Online speed override of a trajectory

Patent metadata

Field	Value
Publication number	US-12498737-B2
Application number	US-202318534461-A
Country	US
Kind code	B2
Filing date	Dec 8, 2023
Priority date	Dec 29, 2022
Publication date	Dec 16, 2025
Grant date	Dec 16, 2025

Abstract

Methods, systems, and apparatus, including computer programs encoded on computer storage media, for overriding an original motion of a robot along a trajectory. The method includes initiating, by a real-time robotics control system, execution of an input trajectory for a robot at a default speed, wherein the input trajectory is a time-parameterized trajectory and specifies a path in an operating environment; before completing execution of the input trajectory, receiving a user input specifying a value of an online speed override factor; in response, generating a phase-parameterized version of the input trajectory using a phase variable; computing, on each real-time control cycle, a target velocity and a target acceleration of the phase-parameterized version of the input trajectory based on the online speed override factor; and causing the robot to transition to the target velocity and the target acceleration while traversing the path in the operating environment.

First claim

What is claimed is:

1 . A method comprising:
initiating, by a real-time robotics control system, execution of an input trajectory for a robot at a default speed, wherein the input trajectory is a time-parameterized trajectory and specifies a path in an operating environment; before completing execution of the input trajectory, receiving a user input specifying a value of an online speed override factor; in response, generating a phase-parameterized version of the input trajectory using a phase variable; computing, on each real-time control cycle, a target velocity and a target acceleration of the phase-parameterized version of the input trajectory based on the online speed override factor; and causing the robot to transition to the target velocity and the target acceleration while traversing the path in the operating environment.

2 . The method of claim 1 , wherein computing the target velocity and the target acceleration comprises:
for a position in the input trajectory in real time, computing first and second derivatives of the position in the phase-parameterized version of the input trajectory with respect to the real time.

3 . The method of claim 1 , wherein generating the phase-parameterized version of the input trajectory comprises:
generating a sequence of piecewise continuous splines for the input trajectory, each spline being a polynomial of the phase variable.

4 . The method of claim 3 , wherein the sequence of piecewise continuous splines are functions of a trajectory time variable, wherein the trajectory time variable is a function of the phase variable, and is equivalent to a corresponding real time when the value of the online speed override factor is set to one.

5 . The method of claim 1 , wherein the online speed override factor is a function of a first-order time derivative of the phase variable.

6 . The method of claim 1 , further comprising:
obtaining data representing a lower bound velocity and an upper bound velocity; computing a first-order derivative of the phase-parameterized version of the input trajectory with respect to real time at a corresponding position; and determining an upper bound value and a lower bound value for the online speed override factor by ensuring that the first-order derivative of the position satisfies a range defined by the lower bound velocity and the upper bound velocity.

7 . The method of claim 1 , further comprising:
obtaining data representing a lower bound acceleration and an upper bound acceleration; computing a second-order derivative of the position in the phase-parameterized version of the input trajectory with respect to real time; and determining an upper bound value and a lower bound value for a first-order time derivative of the online speed override factor by ensuring that the second-order derivative of the position satisfies a range defined by the lower bound acceleration and the upper bound acceleration.

8 . The method of claim 1 , further comprising:
determining whether the value of the online speed override factor satisfies a predetermined criterion; and in response to determining that the value of the online speed override factor does not satisfy the predetermined criterion, generating a notification to be displayed on a user interface for another value of the online speed override factor.

9 . The method of claim 1 , further comprising:
iteratively increasing a current value of the online speed override factor to approach the user-specified value of the online speed override factor without exceeding a predetermined limit for the value of the online speed override factor.

10 . The method of claim 9 , wherein iteratively increasing the current value of the online speed override factor to approach the user-specified value of the online speed override factor comprises:
for each iteration step, receiving a current value of the online speed override factor and a current value of the first-order time derivative of the online speed override factor for the iteration step; and determining, for a next iteration step, an updated value of the online speed override factor and an updated value of the first-order time derivative of the online speed override factor based on the current value of the online speed override factor and the current value of the first-order time derivative of the online speed override factor, wherein the updated values approach the user-specified value while satisfying predetermined limits.

11 . The method of claim 1 , wherein the value of the online speed override factor specified by the user input is applied to a single segment of the input trajectory for generating the target velocity and the target acceleration.

12 . The method of claim 1 , wherein the value of the online speed override factor specified by the user input is applied to a first segment of the input trajectory, and the user input further comprises a second value of the online speed override factor applied to a second segment of the input trajectory.

13 . A system comprising one or more computers and one or more storage devices storing instructions that when executed by one or more computers cause the one or more computers to perform respective operations, the operations comprising:
initiating, by a real-time robotics control system, execution of an input trajectory for a robot at a default speed, wherein the input trajectory is a time-parameterized trajectory and specifies a path in an operating environment; before completing execution of the input trajectory, receiving a user input specifying a value of an online speed override factor; in response, generating a phase-parameterized version of the input trajectory using a phase variable; computing, on each real-time control cycle, a target velocity and a target acceleration of the phase-parameterized version of the input trajectory based on the online speed override factor; and causing the robot to transition to the target velocity and the target acceleration while traversing the path in the operating environment.

14 . The system of claim 13 , wherein computing the target velocity and the target acceleration comprises:
for a position in the input trajectory in real time, computing first and second derivatives of the position in the phase-parameterized version of the input trajectory with respect to the real time.

15 . The system of claim 13 , wherein generating the phase-parameterized version of the input trajectory comprises:
generating a sequence of piecewise continuous splines for the input trajectory, each spline being a polynomial of the phase variable.

16 . The system of claim 15 , wherein the sequence of piecewise continuous splines are functions of a trajectory time variable, wherein the trajectory time variable is a function of the phase variable, and is equivalent to a corresponding real time when the value of the online speed override factor is set to one.

17 . One or more non-transitory computer-readable storage media storing instructions that when executed by one or more computers cause the one or more computers to perform respective operations, the respective operations comprising:
initiating, by a real-time robotics control system, execution of an input trajectory for a robot at a default speed, wherein the input trajectory is a time-parameterized trajectory and specifies a path in an operating environment; before completing execution of the input trajectory, receiving a user input specifying a value of an online speed override factor; in response, generating a phase-parameterized version of the inpu

Assignees

• Intrinsic Innovation Llc

Inventors

• Giftthaler Markus
• Gaschler Andre
• Sutanto Giovanni

Classifications

• G05D1/646

  Following a predefined trajectory, e.g. a line marked on the floor or a flight path · CPC title

• G05D2107/70

  Industrial sites, e.g. warehouses or factories · CPC title

• G05D2109/10

  Land vehicles · CPC title

• B25J9/1664

  characterised by motion, path, trajectory planning · CPC title

• G05D1/229

  Command input data, e.g. waypoints · CPC title