wpi-aim / dvrk_dynamics_identification Goto Github PK
View Code? Open in Web Editor NEWDynamic model identification of the DVRK
Dynamic model identification of the DVRK
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
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.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. ๐๐๐
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.