions at a first sensitivity level to operating in a second mode with sensitivity to detecting state transitions at a second sensitivity level that is more sensitive than the first sensitivity level; identifying a state transition while operating in the second mode and using the second sensitivity level; and facilitating the identified state transition by actuating the exoskeleton system.


Fluidic robotic actuator system and method

US10562180B2

A fluidic robotic actuator configured to assume at least a neutral position, the fluidic robotic actuator includes a first and second plate defining respective planar portions that are disposed in parallel planes in the neutral position. The fluidic robotic actuator also includes a plurality of elongated bellows extending between the first and second plates, the bellows each having a central main axis that is parallel to the central main axis of the other bellows in the neutral position, the main axis of the bellows being perpendicular to the parallel planes of the first and second plates in the neutral position, the bellows being coupled to the first and second plates at respective first and second ends of the bellows.


Methods and apparatuses for selectively controlling motor power boards

US9231503B2

Methods and systems for building arbitrary motor controllers are described. An example motor controller may include multiple motor power boards connected in a stacked configuration and coupled in parallel. Each motor power board may include one or more power transistors and one or more gate drivers having an input terminal coupled to a control signal connector and an output terminal coupled to a gate terminal of the one or more power transistors. The example motor controller may also include a power bus connector coupled, in parallel, to a respective output terminal of each of the multiple motor power boards. Further, the example motor controller may include a control system coupled to the control signal connector and configured to selectively enable a set that includes one or more of the multiple motor power boards based on an output power requirement.


Robotic devices with ambient indications of joint status

US9375841B1

In examples, robotic devices with ambient indications of joint status are provided. An example robotic device includes one or more actuators coupled through one or more joints to form a robotic manipulator, and an indicator co-located in proximity to the one or more joints to provide visual feedback on the robotic manipulator at the one or more joints and about the one or more joints. The visual feedback may include information indicative of an operating status of the one or more joints including an indication of an amount of torque that the one or more joints is experiencing. The robotic device also includes a controller programmable to control the indicator co-located proximal to the one or more joints to provide the visual feedback indicative of the operating status of the one or more joints.


Cogging torque measurement for a robot actuator

US9205556B1

Systems and methods for measuring cogging torque. An example method includes causing an electric motor to rotate in a positive direction, and for given multiple encoder positions of an encoder, determining a first respective motor winding current applied to the electric motor at the given encoder position. Additionally, the method includes causing the electric motor to rotate in a negative direction, and for the given multiple encoder positions, determining a second respective motor winding current applied to the electric motor at the given encoder position. Further, the method includes, for the given multiple encoder positions, determining a respective cogging torque based on a difference between the first and second respective winding currents. And the method includes storing a cogging torque profile for the electric motor in a database based on the determined respective cogging torque for the given multiple encoder positions.


System and method for failure detection of a robot actuator

US9205560B1

Systems and methods for detecting actuator component or sensor failure using non-equivalent sensors are described. An example method includes actuating a robot actuator, and determining a first result and second result of the actuation using a first sensor and second sensor respectively. Additionally, the method includes determining a first estimate of an internal state of the robot actuator using the first result, and determining a second estimate of the internal state using the second result and a normalization function that normalizes the second result for comparison with the first estimate. Further, the method includes determining whether a difference between the first estimate of the internal state and the second estimate of the internal state satisfies an error threshold. And the method includes providing an output indicative of a potential fault of the robot actuator in response to determining that the difference does not satisfy the error threshold.

Using Format