公开(公告)号：US10017218B1

公开(公告)日：2018-07-10

申请号：US15194493

申请日：2016-06-27

Applicant: Google Inc.

Inventor： Benjamin Swilling ,  Eric Whitman ,  Stephen Berard ,  Alfred Anthony Rizzi ,  Alex Yu Khripin ,  Gina Christine Fay

IPC: G06F19/00 ,  B62D57/032 ,  B25J9/00 ,  B25J9/16

CPC classification number: B62D57/032 ,  B25J9/0006 ,  B25J9/162 ,  B25J9/1664 ,  Y10S901/01

Abstract: A legged robot may seek to operate according to a target gait. The legged robot may include leg members and leg joints. Possibly based on the target gait and state of the legged robot, an ordered list of gait controllers may be obtained. The gait controllers in the ordered list may define respective gaits of the legged robot, and may include respective validity checks and output parameters for the respective gaits. The ordered list may begin with a target gait controller that defines the target gait. The ordered list may be traversed in order from the target gait controller until a validity check associated with a particular gait controller passes. The legged robot may be instructed to actuate the leg members and/or leg joints according to output parameters of the particular gait controller.

公开(公告)号：US09925667B1

公开(公告)日：2018-03-27

申请号：US15005687

申请日：2016-01-25

Applicant: Google Inc.

Inventor： Stephen Berard ,  Alex Yu Khripin ,  Benjamin Swilling

IPC: B25J9/16 ,  B62D57/032 ,  B25J13/08 ,  B25J19/00

CPC classification number: B25J9/1641 ,  B25J9/1628 ,  B25J9/1633 ,  B25J13/085 ,  B25J19/0008 ,  B62D57/032 ,  Y10S901/01 ,  Y10S901/27 ,  Y10S901/28 ,  Y10S901/30

Abstract: The disclosure provides systems and methods for mitigating slip of a robot appendage. In one aspect, a method for mitigating slip of a robot appendage includes (i) receiving an input from one or more sensors, (ii) determining, based on the received input, an appendage position of the robot appendage, (iii) determining a filter position for the robot appendage, (iv) determining a distance between the appendage position and the filter position, (v) determining, based on the distance, a force to apply to the robot appendage, (vi) causing one or more actuators to apply the force to the robot appendage, (vii) determining whether the distance is greater than a threshold distance, and (viii) responsive to determining that the distance is greater than the threshold distance, the control system adjusting the filter position to a position, which is the threshold distance from the appendage position, for use in a next iteration.

公开(公告)号：US09395726B1

公开(公告)日：2016-07-19

申请号：US14573092

申请日：2014-12-17

Applicant: Google Inc.

Inventor： Alfred Anthony Rizzi ,  Alex Khripin ,  Michael Scott Rose ,  Gina Fay ,  Stephen Berard

IPC: G06F19/00 ,  G05D1/02 ,  B62D57/02

CPC classification number: B62D57/032 ,  Y10S901/01

Abstract: Examples for implementing bound and gallop gaits are described herein. A computing system may receive an input for a robotic device to perform a gallop gait or a bound gait. Responsive to receiving the input, the computing system may determine a state of the robotic device based on sensor data monitoring the robotic legs. A sagittal controller of the robotic device may determine vertical impulses and target locations for controlling the legs during the gallop gait based on a pitch, a height, and a velocity of the robotic device. One or more continuous controllers may determine adjustments for controlling the legs based on a roll, a yaw, and/or lateral motions of the robotic device that may result from the robotic device traveling at the velocity and direction as specified in the input. Further, to perform the gait, the controllers may provide instructions to control the legs.

Abstract translation: 本文描述了实施绑定和驰骋步态的实例。 计算系统可以接收用于机器人装置的输入以执行驰骋步态或束缚步态。 响应于接收输入，计算系统可以基于监测机器人腿的传感器数据来确定机器人设备的状态。 机器人装置的矢状控制器可以基于机器人装置的俯仰，高度和速度确定在驰骋步态期间控制腿的垂直脉冲和目标位置。 一个或多个连续控制器可以基于机器人装置的滚动，偏航和/或侧向运动来确定用于控制腿部的调节，该机器人装置可能由机器人装置在输入中指定的速度和方向上行进。 此外，为了执行步态，控制器可以提供控制腿的指令。

公开(公告)号：US09987745B1

公开(公告)日：2018-06-05

申请号：US15089355

申请日：2016-04-01

Applicant: Google Inc.

Inventor： Stephen Berard ,  Benjamin Swilling ,  Matthew Malchano

IPC: G06F19/00 ,  G05B19/18 ,  B25J9/16

CPC classification number: B25J9/163 ,  Y10S901/09

Abstract: The present disclosure relates to methods and systems for robust robotic task execution. An example method includes obtaining a task-level goal for a robot associated with one or more sub-goals, where accomplishment of the one or more sub-goals accomplishes the task-level goal. Carrying out an operation in pursuance of a given sub-goal may involve controlling at least one actuator of the robot. The method also includes determining one or more parameters indicative of a state of a system that includes the robot and an environment proximate to the robot. The method further includes selecting a particular sub-goal based on at least one of the one or more parameters. Additionally, the method includes selecting at least one controller based on at least one of the one or more parameters and the selected sub-goal. Further, the method includes causing the robot to operate in accordance with the at least one selected controller.

公开(公告)号：US09969082B1

公开(公告)日：2018-05-15

申请号：US14988390

申请日：2016-01-05

Applicant: Google Inc.

Inventor： Stephen Berard ,  Benjamin Swilling ,  Matthew Malchano

IPC: G05B19/04 ,  B25J9/16 ,  B62D57/032

CPC classification number: B25J9/163 ,  B62D57/032 ,  Y10S901/01 ,  Y10S901/02 ,  Y10S901/27 ,  Y10S901/30

Abstract: The present disclosure relates to methods and systems for improving robotic task selection and execution. An example method includes determining an external environment state based on receiving information indicative of at least one aspect of an environment proximate to a robotic system having at least one actuator. The method also includes optionally determining a goal to be accomplished by a robotic system and determining a plurality of possible tasks each including at least one task involving the at least one actuator that may be carried out by the robotic system in pursuance of the goal. For each possible task group, the method includes determining a respective task group score based on an expected performance capability. The expected performance capability is based, at least in part, on the external environment state. The method includes selecting a task group based on the respective task group scores.

公开(公告)号：US09879700B1

公开(公告)日：2018-01-30

申请号：US14510416

申请日：2014-10-09

Applicant: Google Inc.

Inventor： Zachary John Jackowski ,  Stephen Berard ,  Alex Khripin ,  Alfred Anthony Rizzi

IPC: F15B1/04 ,  F15B21/00 ,  F15B1/033

CPC classification number: F15B1/04 ,  F15B1/033 ,  F15B21/001 ,  F15B2201/51 ,  F15B2201/515 ,  Y10S901/22

Abstract: A control system may receive sensor data indicative of respective fluid levels of two or more hydraulic accumulators configured to operate at respective target fluid levels within a hydraulic system. The control system may determine respective errors of the hydraulic accumulators based on the respective fluid levels and respective target fluid levels of the hydraulic accumulators. The respective errors may correspond to pressure errors, fluid volume errors, or other types of errors of the hydraulic accumulators. Responsive to determining the respective errors, the control system may determine that the error of a given hydraulic accumulator is greater than errors of the other hydraulic accumulators and provide instructions to control a hydraulic valve to supply fluid from a single pump of the hydraulic system to the given hydraulic accumulator.