Particle Filters (and Navigation)

Particle Filters (and Navigation)

本课程是 Applied Kalman Filtering 专项课程的一部分

位教师：Gregory Plett

访问权限由 Coursera Learning Team 提供

4个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

4个模块

深入了解一个主题并学习基础知识。

中级等级

推荐体验

2 周完成

在 10 小时一周

灵活的计划

自行安排学习进度

您将获得的技能

要了解的详细信息

可分享的证书

添加到您的领英档案

作业

24 项作业

授课语言：英语（English）

了解顶级公司的员工如何掌握热门技能

了解关于 Coursera for Business 的更多信息

Petrobras, TATA, Danone, Capgemini, P&G 和 L'Oreal 的徽标

积累特定领域的专业知识

本课程是 Applied Kalman Filtering 专项课程专项课程的一部分

在注册此课程时，您还会同时注册此专项课程。

向行业专家学习新概念
获得对主题或工具的基础理解
通过实践项目培养工作相关技能
获得可共享的职业证书

该课程共有4个模块

As the final course in the Applied Kalman Filtering specialization, you will learn how to develop the particle filter for solving strongly nonlinear state-estimation problems. You will learn about the Monte-Carlo integration and the importance density. You will see how to derive the sequential importance sampling method to estimate the posterior probability density function of a system’s state. You will encounter the degeneracy problem for this method and learn how to solve it via resampling. You will learn how to implement a robust particle-filter in Octave code and will apply it to an indoor-navigation problem.

This week, you will learn a computationally intensive method to estimate the state of highly nonlinear systems, where the pdfs do not need to be Gaussian.

涵盖的内容

7个视频12篇阅读材料5个作业1个讨论话题1个非评分实验室

7个视频总计103分钟

4.1.1: Welcome to the course! 8分钟
4.1.2: Review of key concepts 17分钟
4.1.3: Developing the integral framework for general Bayesian recursion 20分钟
4.1.4: How to approximate integrals numerically 12分钟
4.1.5: Implementing Bayesian inference via numeric integration 18分钟
4.1.6: Octave code to implement Bayesian inference 26分钟
4.1.7: Summary of "A brute-force solution for highly nonlinear systems" module plus next steps 3分钟

12篇阅读材料总计120分钟

Frequently Asked Questions 10分钟
Course Resources 10分钟
How to Use Discussion Forums 10分钟
Earn a Course Certificate 10分钟
Are you interested in earning an online MSEE degree? 10分钟
Notes for Lesson 4.1.1 10分钟
Notes for Lesson 4.1.2 10分钟
Notes for Lesson 4.1.3 10分钟
Notes for Lesson 4.1.4 10分钟
Notes for Lesson 4.1.5 10分钟
Notes for Lesson 4.1.6 10分钟
Notes for Lesson 4.1.7 10分钟

5个作业总计70分钟

Practice assignment for Lesson 4.1.3 10分钟
Practice assignment for Lesson 4.1.4 10分钟
Practice assignment for Lesson 4.1.5 10分钟
Practice assignment for Lesson 4.1.6 10分钟
Graded assignment for week 1 30分钟

1个讨论话题总计10分钟

Introduce yourself 10分钟

1个非评分实验室总计30分钟

Jupyter notebook implementing brute-force Bayesian inference 30分钟

This week, you will learn the tricks we will use to approximate the brute-force solution.

涵盖的内容

6个视频6篇阅读材料6个作业4个非评分实验室

6个视频总计71分钟

4.2.1: Introducing the Monte-Carlo method for approximating an integral 13分钟
4.2.2: The importance of an importance density 12分钟
4.2.3: Weight normalization 17分钟
4.2.4: The impulse function 15分钟
4.2.5: How to visualize a pdf stored as a sum of impulses? 10分钟
4.2.6: Summary of "How to approximate multidimensional integrals efficiently" module plus next steps 3分钟

6篇阅读材料总计60分钟

Notes for Lesson 4.2.1 10分钟
Notes for Lesson 4.2.2 10分钟
Notes for Lesson 4.2.3 10分钟
Notes for Lesson 4.2.4 10分钟
Notes for Lesson 4.2.5 10分钟
Notes for Lesson 4.2.6 10分钟

6个作业总计80分钟

Practice assignment for Lesson 4.2.1 10分钟
Practice assignment for Lesson 4.2.2 10分钟
Practice assignment for Lesson 4.2.3 10分钟
Practice assignment for Lesson 4.2.4 10分钟
Practice assignment for Lesson 4.2.5 10分钟
Graded assignment for week 2 30分钟

4个非评分实验室总计120分钟

Jupyter notebook to experiment with Monte-Carlo method 30分钟
Jupyter notebook to experiment with importance sampling 30分钟
Jupyter notebook to illustrate weight normalization 30分钟
Jupyter notebook to visualize pdfs from weighted impulses 30分钟

This week, you will put all of the tricks from week two together to implement (and then refine) the particle-filter method.

涵盖的内容

7个视频7篇阅读材料7个作业4个非评分实验室

7个视频总计114分钟

4.3.1: Sequential importance sampling (the particle filter) 33分钟
4.3.2: Setting up an example of the particle filter 15分钟
4.3.3: Octave code to implement a particle filter 18分钟
4.3.4: Examining the variables of the basic SIS algorithm 13分钟
4.3.5: How to "resample" the particles to reduce redundancy 18分钟
4.3.6: Implementing resampling in Octave; revisiting example 14分钟
4.3.7: Summary of "Developing and refining the particle-filter algorithm" module plus next steps 3分钟

7篇阅读材料总计70分钟

Notes for Lesson 4.3.1 10分钟
Notes for Lesson 4.3.2 10分钟
Notes for Lesson 4.3.3 10分钟
Notes for Lesson 4.3.4 10分钟
Notes for Lesson 4.3.5 10分钟
Notes for Lesson 4.3.6 10分钟
Notes for Lesson 4.3.7 10分钟

7个作业总计90分钟

Practice assignment for Lesson 4.3.1 10分钟
Practice assignment for Lesson 4.3.2 10分钟
Practice assignment for Lesson 4.3.3 10分钟
Practice assignment for Lesson 4.3.4 10分钟
Practice assignment for Lesson 4.3.5 10分钟
Practice assignment for Lesson 4.3.6 10分钟
Graded assignment for week 3 30分钟

4个非评分实验室总计120分钟

Jupyter notebook to implement SIS method 30分钟
Jupyter notebook to diagnose problem with SIS method 30分钟
Jupyter notebook to illustrate need for resampling 30分钟
Jupyter notebook implementing SIS with resampling 30分钟

This week, you will learn how to apply the particle filter to an indoor navigation problem.

涵盖的内容

6个视频6篇阅读材料6个作业1个非评分实验室

6个视频总计87分钟

4.4.1: Concepts in navigation 17分钟
4.4.2: The indoor navigation problem 15分钟
4.4.3: Setting up a sensor model for an example 20分钟
4.4.4: Setting up pdfs for the example 13分钟
4.4.5: Implementing indoor navigation using a particle filter in Octave 19分钟
4.4.6: Summary of "Navigation application using a particle filter" module plus next steps 3分钟