Skip to main content
11 votes
Accepted

AprilTag vs Aruco markers

Aruco (as implemented in OpenCV): Pros Easy to set up (with readily available aruco marker generator, opencv & ros implementation, etc.) fewer false detection (with default parameters) Cons ...
Rufus's user avatar
  • 486
6 votes
Accepted

State of a Robot

To extends the answer from the_parzival a bit: There are different kind of robots so that 'robot state' can have different meanings. If you have a drone or Roomba-robot, the most important state is ...
FooTheBar's user avatar
  • 1,375
6 votes

What's the difference between Pose Measurement and Position Measurement?

what you are looking for is written in the paper. Position refers only to x,y,z translational measurements while pose means position and orientation.
jdios's user avatar
  • 497
6 votes

Which is the best visual fiducial marker (2D barcode)?

AprilTag is the state-of-the-art solution for pose estimation. The library itself already has pre-built functions to compute the marker position, given its size. The pose is estimated by homography ...
valleymanbs's user avatar
4 votes

What's the difference between the term "pose estimation" and "visual odometry"?

It is also often the case that the author lacks knowledge, makes mistakes, or is adding unnecessary statements to their work. Just because it is published does not make it true. In this case though, ...
hauptmech's user avatar
  • 4,445
4 votes

What's the difference between the term "pose estimation" and "visual odometry"?

Pose estimation means determining position and orientation. Odometry is using a (any) sensor to determine how much distance has been traversed, so visual odometry is just clarification that the ...
Chuck's user avatar
  • 15.9k
4 votes
Accepted

Integrating GPS into Graph SLAM (how orientation fixed?)

You can use a very low information matrix value at the orientation elements of your state, given that the information matrix is the inverse of the covariance matrix. The covariance matrix ...
Ricardo Achilles's user avatar
4 votes
Accepted

Calculate transform from different poses

I am just going to explain from the basics. So feel free to skip through the first part and scroll to the bottom if you want the answer. Basics: The 3 parameters of your pose are $x,y,\theta$. These ...
edwinem's user avatar
  • 1,871
3 votes
Accepted

Position vs Image based visual servoing?

The problem in both cases is to move the robot tool to some pose relative to an object. Let's assume the camera is attached to the end of a robot arm (eye in hand case) so we will consider this a ...
Peter Corke's user avatar
  • 1,702
3 votes

smoothing the robot poses inbetween two known poses

To get a smooth trajectory you should not have jumps in acceleration and because you are talking about pose both rotational and translational accelerations should be smooth. You can achieve this with ...
nionios's user avatar
  • 311
3 votes

smoothing the robot poses inbetween two known poses

You could try to use a bezier curve (https://en.wikipedia.org/wiki/B%C3%A9zier_curve) to interpolate with a curve and via points between A and B'. Also, is this a mobile robot or a robot arm? Do you ...
jdios's user avatar
  • 497
3 votes
Accepted

Number of diagonal elements in the pose covariance matrix

The quaternion part [q_x, q_y, q_z, q_w] has four numbers but is a representation of 3D orientation, which has 3 degrees of freedom. Another common representation ...
Parker Lusk's user avatar
3 votes

Get a rotation to align a vector, n with another vector, a and be able to rotate around a

Assuming you are working in 3-dimensions, this is exactly what the cross-product does. To find the vector of rotation that rotates $\mathbf{n} \in \mathbb{R}^{3}$ into $\mathbf{a} \in \mathbb{R}^{3}$, ...
domo_arigato's user avatar
2 votes

Full 3D Pose (Scale, Rotation and Translation) Estimation using Gyro and Acceleromter sensors fusion

The packages you've found don't estimate scale or 3d pose because that's not really feasible using just an imu. The only way to get 3d pose from an imu is to integrate acceleration (adjusting for ...
ryan0270's user avatar
  • 2,814
2 votes

How many AR markers should I use to get the object pose?

Without knowing exactly what type of AR marker you are interested in, I'll talk about two types that I am familiar with: ArUco and April Tags. Both are AR markers that have open source libraries with ...
Parker Lusk's user avatar
2 votes
Accepted

How to properly initialize every new pose in a Visual SLAM algorithm (namely DSO)?

DSO initializes the scene and camera poses with a specific scale factor such that the average inverse depth of the pointHessians is one. After the initialization the first two frameHessians are led ...
felipe7's user avatar
  • 36
2 votes

How to detect writing on a chalkboard?

Since you are going to have a mechanism that can draw within a square why not put a light sensor on it and use the same mechanism scan for the opponent's move? At the start of the game, scan all the ...
markshancock's user avatar
2 votes

Resources for object detection with 2D Laser Scanner (planar only)

I think you can divide your problem into two subproblems: 1) Partition your 2D scan into segments/clusters which represent single objects. A basic algorithm could be: Start at first laser reading ...
Eric Dörheit's user avatar
2 votes

How can I calibrate 3 cameras without knowing global pose of the object & camera locations? How can I find the pose of each camera wrt the first one?

The process you need to go through is actually similar to the camera calibration procedure in OpenCV or other software. The chessboard is replaced by your robot, and you can skip the intrinsic ...
edwinem's user avatar
  • 1,871
2 votes
Accepted

Incorporating motion model in Graph Slam and Bundle adjustment

Would say you can generally do 2 different ways of incorporating the information. Compute the odometry. Simply compute how far your robot is supposed to move in between frames. Either using your ...
edwinem's user avatar
  • 1,871
2 votes

Manually generate antipodal grasps for grasping

You can use GraspIt! from the moveit ROS metapackage. I would recommend, however, deriving your own vector approach for grasping objects. You have to give your grasping software your gripper ...
robotsfoundme's user avatar
2 votes
Accepted

How to prove expression for relative pose in one frame given relative pose in another frame

Consider the graph below: Starting from the point $2k+1$, we can count the transformations anticlockwise, ending up again at the same point; hence, the aggregate transformation shall be the identity ...
Ugo Pattacini's user avatar
2 votes

Conversion of roll, pitch and yaw from ENU to NED

ENU = East, North, Up NED = North, East, Down So, if you have x_ENU, y_ENU, and z_ENU, then: ...
Chuck's user avatar
  • 15.9k
2 votes

How to put ArUco markers in Gazebo Classic

This forum post and this blog post and corresponding example model are pretty helpful. This is just a simple model defining a link which has a front visual and a back visual. The front visual loads ...
JRTG's user avatar
  • 2,074
1 vote

How do you handle angle discontinuities in estimation problems?

As mentioned by @long-smith the standard solution is to use quaternions. However if you specifically are asking how to deal with errors using angles that are modulo $2\pi$ you are going to want to add ...
Tully's user avatar
  • 25.1k
1 vote

Reset coordinate system of robot while maintaining relationship to the previous

Instead of just considering it a reset, you should consider it a coordinate system transformation: You set the position to zero, that means that you create a transformation matrix which brings your ...
50k4's user avatar
  • 6,682
1 vote
Accepted

Dual constraint non-linear optimization for SLAM

The two constraints have different units, first give an error in meter, second give an error in pixel. Is it a problem for the optimization to minimize two constraints with different scale units ? ...
edwinem's user avatar
  • 1,871
1 vote

State of a Robot

The answer by parzival is only a partial answer. Especially with robots with more than 3 axes, the matrix cannot be solved for a deterministic state, a famous example of this is Dirac's belt trick, ...
tuskiomi's user avatar
  • 195
1 vote

State of a Robot

The state of the Robot refers to the properties of the robot that you want to estimate. If you take a 2D robot as an example, then you might be interested in its 2d position which refers to $$ X(t)...
the_parzival's user avatar
1 vote

For pose estimation, what is the typical range of the rotation values that are estimated? Is it from -180 to 180 degrees?

The range between -1 or +1 is a normalized range like you said. The question is the following: Were those values divided by 180 (degrees) or 2*pi (radians)? You should check any existant documentation ...
Bruno Pinto's user avatar

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