CSE 568
Robotics Algorithms
MWF 11:00 11:50 AM
Prof. Karthik Dantu
[email protected]
http:/www.cse.bualo.edu/faculty/kdantu/
Davis 331
Oce Hours: MW 1-2pm
(716) 645-2670
This syllabus is subject to change over the course of the semester.
Course Description
1. a.
Let X denote the first chicken pulled out randomly from coop B.
Let Y be the 2 chickens that escape from coop A to coop B.
P(X=F) = P(X=F|Y=MM)P(Y=MM) + P(X=F|Y=FF)P(Y=FF) + P(X=F|Y=MF)P(Y=MF)
P(X=F) = (10C
University at Buffalo, Computer Science and Engineering
CSE 468/568: Robot Algorithms
Homework 3: Probabilistic Algorithms
Problem 1
You maintain two chicken coops in your garage. Coop A has ten male and ve female chickens.
Coop B has ve male and ten fema
University at Buffalo, Computer Science and Engineering
CSE 468/568: Robot Algorithms
Homework 1: Kinematics
Karthik Dantu
This is the rst assignment of the class and carries 5% of your total grade. It is due on 3rd
March (Monday) before class. Please sta
CSE 568: Midterm
1
CSE 568 Midterm
Kinematics
I
2r
Y
30
2d
o
P
3d
2r
I
X
Figure 1: Given robot
You are given a robot as shown in Figure 1 with dimensions as shown. We observe it
from an inertial frame denoted by I XI Y. Let us assume r = 2m and d = 1m. Fo
CSE 468/568: Lab 3
1
CSE 468/568 Lab 3: Grid Localization Based on
Real Data in ROS
The objective of this assignment is to make you familiar with Grid Localization which
is a variant of discrete Bayes Localization. In addition you will learn how to create
CSE 468/568: Robotics Algorithms
Legged Locomotion
Karthik Dantu
[email protected]
Some slides adopted from robotics courses at U. Freiburg, ETH, CMU, DIT, USC, and others
Administrivia
ROS on CSE machines
silversun.cse.buffalo.edu
Instructions on wik
Introduction to Robot Control
Karthik Dantu
CSE 468/568
Localization
Mapping
position
global map
Cognition
Path Planning
path
environmental model
local map
Perception
Mission
commands
Path
Execution
Information
Extraction
Actuator
commands
raw-data
Acting
CSE 468/568: Robotics Algorithms
Robot Planning and Navigation
Architectures
Karthik Dantu
[email protected]
Some slides adopted from ETH, Berkeley, the textbook and others
Lab 2: Obstacle Avoidance and
Feature Detection
Implement Bug2 using laser range
ROS %
Karthik Dantu
CSE 468/568:Robo:cs Algorithms
%: Introduc:on
Allows ROS nodes to
keep track of mul:ple
frames and
rela:onships between
the frames
Builds a tree structure
One node (frame) can
have only one parent
Each node can have
mu
Robot Autonomy
Karthik Dantu
CSE 468/568: Robo;cs Algorithms
Recap
Robot = sensors + actuators + computing +
communication + ability to move
Objective: Make a robot autonomous
To answer these questions, the
robot has to
Where am I?
What is around
Range Sensing
Karthik Dantu
CSE 468/568:Robo;cs Algorithms
Range Sensors
Laser range nders give
depth informa;on
Data in polar coordinates
Angular resolu;on 0.25-1
degree
Depth range 5cm to 20m
(or more) with resolu;on
of 10-15mm
Five-ten
CSE 468/568: Robotics Algorithms
Karthik Dantu
[email protected]
Class Logistics
Instructor: Karthik Dantu (W 4-5pm, F 3-4pm)
TA: Zakieh Hashemifar (T-Th 3-4pm)
Recitations: Davis 113A(T-Th 10-11 AM)
Please register on Piazza main forum for interaction.
CSE 468/568: Robotics Algorithms
ROS: Introduction
Karthik Dantu
[email protected]
Some slides adopted from Brown, UT-Austin, ros.org, and others
Robotics Research A Decade Ago
Only for advanced/graduate students
Everything home-grown
Hardware
Softwa
CSE 468/568: Robotics Algorithms
Karthik Dantu
[email protected]
Some slides adopted from robotics courses at U. Freiburg, ETH, CMU, DIT,
USC, and others
Recap
Robot = sensors + actuators + computing +
communication + ability to move
Objective: Make a
gia64369_ch08.qxd
9/21/05
4:26 PM
Page 255
8
Torque and Angular
Momentum
I
n gymnastics, the iron cross is
a notoriously difcult feat that
requires incredible strength.
Why does it require such great
strength? To perform the iron
cross, the forces exerted
Feature extraction: Corners and blobs
Why extract features?
Motivation: panorama stitching
We have two images how do we combine them?
Why extract features?
Motivation: panorama stitching
We have two images how do we combine them?
Step 1: extract featu
CSE 468/568: Robotics Algorithms
Notes: Planar Transformations
Feb 8, 2015
Lecturer: Karthik Dantu
1
Planar Rotation
Consider two coordinate systems Q = (X, Y ) and Q = (X , Y ), where Q is rotated by an angle
counter-clockwise from Q. We want to transfo
Sensors 2014, 14, 17567-17585; doi:10.3390/s140917567
OPEN ACCESS
sensors
ISSN 1424-8220
www.mdpi.com/journal/sensors
Article
In-Flight Estimation of Center of Gravity Position Using
All-Accelerometers
Yazan Mohammad Al-Rawashdeh 1,*, Moustafa Elshafei 1
CSE 468/568: Robotics Algorithms
Topic 2: Kinematics of Wheeled Robots
February 21, 2015
Lecturer: Karthik Dantu
1
Introduction
Kinematics is the branch of classical mechanics which describes the motion of points, bodies (objects) and
systems of bodies (g
CSE 468/568: Robotics Algorithms
Wheeled and Aerial Locomotion
Karthik Dantu
[email protected]
Some slides adopted from robotics courses at U. Freiburg, ETH, CMU, DIT, USC, and others
Recap
Locomotion: Environment is fixed and the robot moves by imparti
University at Buffalo, Computer Science and Engineering
CSE 468/568: Robot Algorithms
Homework 1: Kinematics
Karthik Dantu
This is the rst assignment of the class and carries 5% of your total grade. It is due on 2nd
March (Monday) before class. Please sta
CSE 468/568: Robotics Algorithms
Perception From Range Sensors
Karthik Dantu
[email protected]
Some slides adopted from robotics courses at Utah, MIT, ETH, CMU, DIT, USC, and others
Range Sensors
Laser range finders give
depth information
Data in polar
COS 495 - Lecture 14
Autonomous Robot Navigation
Instructor: Chris Clark
Semester: Fall 2011
1
Figures courtesy of Siegwart & Nourbakhsh
Control Structure
Prior Knowledge
Operator Commands
Localization
Perception
2
Cognition
Motion Control
Outline
1. Mark
CSE 468/568: Robotics Algorithms
Image Processing I
Correlation
Karthik Dantu
[email protected]
Some slides adopted from robotics courses at Utah, MIT, ETH, CMU, DIT, USC, and others
Introduction
Field of signal processing where input signal is an image