Perception and Estimation in Robotics, 2019 Fall.
[Announcement]
Please visit https://lms.ncu.edu.tw/ for more information.
[Couse information]
In the past 10 years, the robotics community has successfully applied perception algorithms (e.g., localization, mapping, object detection and tracking) to real world problems (e.g., localization of robots and VR/AR devices). The robots are able to sense the environments, know where I am in the map and where the targets are. The objective of this course is to teach students how to design perception algorithms using Kalman filter/Particle filter. In particular, the course will focus on Bayesian filter, Kalman filter, particle filter for estimation, localization, mapping and tracking applications. The students will have intensive hand-on training about how to solve perception problems for robots.
Instructor: Prof. Kuo-Shih Tseng
Time & classroom: Mon 789, M-218
Office hour: Mon 23 (9am-11am)
Office: Room 407, Hong-Jing building
[Requirements]
Familiarity of probability, linear algebra, and programming (e.g., C/C++, Python or MATLAB).
Due to the limited number of robots, only 25 students can take this course.
If you are interested in this course, please attend the first lecture on 2019/9/9.
Prof. Tseng will evaluate your probability, linear algebra and programming ability.
You should prove your ability via transcripts or other supporting documents.
If you are qualified, you will be admitted to this course.
If you are not qualified, you are still welcome to this course as an audience.
If you would like to take this course, please send me (kuoshih@math.ncu.edu.tw) the following documents by 9/13(Fri.):
A. 1-page SOP to explain why you want to take this course
B. Your transcript to demonstrate your ability in program, probability and linear algebra
C. Other supporting documents (e.g., programming competition award)
If you are qualified, I will give you a card to enroll in this course.
If you cannot enroll in this course, you still can be an audience.
However, you cannot use the robots & I will not grade your HW.
[Schedule]
[Textbook]
Prof. Kuo-Shih Tseng’s slides.
Optional textbook:
Sebastian Thrun, Wolfram Burgard and Dieter Fox, “Probabilistic Robotics”, MIT Press, 2006.
[Grade]
The grade for this course will consist of the following components:
Homework (X3) 30%
Midterm Exam 30%
Project Proposal (1-2 page) 10%
Project Presentation and Demonstration 10%
Project Report (4-8 pages) 20%
In the final project, the students need to propose an interesting application of perception, formulate the problem, implement algorithms on a real robot (e.g., Minibot or Bebop) or simulator (e.g, ROS).
More information about the AI maker Lab can be found in this link.
Perception and Estimation in Robotics, 2018 Fall.
[Announcement]
Please visit https://lms.ncu.edu.tw/ for more information.
[Couse information]
In the past 10 years, the robotics community has successfully applied perception algorithms (e.g., localization, mapping, object detection and tracking) to real world problems (e.g., localization of robots and VR/AR devices). The robots are able to sense the environments, know where I am in the map and where the targets are. The objective of this course is to teach students how to design perception algorithms using Kalman filter/Particle filter. In particular, the course will focus on Bayesian filter, Kalman filter, particle filter for estimation, localization, mapping and tracking applications. The students will have intensive hand-on training about how to solve perception problems for robots.
Instructor: Prof. Kuo-Shih Tseng
Time & classroom: Mon 789, M-327
Office hour: Mon 23 (9am-11am)
Office: Room 407, Hong-Jing building
[Requirements]
Familiarity of probability, linear algebra, and programming (e.g., C/C++, Python or MATLAB).
Due to the limited number of robots, only 20 students can take this course.
If you are interested in this course, please attend the first lecture on 2018/9/10.
Prof. Tseng will evaluate your probability, linear algebra and programming ability.
You should prove your ability via transcripts or other supporting documents.
If you are qualified, you will be admitted to this course.
If you are not qualified, you are still welcome to this course as an audience.
If you would like to take this course, please send me (kuoshih@math.ncu.edu.tw) the following documents by 9/14(Fri.):
A. 1-page SOP to explain why you want to take this course
B. Your transcript to demonstrate your ability in program, probability and linear algebra
C. Other supporting documents (e.g., programming competition award)
If you are qualified, I will give you a card to enroll in this course.
If you cannot enroll in this course, you still can be an audience.
However, you cannot use the robots & I will not grade your HW.
[Schedule]
[Textbook]
Prof. Kuo-Shih Tseng’s slides.
Optional textbook:
Sebastian Thrun, Wolfram Burgard and Dieter Fox, “Probabilistic Robotics”, MIT Press, 2006.
[Grade]
The grade for this course will consist of the following components:
Homework (X3) 30%
Midterm Exam 30%
Project Proposal (1-2 page) 10%
Project Presentation and Demonstration 10%
Project Report (4-8 pages) 20%
In the final project, the students need to propose an interesting application of perception, formulate the problem, implement algorithms on a real robot (e.g., Minibot or AR.Drone) or simulator (e.g, ROS).
[Final Project Demo]