US4990838A
Expired / Lapsed
US
⏱️ 0.0 years remaining
Movement trajectory generating method of a dynamical system
Assignee: Sony Corp
•
Filing: 1990-01-03
•
Granted: 1991-02-05
•
Expires: 2010-01-03
Abstract
Abstract A movement trajectory generating system of a dynamical system uses neural network units (1, 2, 3) including cascade connection of a first layer (11, 21, 31), a second layer (12, 22, 32), a third layer (13, 23, 33) and a fourth layer (14, 24, 34), to learn a vector field of differential equations indicating forward dynamics of a controlled object (4). Conditions concerning trajectories of a final point and a via-point of movement of the controlled object and locations of obstacles are given from a motor center (5). While smoothness of movement is ensured by couplings of electric synapses using errors with respect to those conditions as total energy, least dissipation of energy is attained, whereby trajectory formation and control input for realizing the trajectory are obtained simultaneously.
Inventors
- 👤 Mitsuo Kawato
- 👤 Yoshiharu Maeda
- 👤 Yoji Uno
- 👤 Ryoji Suzuki
Bibliographic Details
Application Number
—
Jurisdiction
US
Data Source
google_patents
Last Synchronized
2026-10-29 07:12
CPC Classifications
G; G05; G05B; G05B19/00; G05B19/02; G05B19/18; G05B19/41; B; B25; B25J; B25J9/00; B25J9/16; B25J9/1602; B25J9/161; G06; G06N; G06N3/00; G06N3/02; G06N3/04; G06N3/045; G06N3/0499; G06N3/08; G06N3/09; G05B2219/00; G05B2219/30; G05B2219/33; G05B2219/33027; G05B2219/42; G05B2219/42155; G05B2219/49; G05B2219/49157
Claims Analysis
Total Claims: 16
Claim 1
Independent Claim
111 words
A method for generating a time trajectory of a controlled object comprising the steps of: generating said time trajectory of said controlled object in a network by using conditions for estimating the movement trajectory comprising at least one of a movement time, a start point, an end point and a via-point of the trajectory, and obstacles to the movement; and using a criterion for ensuring smoothness of the movement trajectory by minimizing evaluation functions in integration for a movement time obtained by square of a function of movement comprising at least one of the third derivative of position with respect to time, time change of torque, and time change of force.
Claim 2
Independent Claim
111 words
A method for generating a time trajectory of a controlled object comprising the steps of: generating said time trajectory of said controlled object in a network by using conditions for estimating the movement trajectory comprising at least one of a movement time, a start point, an end point and a via-point of the trajectory, and obstacles to the movement; and using a criterion for ensuring smoothness of the movement trajectory by minimizing evaluation functions in integration for a movement time obtained by square of a function of movement comprising at least one of the third derivative of position with respect to time, time change of torque, and time change of force.
Claim 3
Independent Claim
174 words
A method for generating a time trajectory of a controlled object comprising the steps of: generating said time trajectory of said controlled object in a network by using conditions for estimating the movement trajectory comprising at least one of a movement time, a start point, an end point and a via-point of the trajectory, and obstacles to the movement; using a criterion for ensuring smoothness of the movement trajectory by minimizing evaluation functions in integration for a movement time obtained by square of a function of movement comprising at least one of the third derivative of position with respect to time, time change of torque, and time change of force; obtaining in the network a number of internal models by multiplying by a unit of time a vector field of nonlinear differential equations describing dynamic characteristics of said controlled object; and generating the time trajectory of said controlled object by using bypasses corresponding to a flow of differential equations and discrete diffusion couplings for satisfying the evaluation criterion for ensuring the smoothness of movement.
Claim 4
Independent Claim
174 words
A method for generating a time trajectory of a controlled object comprising the steps of: generating said time trajectory of said controlled object in a network by using conditions for estimating the movement trajectory comprising at least one of a movement time, a start point, an end point and a via-point of the trajectory, and obstacles to the movement; using a criterion for ensuring smoothness of the movement trajectory by minimizing evaluation functions in integration for a movement time obtained by square of a function of movement comprising at least one of the third derivative of position with respect to time, time change of torque, and time change of force; obtaining in the network a number of internal models by multiplying by a unit of time a vector field of nonlinear differential equations describing dynamic characteristics of said controlled object; and generating the time trajectory of said controlled object by using bypasses corresponding to a flow of differential equations and discrete diffusion couplings for satisfying the evaluation criterion for ensuring the smoothness of movement.
Claim 5
Dependent Claim
81 words
A trajectory generating method in accordance with claim 2, further comprising: using a multilayer neural network for learning internal models obtained by multiplying, by the unit of time, the vector field of said nonlinear differential equations, wherein a large number of said multilayer neural networks are cascade-connected, and generating said time trajectory of said controlled object by using bypasses corresponding to a flow of the differential equations and electric synapses for satisfying the evaluation criterion for ensuring the smoothness of movement.
Claim 6
Dependent Claim
104 words
A movement trajectory generating method of a dynamical system, for generating a time trajectory of a controlled object, a number of cascade-connected multilayer neural networks being included, said method comprising learning forward dynamics and kinematics of said controlled object by using said multilayer neural networks, and providing conditions concerning trajectory of a final point and a via-point of movement of said controlled object, and locations of obstacles, generating the trajectory and obtaining a control input for realizing the trajectory simultaneously by least dissipation of energy while ensuring smoothness of movement by electric synaptic couplings using errors with respect to said conditions as total energy.
Claim 7
Dependent Claim
104 words
A movement trajectory generating method of a dynamical system, for generating a time trajectory of a controlled object, a number of cascade-connected multilayer neural networks being included, said method comprising learning forward dynamics and kinematics of said controlled object by using said multilayer neural networks, and providing conditions concerning trajectory of a final point and a via-point of movement of said controlled object, and locations of obstacles, generating the trajectory and obtaining a control input for realizing the trajectory simultaneously by least dissipation of energy while ensuring smoothness of movement by electric synaptic couplings using errors with respect to said conditions as total energy.
Claim 8
Independent Claim
75 words
A method for generating a time trajectory for a controlled object, using a control network, the method comprising the steps of: inputting condition data; estimating a movement trajectory of the controlled object based on the condition data; generating a function of the movement of the controlled object; squaring the function of movement; integrating the squared function of movement to derive an evaluation function; and minimizing the derived evaluation function to smooth the estimated movement trajectory.
Claim 9
Independent Claim
75 words
A method for generating a time trajectory for a controlled object, using a control network, the method comprising the steps of: inputting condition data; estimating a movement trajectory of the controlled object based on the condition data; generating a function of the movement of the controlled object; squaring the function of movement; integrating the squared function of movement to derive an evaluation function; and minimizing the derived evaluation function to smooth the estimated movement trajectory.
Claim 10
Dependent Claim
33 words
A method for generating a time trajectory as in claim 5 wherein the input condition data relates to movement time, start point, end point, a via-point of the trajectory or obstacles to movement.
Claim 11
Dependent Claim
50 words
A method for generating a time trajectory as in claim 5 further comprising the steps of: detecting the position of the controlled object as a function of time; generating a third derivative of the position signal; and using the third derivative of the position signal as said function of movement.
Claim 12
Dependent Claim
38 words
A method for generating a time trajectory as in claim 5 further comprising the steps of: detecting change in the torque per unit time; and using the change in torque per unit time as said function of movement.
Claim 13
Dependent Claim
31 words
A method for generating a time trajectory as in claim 5 further comprising the steps of: detecting change in force; and using the change in force as the function of movement.
Claim 14
Dependent Claim
29 words
A method for generating a time trajectory as in claim 5 further comprising the step of using a neural network as the control network to generate the time trajectory.
Claim 15
Dependent Claim
35 words
A method for generating a time trajectory as in claim 5 performed in a cascade connected multilayer neural network wherein the estimating, generating and smoothing steps are performed in a cascade connected multilayered neural network.
Claim 16
Dependent Claim
28 words
A method for generating a time trajectory as in claim 5 further comprising the step of using the smoothed estimated trajectory to control movement of the controlled object.
References Cited (Backward Citations)
US3950733A
Cited
US4852018A
Cited
US4796199A
Cited
US4860215A
Cited
US4884216A
Cited
US4897811A
Cited
USPTO Annuity & Maintenance Windows
| Annuity Stage | Window Opens | Payment Deadline | Surcharge Period Until | Estimated Fee | Status |
|---|---|---|---|---|---|
| 3.5 Years (Year 4) | 1994-02-04 | 1994-08-06 | 1995-02-05 | $2000.00 | Window Closed / Lapsed |
| 7.5 Years (Year 8) | 1998-02-04 | 1998-08-06 | 1999-02-05 | $3760.00 | Window Closed / Lapsed |
| 11.5 Years (Year 12) | 2002-02-04 | 2002-08-06 | 2003-02-05 | $7700.00 | Window Closed / Lapsed |