ROS Answers: Open Source Q&A Forum - RSS feedhttps://answers.ros.org/questions/Open source question and answer forum written in Python and DjangoenROS Answers is licensed under Creative Commons Attribution 3.0Tue, 12 Aug 2014 06:53:39 -0500BFL - bind variableshttps://answers.ros.org/question/189700/bfl-bind-variables/We're trying to use a Bayesian Filter to do some sensor fusion for estimating the joints positions on a joint based robot. For this we're using the **BFL library** as is done in the [robot-pose-ekf](https://github.com/ros-planning/navigation/tree/hydro-devel/robot_pose_ekf) package.
We now have two versions of the same filter (one using `ExtendedKalmanFilter`, the other one a particle filter: `BootstrapFilter`) that converges but haven't yet found a way of binding the BFL state representation variables. In our case, we'd like to make sure that each variable of the state stays within the joint limits.
Feel free to ask for more details as I'm not exactly sure what is most relevant.Mon, 11 Aug 2014 08:41:17 -0500https://answers.ros.org/question/189700/bfl-bind-variables/Answer by Ugo for <p>We're trying to use a Bayesian Filter to do some sensor fusion for estimating the joints positions on a joint based robot. For this we're using the <strong>BFL library</strong> as is done in the <a href="https://github.com/ros-planning/navigation/tree/hydro-devel/robot_pose_ekf">robot-pose-ekf</a> package.</p>
<p>We now have two versions of the same filter (one using <code>ExtendedKalmanFilter</code>, the other one a particle filter: <code>BootstrapFilter</code>) that converges but haven't yet found a way of binding the BFL state representation variables. In our case, we'd like to make sure that each variable of the state stays within the joint limits.</p>
<p>Feel free to ask for more details as I'm not exactly sure what is most relevant.</p>
https://answers.ros.org/question/189700/bfl-bind-variables/?answer=189828#post-id-189828*from Enrico on BFL mailing list*
This is a constrained optimization problem. I am afraid there is no "clean" way of doing this.
If the state variables are defined by Gaussian pdfs, than by definition
those span an infinite support.
You could try to make variables outside of the joint limits "highly
unlikely" by filtering your measurements, and rejecting those outside a
validation area, or carefully defining Process noise and Measurement Noise
Covariance Matrices, but if you really want to use constraints, that
you're actually solving an Estimation + Constrained Optimization problem,
and you'll need different tools for that.
Tue, 12 Aug 2014 06:53:39 -0500https://answers.ros.org/question/189700/bfl-bind-variables/?answer=189828#post-id-189828