Vidéo pédagogique
Notice
Sous-titrage
English
Langue :
Anglais
Crédits
Agostino Martinelli (Intervention)
Conditions d'utilisation
This course material is provided under Creative Commons License BY-NC-ND: the name of the author should always be mentioned ; the user can exploit the work except in a commercial context and he cannot make changes to the original work.
DOI : 10.60527/mjb6-v610
Citer cette ressource :
Agostino Martinelli. Inria. (2015, 1 juin). ﻿2.1. Localization process in a probabilistic framework: basic concepts , in 2. Bayes and Kalman Filters. [Vidéo]. Canal-U. https://doi.org/10.60527/mjb6-v610. (Consultée le 6 août 2024)

# ﻿2.1. Localization process in a probabilistic framework: basic concepts

Réalisation : 1 juin 2015 - Mise en ligne : 29 décembre 2016
• document 1 document 2 document 3
• niveau 1 niveau 2 niveau 3
Descriptif

In this part, we will talkabout localization which is a fundamental problem that arobot has to be able to solve in order to accomplish almost any tasks.In particular, we will start by discussing several motion sensor modelsand, starting from them, we will derive and we will discuss themost appropriate approaches to solve localization which areadopted by the mobile robotics community.

Intervention
Thème
Documentation

## Dans la même collection

• Vidéo pédagogique
00:07:44

### 2.4. Sensor statistical models

Martinelli
Agostino

So far in the characterization of our sensor measurements, we didn't talk about the errors. This is precisely what we want to do in this video. In particular, we want to compute two probability

• Vidéo pédagogique
00:11:52

### 2.7. Grid Localization: an example in 1D

Martinelli
Agostino

Now that we have the equations of the Bayes filter, we need a method in order to implement in real cases these equations. So, in the following, I want to discuss two methods, which are commonly

• Vidéo pédagogique
00:07:47

### 2.3. Wheel encoders for a differential drive vehicle

Martinelli
Agostino

In this video, we want to discuss the case of a wheel encoders in 2D, and in particular the case of a robot equipped with a differential drive which is very popular in mobile robotics.

• Vidéo pédagogique
00:06:07

### 2.5. Reminds on probability

Martinelli
Agostino

In this sequence I want to remind you a few concepts in the theory of probability and then in the next one we finally derive the equations of the Bayes filter. So the concept that I want to

• Vidéo pédagogique
00:08:01

### 2.8. The Extended Kalman Filter (EKF)

Martinelli
Agostino

We have seen the grid localization, and the advantage of this approach is that we can deal with any kind of probability distribution; in particular we don't need to do a Gaussian assumption. The

• Vidéo pédagogique
00:08:04

### 2.2. Characterization of proprioceptive and exteroceptive sensors

Before deriving the equations of the Bayes filter, I want to remind you a few concepts in the theory of probability, and also some mathematical characterization for the statistical error of the

• Vidéo pédagogique
00:07:35

### 2.6. The Bayes Filter

Martinelli
Agostino

The equations of the Bayes filters are the equation that allow us to update the probability distribution for the robot to be in a given configuration by integrating the information that are in the

## Avec les mêmes intervenants et intervenantes

• Vidéo pédagogique
00:07:21

### 3.6. Observability in robotics

Martinelli
Agostino

In this video we discuss a fundamental issue which arises when we deal with an estimation problem: understanding if the system contains enough information to perform the estimation of the state.

• Vidéo pédagogique
00:08:10

### 3.8. Applications of the Observability Rank Criterion

Martinelli
Agostino

In this video we want to apply the observability rank criterion to understand the observability properties of the system that we saw in the previous videos.

• Vidéo pédagogique
00:10:35

### 3.4. The use of the EKF in robotics

Martinelli
Agostino

In this video I want to explain the steps that we have to follow in order to implement an extended Kalman filter in robotics.

• Vidéo pédagogique
00:08:46

### 3.2. Examples for the Perception in the EKF

Martinelli
Agostino

In this video we discuss the second two equations of the Kalman filter.

• Vidéo pédagogique
00:09:13

### 3.1. Examples for the Action in the EKF

Martinelli
Agostino

In part 2, we have seen the equations of the Bayes filter, which are the general equations which allow us to update the probability distribution, as the data from both proprioceptive sensors and

• Vidéo pédagogique
00:06:12

### 3.5. Simultaneous Localization and Mapping (SLAM)

Martinelli
Agostino

In this video, we are discussing the SLAM problem: simultaneous localization and mapping.

• Vidéo pédagogique
00:06:56

### 3.7. Observability Rank Criterion

Martinelli
Agostino

In this video, we discuss an automatic method which is analytical and allows us to answer the question if a state is observable or not: this method is the Observability Rank Criterion which has

• Vidéo pédagogique
00:07:21

### 3.3. The EKF is a weight mean

Martinelli
Agostino

In this video I want to discuss the second two equations of the Kalman filter. And in particular I want to show that these actually perform a kind of weight mean.

• Vidéo pédagogique
00:06:07

### 2.5. Reminds on probability

Martinelli
Agostino

In this sequence I want to remind you a few concepts in the theory of probability and then in the next one we finally derive the equations of the Bayes filter. So the concept that I want to

• Vidéo pédagogique
00:07:47

### 2.3. Wheel encoders for a differential drive vehicle

Martinelli
Agostino

In this video, we want to discuss the case of a wheel encoders in 2D, and in particular the case of a robot equipped with a differential drive which is very popular in mobile robotics.

• Vidéo pédagogique
00:08:01

### 2.8. The Extended Kalman Filter (EKF)

Martinelli
Agostino

We have seen the grid localization, and the advantage of this approach is that we can deal with any kind of probability distribution; in particular we don't need to do a Gaussian assumption. The

• Vidéo pédagogique
00:07:44

### 2.4. Sensor statistical models

Martinelli
Agostino

So far in the characterization of our sensor measurements, we didn't talk about the errors. This is precisely what we want to do in this video. In particular, we want to compute two probability

## Sur le même thème

• Conférence
00:57:12

### Et si l’intelligence artificielle déferlait sur les océans ?

L’évolution des technologies d’observation et de modélisation a joué un rôle central dans l’accroissement des connaissances sur le fonctionnement des océans ou dans le développement des activités

• Conférence
00:59:29

### La vidéo sous-marine au service de la recherche halieutique

Accessible à de nombreuses applications, tant en biologie ou qu'en technologie des pêches, la vidéo sous-marine est de plus en plus utilisée dans le domaine de la recherche halieutique. Les progrès

• Vidéo pédagogique
00:07:25

### 5.6. Predicting Human Motion

Vasquez Govea
Alejandro Dizan

In video 5.5 we have defined an HMM in Python. In this video we are going to learn how to use it to estimate and predict motion.

• Vidéo pédagogique
00:07:52

### 5.9. Other approaches: Planning-based approaches

Vasquez Govea
Alejandro Dizan

In this video we are going to study a second, and probably the most promising alternative for motion prediction: planning-based algorithms.

• Vidéo pédagogique
00:04:13

### 5.4. Bayesian filter inference

Vasquez Govea
Alejandro Dizan

In this video we will review the base filter and we will study a particular instance of the Bayesian filter called Hidden Markov models which is a discrete version of a Bayesian filter.

• Vidéo pédagogique
00:05:32

### 5.7. Typical Trajectories: drawbacks

Vasquez Govea
Alejandro Dizan

In previous videos we have discussed how to implement the typical trajectories and motion patterns approach. In this video we are going to discuss what are the drawbacks of such an approach,

• Vidéo pédagogique
00:04:39

### 5.5. From trajectories to discrete time-state models

Vasquez Govea
Alejandro Dizan

In this video we are going to apply the concepts we have reviewed in the video 5.4 into real trajectories.

• Vidéo pédagogique
00:05:35

### 5.8. Other approaches: Social Forces

Vasquez Govea
Alejandro Dizan

In this video we will review one of the alternatives we are proposing to the use of Hidden Markov models and typical trajectories: the Social Force model.

• Vidéo pédagogique
00:09:44

### 4.9. Situation Awareness – Collision Risk Assessment and Decision (Object level)

Laugier
Christian

This video addresses the problem of collision risk assessment and decision.

• Vidéo pédagogique
00:07:39

### 4.1. Robot Perception for Dynamic environments: Outline and DP-Grids concept

Laugier
Christian

The fourth part of the course addresses perception, situation awareness and decision making. In this first video, we're giving an outline of the problem and introducing the new concept of dynamic

• Vidéo pédagogique
00:09:02

### 5.2. Expectation-Maximization Clustering

Vasquez Govea
Alejandro Dizan

In this video, we are going to start working towards building a motion model.

• Vidéo pédagogique
00:06:15

### 4.6. Detection and Tracking of Mobile Objects – Model and Grid based approaches

Laugier
Christian

This video addresses the question of model-based and grid-based approaches.