2016 lecture 0 introduction and lecture overview
TRANSCRIPT
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
1/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Roland Siegwart, Margarita Chli, Martin Rufli
Introduction | Lecture Overview 1
Mobile Robots | Introduction and Lecture OverviewAutonomous Mobile Robots
https://edge.edx.org/courses/course-v1:ETHx+AMRx_Internal_FS2016+2016_Spring/
Spring 2016
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
2/36
|
Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Roland Siegwart, ETH Zurich
Margarita Chli, ETH Zurich
Martin Rufli, IBM Research
Video segments
Marco Hutter, ETH Zurich
Davide Scaramuzza, Univ. of Zrich
Paul Furgale, Apple
Introduct ion | Lecture Overview 3
Autonomous mobile robot | your teachers
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
3/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Running as an ETH-internal MOOC (Massive Open Online Course)
Over 30 short video lectures that we call segments. The segments are complemented with:
short questions for each segment to verify your understanding and progress
various exercises (problem sets)
videos showing the current state-of-the-art in the field
Please register on edge.edx.org and sign up for the lecture AMRx of ETHx
Textbook
Introduction to Autonomous Mobile Robots
Roland Siegwart, Illah Nourbakhsh, Davide Scaramuzza
The MIT Press
Other materials
http://www.asl.ethz.ch/education/lectures/autonomous_mobile_robots.html
Introduction | Lecture Overview 4
Autonomous mobile robot | about the coursehttps://edge.edx.org/courses/course-v1:ETHx+AMRx_Internal_FS2016+2016_Spring/
On sale in LEE J206 for CHF 40
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
4/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
We expect you to view and study the following elements beforehand:
video segment relevant AMR book chapters
problem sets and quizzes
Lecture on Tuesday 10:15 12:00 in CAB G 11
Organized as flipped classroom we need your active participation!!
Video Segments will not be repeated
Focus on putting the learnt content into context
Questions from students (in forum until Friday before the related lecture)
go over difficult problems
go a bit more in detail where needed (e.g. proofs of theorems, etc.)
Exercises on Tuesday 14:15 16:00 in CAB G 11 (around every second week)
Special exercises only supported for ETH students
Introduction | Lecture Overview 5
The Lecture
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
5/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 6
Lecture Program
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
6/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Type
Written session examination
Language of examination
English
Course attendance confirmation required
No Repetition
The performance assessment is only offered in the session after the course unit. Repetition
only possible after re-enrolling.
Mode of examination written 120 minutes
Written aids
4 A4-pages personal summary
Introduction | Lecture Overview 7
Exam
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
7/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
The three key questions in Mobile Robotics Where am I ?
Where am I going ?
How do I get there ?
To answer these questions the robot has to
have a model of the environment (given or autonomously built)
perceive and analyze the environment
find its position/situation within the environment
plan and execute the movement
Introduction | Lecture Overview 8
Autonomous mobile robot | the key questions
?
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
8/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 9
Autonomous mobile robot | the see-think-act cycle
see-think-actraw data
position
global map
Sensing Acting
Information
Extraction
Path
Execution
Cognition
Path Planning
knowledge,
data base
mission
commands
Localization
Map Building
MotionControl
Perception
actuator
commands
environment model
local mappath
Real World
Environment
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
9/36
|
Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Wheel types and its constraints
Rolling constraint
no-sliding constraint (lateral)
Motion control
Introduction | Lecture Overview 10
Motion Control | kinematics and motion control
, ,
, , ?
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
10/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 11
Autonomous mobile robot | the see-think-act cycle
see-think-actraw data
position
global map
Sensing Acting
Information
Extraction
Path
Execution
Cognition
Path Planning
knowledge,
data base
mission
commands
Localization
Map Building
MotionControl
Perception
actuator
commands
environment model
local mappath
Real World
Environment
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
11/36
|
Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Laser scanner
time of flight
Camers
Introduction | Lecture Overview 12
Perception | sensing
Lens
Focal Point
fFocal Length:
objectFocalPlane
GPSIMU
Wheel
encoders
Laser scanner
Omnidirectional
camera
Standard
camera
Laser
scanners
Security
switch
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
12/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Keypoint Features
features that are reasonably invariant to
rotation, scaling, viewpoint, illumination
FAST, SURF, SIFT, BRISK,
Filtering / Edge Detection
Introduction | Lecture Overview 13
Perception | information extraction
11
62
3
4
5
6
7
89
1
5
1
41
31
2
1
1 1
0
C
Image from [Rosten et al., PAMI 2010]
Keypoint matching
BRISK example
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
13/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 14
Autonomous mobile robot | the see-think-act cycle
see-think-actraw data
position
global map
Sensing Acting
Information
Extraction
Path
Execution
Cognition
Path Planning
knowledge,
data base
mission
commands
Localization
Map Building
MotionControl
Perception
actuator
commands
environment model
local mappath
Real World
Environment
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
14/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
SEE: The robot queries its sensors finds itself next to a pillar
ACT: Robot moves one meter forward motion estimated by wheel encoders accumulation of uncertainty
SEE: The robot queries its sensors
again finds itself next to a pillar
Belief update (information fusion)
Introduction | Lecture Overview 15
Localization | where am I?
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
15/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 16
Autonomous mobile robot | the see-think-act cycle
see-think-actraw data
position
global map
Sensing Acting
Information
Extraction
Path
Execution
CognitionPath Planning
knowledge,
data base
mission
commands
Localization
Map Building
MotionControl
Perception
actuator
commands
environment model
local mappath
Real World
Environment
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
16/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 17
Cognition | Where am I going ? How do I get there ?
Goal
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
17/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Global path planning
Graph search
Local path planning
Local collision avoidance
Introduction | Lecture Overview 18
Cognition | Where am I going ? How do I get there ?
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
18/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 19
Autonomous mobile robot | the see-think-act cycle
see-think-actraw data
position
global map
Sensing Acting
Information
Extraction
Path
Execution
CognitionPath Planning
knowledge,
data base
mission
commands
Localization
Map Building
MotionControl
Perception
actuator
commands
environment model
local mappath
Real World
Environment
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
19/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 20
Autonomous mobile robot | we invite you to join the course
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
20/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 21
Autonomous Mobile Robots | Some recent examplesExamples not part of MOOC Video Segment
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
21/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 24
From Perception to Understanding positionglobal map
Perception Motion Control
Cognition
Real World
Environment
Localization
environment model
local mappath
Raw DataVision, Laser, Sound, Smell,
FeaturesLines, Contours, Colors, Phonemes,
ObjectsDoors, Humans, Coke bottle, car ,
Places / SituationsA specific room, a meeting situation,
Models / Semantics imposed
learned
Models imposed
learned
Navigation
Interaction
Servicing / ReasoningFunctional / ContextualRelationships of Objects
imposed
learned
spatial / temporal/semantic
Fusing&
Compressing
Information
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
22/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Laser-based outdoor navigation
Introduction | Lecture Overview 31
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
23/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
32
V-Charge | Automonous driving using close-to-market sensors
Introduction | Lecture Overview
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
24/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
33
V-Charge |Autonomous driving using close-to-market sensors
Introduction | Lecture Overview
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
25/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 34
Typical Situation
http://www.youtube.com/watch?v=wn2NfUH0G-Q
http://hamilton-baillie.co.uk
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
26/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
V-Charge Review 2 | Driving Demo
Introduction | Lecture Overview 35
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
27/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Mixed-traffic scenarios
Introduction | Lecture Overview 36
V-Charge | the ultimate vision
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
28/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Project goals Robotic help for Urban Search and Rescue
UGV and UAV combined for scene exploration
Yearly evaluation of system by firemen
Environment modeling
Online 3D mapping from laser sensor
Based on enhanced ICP released open-source Topological segmentation for human-robot interaction
Introduction | Lecture Overview 37
NIFTi Urban Search and Rescuing www.nifti.eu/
Omnicam
Rotating Laser
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
29/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Swarm of small helicopters
Vision only navigation (one camera, GPS denied)
Fully autonomous with on-board computing
Feature based visual SLAM
40
Vision only UAV navigation
Proto1
Proto2
Proto3
www.sfly.ethz.ch/
Introduction | Lecture Overview
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
30/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
41
UAV | collision avoidance and path planning
Proto1
Proto2
Proto3
Introduction | Lecture Overview
Real time 3D mapping (on-board)
optimal path planning considering localization uncertainties
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
31/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview
Solar powered fixed wing airplanes:Long duration / continuous fl ights
senseSoar Wingspan: 3 m
Wing area: 0.725 m2 Peak Solar power 140 W Power Consumption 50 W Masses:
Overall: 3.72 kg Batteries: 1.89 kg
Nominal Speed 10 m/s Sensors
Air speed IMU, GPS Camera and IR camera
AtlantikSolar Wingspan: 5.64 m
Solar area: 1.5 m2 Peak Solar power 280 W Power Consumption 40 W Masses:
Overall: 6.2 kg Batteries: 1.89 kg
Nominal Speed 10 m/s Sensors
Air speed IMU, GPS Camera
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
32/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
http://www.youtube.com/watch?v=Jql6TSyudFE
43
Efficient Walking and Running |what nature evolved (Extreme Jumpy Dog)
Introduction | Lecture Overview
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
33/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction | Lecture Overview 44
Efficient Walkingand Running | serial elastic actuation
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
34/36
|Autono mou s Mo bil e Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
precise torque control during stance
fast task space position control during swing virtual model controller for ground contact
autonomous gait discovery by stochastic optimization
StarlETH | agile, efficiency and robust
Introduction | Lecture Overview 45
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
35/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Hondas ASIMO - Advanced Step in Innovative MObility
Designed to help people in their everyday lives One of the most advanced humanoid robots
Compact, lightweight
Sophisticated walk
technology Human-friendly design
Introduction | Lecture Overview 47
Humanoid Robot: ASIMO
Video: Honda 2012
-
7/25/2019 2016 Lecture 0 Introduction and Lecture Overview
36/36
|Autono mous Mob ile Robots
Roland Siegwart, Margarita Chli, Martin Rufli
ASLAutonomous Systems Lab
Introduction |Lecture Overview 48
Beyond Mobili ty | PR2 robot from Willow Garage
Fold towels
Clean-upCourtesy of