3

It's true that using RL in robotics involves many challenges, including the usually high dimensionality of problem spaces, the cost and limitations of real-world sessions, the impossibility or perfectly modelling the robot-environment system, and the complexity of reward functions that accurately reflect desired behaviors. That said, a number of approaches ...


2

These two concepts are complementary and you use them together, the motion profile providing the input to your control scheme. At each time-step the motion profile gives you the reference values for the control loop scheme (and also some feed forward values if needed). This goes both for the acceleration and the deceleration phases. in both cases, the motion ...


1

Your intuition is partially correct in the sense that you ought to go with position control implemented via velocity commands resorting to a kinematic (not dynamic) model of the manipulator. This can be explained by inspecting one of the easiest policy used for inverse kinematics, $$ \dot{\mathbf{q}} = \mathbf{J}^{-1} \cdot \left( \mathbf{x}_d - \mathbf{x}(\...


1

Extending the previous answer which describes how to compute a minimum-jerk trajectory given a consistent distance coordinate system. A simple way to do this is to treat the first coordinate as your origin then convert each other GPS point to meter distances from your first coordinate using one of the latitude and longitude equations here


1

As reported for example in https://robotics.stackexchange.com/a/21571/6941, a minimum-jerk trajectory in one dimension is coded with respect to time $t$ as: $$ x(t) = x_i + (x_f-x_i) \cdot \left( 10\left(\frac{t}{t_f}\right)^3 -15\left(\frac{t}{t_f}\right)^4 +6\left(\frac{t}{t_f}\right)^5\right), $$ where $t_f$ is the final time ($2\, \text{s}$ in your case),...


1

Based on your comment: if I am able to get 0 to 2pi, would be enough as well. The following code will do it: modifiedHeading = SensorOutput(); if(modifiedHeading < 0) { modifiedHeading += 360f; } But, as I've mentioned previously, you still have the jump discontinuity, but you've moved it from the 359/1 degree range from the 179/-179 degree range.


1

You can take a look at PLCOpen Motion. This can be thought of a motion control SDK for programming languages used in the automation world. This is general purpose and well established. Furthermore, you can take a close look at all Robot Controller programming languages (like Kuka KRL, ABB Rapid, Fanuc Karel, Staubli Val3, etc.) These are programming ...


1

with the key words chuck gave me I found an article of David Anisi about "Optimal motion control of a ground vehicle". There he describes an algorithm using the Hamilton to solve these kind of optimal control problems. Chuck was right that I had to add parameters for linear as well as angular velocity. Therefore my constraints are $\dot{p_1}=v cos(\phi)$ $...


1

Let me start by saying I haven't done trajectory optimization or anything, but I've done quite a bit of differential equations for controls. I think your equations might not be solvable because of the way you've defined your constraint conditions: $$ \dot{p}_1=\cos{\phi} \\ \dot{p}_2=\sin{\phi} \\ $$ If you want your heading/orientation to remain steady, ...


Only top voted, non community-wiki answers of a minimum length are eligible