GithubHelp home page GithubHelp logo

wpi-aim / dvrk_dynamics_identification Goto Github PK

View Code? Open in Web Editor NEW
32.0 10.0 15.0 147.66 MB

Dynamic model identification of the DVRK

Jupyter Notebook 99.40% Python 0.58% MATLAB 0.01% M 0.01%
surgical-robots dynamic-models parameter-identification dvrk

dvrk_dynamics_identification's People

Contributors

adnanmunawar avatar nsujumnong avatar radiang avatar wangyanhit avatar

Stargazers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

Watchers

 avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar  avatar

dvrk_dynamics_identification's Issues

Class Fourier may be err when caculate dq

when I run this script ,we got the result of excited_trajectory about q,dq,ddq.
but the curve of dq didn't correspd to the curve of q's diff,
I have tested many time , the result of the curve dq is wrong.
The definition of Class Fourier in fourier.py is wrong.

so once the dq is wrong ,the cond(H)will wrong ,so the x_result of ols is wrong.
I hope you can pay attention to the issue

Joint Constraints Not Respected during Trajectory Optimization

using the psm_fontanelli notebook, I tried to generate an optimal trajectory while setting the joint constraints for joint 1 with a "psm_simplified" model:

from numpy import deg2rad

optimal_trajectory_folder = 'data/optimal_trajectory/'
trajectory_folder = 'data/' + model_name +'/optimal_trajectory/'

base_freq = 0.18
fourier_order = 6

joint_constraints = []
cartesian_constraints = []

if model_name == 'psm_simplified':
    q_dvrk7 = 1.2177*q7 - 1.2177*q6
#     q_mod6 = (4871*q6)/4000 - (4153*q5)/5000
#     q_mod7 = - (4153*q5)/5000 + (4871*q7)/4000
    
    q_dvrk5 = 1.0186 * q5
    q_mod6 = -0.8306 * q5 + 1.2178 * q6
    q_mod7 = -0.8306 * q5 + 1.2178 * q7
    
    joint_constraints = [(q1, 0, 1.45, -1.7, 1.7), #old value is -1.45 to 1.45
                         (q2, -0.75, 0.8, -1.7, 1.7),
                         (q3,0.07,0.235,-0.35,0.35),
                         (q4,-1.5,1.5,-2,2),
                         (q_dvrk5,-1.4,1.4,-2,2), 
                         (q_dvrk7, 0.15, 3,-3,3),
                         (q_mod7, -1.5, 1.5,-2,2),
                          (q_mod6, -1.5, 1.5,-2,2)]
else:
    raise Exception("No robot name matches " + model_name)
    
traj_optimizer = TrajOptimizer(robot_model, fourier_order, base_freq,
                               joint_constraints=joint_constraints,
                               cartesian_constraints = cartesian_constraints)
                                                                                                 
                                                                                                                     
traj_optimizer.optimize()

however after running the optimization I find that the max and min joint angle 4.6rad. I believe such a large range causes my dvrk to trip as the joint limits are exceeded during the recording of the training data. Hope someone can verify my findings.

Recommend Projects

  • React photo React

    A declarative, efficient, and flexible JavaScript library for building user interfaces.

  • Vue.js photo Vue.js

    ๐Ÿ–– Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.

  • Typescript photo Typescript

    TypeScript is a superset of JavaScript that compiles to clean JavaScript output.

  • TensorFlow photo TensorFlow

    An Open Source Machine Learning Framework for Everyone

  • Django photo Django

    The Web framework for perfectionists with deadlines.

  • D3 photo D3

    Bring data to life with SVG, Canvas and HTML. ๐Ÿ“Š๐Ÿ“ˆ๐ŸŽ‰

Recommend Topics

  • javascript

    JavaScript (JS) is a lightweight interpreted programming language with first-class functions.

  • web

    Some thing interesting about web. New door for the world.

  • server

    A server is a program made to process requests and deliver data to clients.

  • Machine learning

    Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.

  • Game

    Some thing interesting about game, make everyone happy.

Recommend Org

  • Facebook photo Facebook

    We are working to build community through open source technology. NB: members must have two-factor auth.

  • Microsoft photo Microsoft

    Open source projects and samples from Microsoft.

  • Google photo Google

    Google โค๏ธ Open Source for everyone.

  • D3 photo D3

    Data-Driven Documents codes.