Questions tagged [slam]

SLAM (Simultaneous Localization And Mapping) refers to a robot building a map of its environment through it's sensor data (mapping) and keeping track of its own position in that map (localization) at the same time.

Filter by
Sorted by
Tagged with
2
votes
2answers
207 views

Scale estimation in datasets for monocular odometry

Suppose I've developed a monocular SLAM or odometry algorithm. Then I want to test it on some dataset, for example KITTI, TUM etc. How should I deal with the absolute scale in this way? Thanks.
1
vote
1answer
177 views

Hector_navigaton on ROS Melodic error

I'm a newbie on robotics, and currently, I'm working on a project to make an autonomous robot that can mapping the surrounding environment and decide the shortest route towards the goal while avoiding ...
0
votes
1answer
48 views

How to use SLAM generated map to navigate my robot to the destination?

I am trying to understand various SLAM algorithms. In my case, I need my robot to start from point A and reach point B with maximum accuracy as well as precision for all the cases. Note that, as the ...
0
votes
0answers
21 views

Setting An Initial Pose Rotation In ORB SLAM2

I am running ORB SLAM 2 on a drone with a downward facing, RGBD camera. I'm using Gazebo to simulate and Rviz to see the vision_pose ROS topic (the orientation/...
0
votes
1answer
43 views

Do IMU have value in SLAM?

IMU are often used in theoretical models involving SLAM. I'm a bit confused on their practical value since error accumulation is so bad that after a couple seconds you need to completely ignore it. ...
2
votes
3answers
7k views

Hector SLAM, Matching algorithm

I'm trying to understand the scan-matching part of Hector SLAM (PPT summary). It seems a little difficult to understand, in some cases, how is it possible to actually perform the alignment of the ...
0
votes
0answers
11 views

What are the state-of-the-art variants of the basic ICP algorithm for point cloud registration?

The questions is quite straightforward. For the past few days I've been looking into point cloud registration. It looks like it all started with the basic ICP algorithm as described in P. J. Besl and ...
1
vote
1answer
53 views

How do robots move parallel to a wall/line?

I have been studying robotics by myself, lately. I noticed that there are various mapping, localization methods (popularly under SLAM), but are there concepts relating to the robot moving in a ...
0
votes
2answers
123 views
0
votes
0answers
10 views

How to get 2D map using Stereoscopic camer (RGB+D), IMU and GPS?

I am starting with slam using imu, stereo camera (that gives RGB + depth info) camera and gps mounted on my robot. I wish to create a 2D map for it like this: But with landmarks, so that I can stop ...
2
votes
2answers
964 views

How do I evaluate the minimum requirements of the processor and camera for a visual SLAM robot?

I would like to build a visual SLAM robot (just for self-learning purpose) but I get frustrated how I know which processor and camera should be used for visual SLAM. First, for the processor, I have ...
0
votes
0answers
13 views

Improvements over FastSLAM2.0

Are there some papers and/or works that describe improvements for the FastSLAM2.0 algorithm? I'm particularly interested in the following areas: The map is completely unknown at the beginning of the ...
3
votes
2answers
88 views

Do self-driving robots use object-level SLAM?

How do self-driving bots usually deal with transient objects, e.g., parked cars on the side of roads when they can come and go? These aren't moving objects at the time of capture, but they do move at ...
2
votes
1answer
27 views

How to deal with Gaussian Errors, which don't have a mean value of 0?

I'm writing a SLAM algorithm. One of the main problems is, that the landmark measurement error is not really Gaussian distributed, which means, their error doesn't have a mean value of 0. I already ...
1
vote
2answers
131 views

Triangulation: Ceres solver minimizes only the last residual block

I have been attempting to estimate a bunch of 3d coordinates viewed via a multi-view setup with known poses, I have the code running, but the output of ceres seems baffling. There are 7 image frames/...
0
votes
0answers
20 views

When a permutation matrix is desired for transforming camera frame to world frame?

When dealing with rectified images, why would the inverse of a simple permutation matrix $$P = {\begin{bmatrix} 0 & -1 & 0 \\ 0 & 0 & -1 \\ 1 & 0 & 0 \end{bmatrix}}^{-1}$$ ...
0
votes
0answers
11 views

How does isam compare with Gmapping and Hector?

I read about incremental smoothing and mapping (iSAM) first in the paper on hector_slam (a flexible and scalable SLAM system with full 3D motion estimation by Stefan Kohlbrecher et al) and then read ...
0
votes
1answer
274 views

EKF SLAM : SLAM specific Jacobians for new landmarks

I am currently trying to understand the books SLAM for dummies and Simulataneous localization and mapping with the extended Kalman filter to implement slam. I have understood steps 1 and 2 SLAM for ...
0
votes
0answers
49 views

Transforming a 3x3 Covariance Matrix to 2x2

Hello friends of the robotics, for Data Association I have the Robots cov matrix in a 3x3 Form, but the measurements and landmarks only in 2x2. I want to compute the Mahalanobis distance, so how ...
1
vote
1answer
69 views

How is the depth estimation done in DTAM / LSD-SLAM (direct VSLAM)?

I know that DTAM and LSD-SLAM both employ the photometric error between two keyframes to estimate the image depth. But I don't know what the photometric error describes precisely. In the DTAM paper, I ...
2
votes
0answers
33 views

How does loop closure backpropagate the robots states into prior times?

I have read some about loop closure and I am somewhat confused. Suppose we implement something like EKF slam using LIDAR and suppose loop closure is aided by computer vision based features so that if ...
1
vote
0answers
22 views

How to correctly use [VertexSE3Expmap] as two connecting Vertex in Edge_V_V_GICP?

I am working on a pose estimation problem solved by Levenberg-Marquardt with g2o. I want to build 3D rigid constraint between two pose, so I choose Edge_V_V_GICP and test the g2o/examples/icp/...
0
votes
1answer
80 views

How does sensor fusion related to SLAM?

How does sensor fusion affect the SLAM process? If we have a stereo camera with GPS and IMU, how does sensor fusion benefit the SLAM? Do we use sensor fusion to enhance the localization phase of SLAM, ...
1
vote
1answer
79 views

How to generate Particles in Particle Filter?

I have been trying to implement FastSlam 1.0. To implement this, I need to create particles. Now my confusion is how to create Particles? I have some odometry and Measurement data. Using those data ...
1
vote
1answer
115 views

The biases in the state vector of Extended Kalman Filter(EKF)

I am reading one paper on observability Observability Analysis of Aided INS with Heterogeneous Features of Points, Lines and Planes. The state vector contains the current IMU state and the feature ...
1
vote
3answers
3k views

How to call remote ROS node on mobile robot through laptop using wifi?

I've recently tried to get the remote ROS node on a mobile robot through wifi. This is as below picture. I've run roscore command on both laptop and mobile robot ...
2
votes
1answer
79 views

Why innovation equation in Extended Kalman filter is called innovation? [closed]

In the Extended Kalman filter for SLAM, why the innovation equation is called innovation? Is there any reason behind it?
0
votes
0answers
13 views

Should I wrap the intrinsic and extrinsic parameters to a single vector during optimization?

I've read the libmv library dedicated to solving the bundle adjustment problem. The author states it's better to wrap the rotation and translation parameters into a single vector during optimization ...
0
votes
1answer
36 views

Motion model and homogeneous transformation issue on a drone

I am trying to develop a EKF-SLAM algorithm for a drone, and I want to estimate its position in the inertial/world reference frame. I have as control variables the linear and angular velocities in the ...
0
votes
0answers
283 views

What does the normalized image coordinates imply?

In VSLAM or visual odometry, we use a camera matrix P to transform 3D scene points to 2D image points. When using homogeneous representation, we may choose the image coordinates as the normalized ...
0
votes
1answer
38 views

Does every rotation vector has an one-to-one corresponding rotation matrix?

Given a rotation vector, can we always get the same corresponding rotation matrix computed by the Rodrigue's rotation formula?
3
votes
2answers
498 views

In SLAM loop closure, What does a sim3 matrix do?

I am confused between 3D rigid affine(with scale, without shear) transformation and Lie group's sim(3) matrix. 3D affine would be [sR|t; 0 1]. we rotate, scale and then translate a 3D point using ...
0
votes
0answers
18 views

Can someone share with me some modern review paper about the filter-based SLAM?

I'm currently learning the Visual SLAM. But I'm also very curious about the modern filter-based SLAM. Can someone share with me some modern review papers about it?
1
vote
3answers
43 views

Occupancy grid maps

Why do we take probabilistic approch to model the environment for robots in occupancy grid maps.The assumption is always taken that each cell on the grid map is either free or occupied.So why have ...
2
votes
0answers
36 views

How do you handle angle discontinuities in estimation problems?

When one is implementing a state estimator in a system that involves kinematics, will inevitably face the problem of angle discontinuities, i.e., the fact that the angles have to be wrapped between ...
0
votes
1answer
46 views

ICP(Iterative Closest Point) with Partially Overlapping Conditions & Changing Point Numbers

I am currently working on fixing vehicle odometry data using lidar contour points. Since I am receiving lidar data in the form of countour points, I thought I'd use ICP to correct the odometry error ...
2
votes
2answers
58 views

Compute path in absolute frame from sequence of measurements

I have a sequence of measurements $\{(x_i, y_i, \theta_i)\}_{i = 1 \:...\: N}$. Each of these represents the new pose of the robot seen from the previous pose, i.e. a measurement $(x', y', \theta')$ ...
0
votes
0answers
27 views

Are there some papers or books that compactly elaborate the essential part of the multiple view geometry?

I am a novice to visual SLAM and computer vision. Recently I've read a paper "A micro Lie theory for state estimation in robotics" dedicated to introducing the essential part that necessary to ...
0
votes
0answers
33 views

Robot Localization - Motion and Sense Probability

I'm currently taking Udacity's AI for robotics course and came across a question that stumped me. The problem plays on localization probability given uncertainty in our measurement updates. The first ...
1
vote
0answers
40 views

Caculate/Specify the covariance matrix for a omniwheel robot

I have an omnidirectional robot (x, y and rotation around z), which I would like to use the SLAM-algorithm from ROS. But the odometry from the robot has a drift, which makes some error. To improve the ...
2
votes
2answers
113 views

How to handle landmarks in Bundle Adjustment?

At the moment I try to understand Bundle Adjustment on a level to be able to implement it on my own. The major point I'm still confused at is the management of the landmarks. So, let's think of a few ...
0
votes
0answers
18 views

Bundle Adjustment for Monocular SLAM

I am confused with how monocular BA works in visual-based SLAM. Is there any tutorials I can do in openCV to provide me some visualization aid? Thank You.
0
votes
1answer
139 views

Technologies needed for indoor and outdoor navigating robot

Before I begin, I should add that I am a complete beginner in robotics and hope that I can figure out where I should start by asking this question. I am trying to make a robot that is able to ...
0
votes
1answer
53 views

EKF-SLAM what should the observation model be?

I am implementing an EKF algorithm for a drone localization, and while I was defining the observation model I got a bit confused. This is my situation: I have a drone which is able to give me the ...
1
vote
1answer
57 views

What is the concepts of submaps in LIDAR based graph slam algorithms?

I have been reading some slam papers recently and many of the papers mention building and performing scan matching on submaps instead of individual poses. Does it mean that a submap is just a single ...
0
votes
2answers
69 views

Which math books would help in learning SLAM systems? [closed]

Recently I started studying papers on SLAM systems by Durrant-Whyte for my research and I'm finding some difficulties in the math (matrices and probability) that is tackled in these papers. Which ...
0
votes
3answers
176 views

Difference between SLAM and Localization

What are the differences between SLAM and Localization if you have a known map? How does the position probability update differ between the two? In particular I'm curious on if localization is a ...
0
votes
2answers
99 views

Guidance on SBC for Visual-Based SLAM [closed]

Intro: I am a student that just started a project regarding prototyping a mobile robot that involve Indoor SLAM implementation. I am very new to the field of computer vision, SLAM and SBC (single ...
2
votes
0answers
86 views

Applying initial guessing to LiDAR point cloud for ICP processing in Graph SLAM

I am currently in the process of implementing Graph SLAM using ICP and g2o in python 2.7 The data I have are pose data (4 x 4 transformation matrix) and lidar data ( in the format of [x y z 1] with ...
0
votes
1answer
70 views

On the covariance matrix of the EKF SLAM

In the covariance matrix of the EKF SLAM, there are components that specifies the correlation between landmarks. Are those values important? Because while we bulding map of landmarks, we only draw the ...

1
2
3 4 5
7