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
23
votes
8answers
15k views

Absolute positioning without GPS

Using an IMU a robot can estimate its current position relative to its starting position, but this incurs error over time. GPS is especially useful for providing position information not biased by ...
16
votes
2answers
2k views

EKF-SLAM Update step, Kalman Gain becomes singular

I'm using an EKF for SLAM and I'm having some problem with the update step. I'm getting a warning that K is singular, rcond evaluates to ...
14
votes
4answers
8k views

What is inverse depth (in odometry) and why would I use it?

Reading some papers about visual odometry, many use inverse depth. Is it only the mathematical inverse of the depth (meaning 1/d) or does it represent something else. And what are the advantages of ...
14
votes
3answers
559 views

How to determine quality of ICP matches?

In SLAM frontends which use the Iterative Closest Point (ICP) algorithm for identifying the association between two matching point clouds, how can you determine if the algorithm is stuck in a local ...
13
votes
2answers
6k views

Difference between Rao-Blackwellized particle filters and regular ones

From what I've read so far, it seems that a Rao-Blackwellized particle filter is just a normal particle filter used after marginalizing a variable from: $$p(r_t,s_t | y^t)$$ I'm not really sure ...
13
votes
1answer
677 views

How do SLAM algorithms handle a changing environment?

I'm doing some groundwork for a project, and I have a question about the current state of SLAM techniques. When a SLAM-equipped device detects an object, that object's position is stored. If you look ...
12
votes
1answer
362 views

What is the difference between SAM and SLAM?

What is the difference between Smoothing and Mapping (SAM) and Simultaneous Localization and Mapping (SLAM)? These general approaches seem closely related. Can someone describe the differences?
12
votes
4answers
5k views

How to obtain dense point clouds from stereo cameras?

I am trying to use a stereo camera for scene reconstruction, but I can usually only obtain sparse point clouds (i.e. over half the image does not have any proper depth information). I realize that ...
10
votes
1answer
427 views

Who coined (or popularized) the term “SLAM”?

According to Wikipedia's article on SLAM, the original idea came from Randal Smith and Peter Cheeseman (On the Estimation and Representation of Spatial Uncertainty [PDF]) in 1986, and was refined by ...
10
votes
1answer
322 views

Least squares map joining

There is a lot of background here, scroll to the bottom for the question I am trying out the map joining algorithm described in How Far is SLAM From a Linear Least Squares Problem; specifically, ...
9
votes
3answers
2k views

What algorithm can I use for constructing a map of an explored area using a number of ultrasound sensors?

Ultrasound sensors are incredibly cheap these days which makes them a popular choice for many hobbyist robotic applications, and I'd like to use a bunch of them (say 10) around a robot with an ...
9
votes
2answers
1k views

The relationship between point cloud maps and graph maps

I am most familiar with SLAM maps that are point clouds, usually in the form of a vector like $<x,y,\theta,f_{1x},f_{1y},...,f_{nx},f_{ny}>$. I also understand how to create a map like this ...
9
votes
3answers
2k views

How can I improve the map in my Mobile Autonomous Robot using KINECT

A little background of my aim I am in the process of building a mobile autonomous robot which must navigate around an unknown area, must avoid obstacles and receive speech input to do various tasks. ...
9
votes
1answer
239 views

In practical terms, how close is the accuracy of camera-based visual odometry/SLAM methods to lidar-based methods for autonomous car navigation?

Benedict Evans, a general partner at Andreessen Horowitz, claims that “almost all autonomy” projects are using lidar for SLAM, and that not all of them use HD maps. An MIT group is testing self-...
8
votes
5answers
14k views

How computationally powerful is an Arduino Uno board?

What can an Arduino board such as the Uno really do? Of course simple things like controlling a couple servos is very easy for it. However, I don't think an Uno board would be able to preform real-...
8
votes
4answers
2k views

In EKF-SLAM, why do we even need odometry when there is a more reliable sensor?Also, are all SLAM algorithms feature-based?

In the book of SLAM for dummies, why do we even need the odometry when the robot would use the data retrieved from the laser scanner which is more accurate than odometry? Why not just rerly on the ...
8
votes
3answers
2k views

SLAM without landmarks?

First, is it possible to build map without landmarks for a robot in 2D? Let's say we have an aisle surrounded by two walls. The robot moves in this environment. Now is it feasible to build such a ...
8
votes
1answer
2k views

What is the best way to fuse measurements from IMU, LIDAR, and Encoder information in some recursive bayesian filter?

I am doing SLAM with a four wheeled (2-wheel drive) differential drive robot driving through some hall way. The hallway is not flat everywhere. And the robot turns by spinning in place, then traveling ...
7
votes
1answer
765 views

Noise in motion and measurement models

When using an EKF for SLAM, I often see the motion and measurement models being described as having some noise term. This makes sense to me if you're doing a simulation, where you need to add noise ...
6
votes
3answers
4k views

Difference between SLAM and “3D reconstruction”?

I'm reading this paper: http://arxiv.org/abs/1310.2053 (The role of RGB-D benchmark datasets: an overview) and see the following words: Thanks to accurate depth data, currently published papers ...
6
votes
3answers
1k views

Is an accelerometer sufficient to detect displacement, or do I need an INS?

Do I need a complex system (of gyros, accelerometers etc.) to detect if a robot has moved forward or can I simply use an accelerometer. I'm building a robot that learns to walk and I need to detect ...
6
votes
1answer
2k views

SLAM: Why use two cameras (stereo) if SLAM can be done using single camera (monocular)?

I am aware that algorithm for monocular SLAM is complex compared to stereo SLAM. But my question is if by any means it is possible to do SLAM using one camera why one should use two cameras to do the ...
6
votes
1answer
6k views

Are there any advantages to using a LIDAR for SLAM vs a standard RGB camera?

I've been thinking about building a small UAV with an onboard LIDAR, just for fun. I'm interested in SLAM and autonomous flight indoors and thought that I would need a lidar to get a 3D map of the ...
6
votes
1answer
4k views

Build a ROS robot with SLAM without laser

I've build a simple wheeled robot based on two continuous servos, controlled by Raspberry Pi running ROS-groovy, with a smart phone mounted on top to provide additional sensors. I'd like to situate ...
6
votes
1answer
566 views

Comparing maps to groundtruth

When you've created a map with a SLAM implementation and you have some groundtruth data, what is the best way to determine the accuracy of that map? My first thought is to use the Euclidean ...
6
votes
2answers
281 views

Ensemble Kalman Filter SLAM

I know that there is an extended kalman filter approach to simultaneous localization and mapping. I'm curious if there is a SLAM algorithm that exploits the ensemble kalman filter. A citation would ...
6
votes
2answers
90 views

How does a self-driving car locate itself when the environment changes?

There's something I don't quite understand about SLAM. When a self-driving car wants to locate itself using a prior map, how does it do that when the environment keeps changing, e.g., new cars parked ...
5
votes
2answers
4k views

SLAM : Why is marginalization the same as schur's complement?

Consider the system $$ \tag 1 H\delta x=-g $$ where $H$ and $g$ are the Hessian and gradient of some cost function $f$ of the form $f(x)=e(x)^Te(x)$. The function $e(x)=z-\hat{z}(x)$ is an error ...
5
votes
1answer
910 views

role of chi2 in SLAM back-end optimization

All-most all SLAM back-end implementation compute chi2 estimates. Chi2 computation is usually used to compute the best-fitness score of model to the data. How it is related to optimization framework ...
5
votes
3answers
883 views

How can I implement tremaux algo in arduino line follower to navigate and create map?

The Map1 The task is divided into 2 runs, In first run, We have to navigate through whole map and reach the end mark taking all checkpoints. In second run, using the mapping from first run we have to ...
5
votes
2answers
3k views

How to use SLAM with simple sensors

What 2D SLAM implementations (preferably included in ROS) can be used with simple distance sensors like IR or ultrasonic rangefinders? I have a small mobile platform equipped with three forward ...
5
votes
2answers
414 views

SLAM for Autonomous car

I am working on SLAM for autonomous car like vehicles with 2D lasers and IMU (deriving odometry). I would like to know how efficient is using the existing SLAM algorithms (for example: gmapping in ...
5
votes
1answer
924 views

LIDAR Points as Landmarks

I am currently trying to implement a GraphSLAM/SAM algorithm for LIDAR. From papers I've read, you generate a directed graph from expected LIDAR measurements to landmarks similar to the image below (...
4
votes
4answers
1k views

Which micro-controler/processor to be used for autonomous stereo vision robot system?

I am very new two robotics, however I have a working stereo algorithm which I want to combine with a SLAM algorithm. I am developing this system for an other application but I decided integrating it ...
4
votes
6answers
6k views

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

I'm reading a paper: Choi C, Trevor A J B, Christensen H I. RGB-D edge detection and edge-based registration[C]//Intelligent Robots and Systems (IROS), 2013 IEEE/RSJ International Conference on....
4
votes
2answers
2k views

the uncertainty of initializing new landmark in EKF-SLAM

In EKF-SLAM (based-feature map) once the robot senses a new landmark, it is augmented to state vector. As a result, the size of the state vector and the covariance matrix are expanded. My question is ...
4
votes
3answers
2k views

Is there any advantage to velocity motion models over odometry motion models for SLAM?

I've seen several examples of SLAM algorithms (EKF SLAM, Graph SLAM, SEIF SLAM) written in terms of the velocity motion model. I have yet to see an example of any SLAM algorithm utilizing the ...
4
votes
2answers
344 views

Comprehensive comparison of SLAM algorithms

I'm looking for a research paper or series of papers that compare the performance of various simultaneous localization and mapping algorithms for rovers in a variety of real world environments. In ...
4
votes
3answers
2k views

A sensor that can see glass/transparent objects and surfaces

I am currently thinking about making a robot that will autonomously drive around the place. The place I want this robot to drive in however contains quite a few glass walls. When mapping the area I ...
4
votes
1answer
131 views

Suggestion for relevant non-complex simulator

I've recently started working on some localization algorithms like probabilistic road map and SLAM algorithms. What I'm looking for is a software that would help me in simulation for such algorithms. ...
4
votes
1answer
3k views

ROS AMCL does not need odometry data?

I'm reading amcl document on ROS Wiki. In its subscribed topics there is not odometry topic, why? It works only with laser? Subscribed Topics: (From ROS Wiki) scan (sensor_msgs/LaserScan) tf (tf/...
4
votes
2answers
998 views

Why does the low variance resampling algorithm for particle filters work?

I am studying and coding particle filters and I am using the Low variance sampling algorithm suggested in the Probabilistic Robotics book. I understand the procedure for the algorithm. A random number ...
4
votes
1answer
49 views

In the SLAM for dummies what is z-h in updating X?

In SLAM for Dummies there is on page 40 this formula: $X = X+K(z-h)$ What is $z-h$ in updating $X$?
4
votes
1answer
236 views

Scan Matching finds right rotation but false translation

I'm currently developing a SLAM software on a robot, and I tried the Scan Matching algorithm to solve the odometry problem. I read this article : Metric-Based Iterative Closest Point Scan Matching ...
4
votes
1answer
157 views

IPC-Bridge problem

Is anyone able to help me out getting IPC-bridge working on my ubuntu lucid installation (with matlab 2012a)? I'm not being able to finish the last step on here (Compiling the messages folders): https:...
4
votes
1answer
139 views

How to derive the Time-Update equation of SLAM

I was going through the tutorial on SLAM by Hugh Durrant-Whyte and Tim Bailey† and found this Time-Update equation (equation 4 in the paper): $ P\left(\mathrm{x}_{k},\mathrm{m} | \mathrm{Z}_{0:...
4
votes
1answer
133 views

How to avoid matrix singularity in GraphSLAM

I am trying to implement GraphSLAM from Sebastian Thrun's paper, The GraphSLAM Algorithm with Applications to Large-Scale Mapping of Urban Structures. When I compute the inverse of my information ...
4
votes
1answer
837 views

Calculate the uncertainty of a 6-dof pose for graph-based SLAM

This question is strongly related to my other question over here. I am estimating 6-DOF poses $x_{i}$ of a trajectory using a graph-based SLAM approach. The estimation is based on 6-DOF ...
4
votes
1answer
259 views

In order to integrate MCL and Occupancy Grid to implement Grid-based FastSLAM, do you have to record all data?

It's unclear as to how one goes about integrating Occupancy Grid mapping and Monte Carlo localization to implement SLAM. Assuming Mapping is one process, Localization is another process, and some ...
4
votes
2answers
944 views

EKF-SLAM initialize new landmark in covariance matrix

I am trying to implement an EKF-SLAM using the algorithm for unknown correspondences proposed in the book "Probalistic Robotics" by Sebastian Thrun in Table 10.2 . By now I understand actually all ...

1
2 3 4 5
7