Cedric Pradalier Cedric.pradalier@mavt.ethz.ch

Zürich

Autonomous Systems Lab


Cedric Pradalier

Cedric.pradalier@mavt.ethz.ch


ICRA Workshop on Planetary Rovers, May 2010

Zürich

Autonomous Systems Lab

2

Welcome to Anchorage

Zürich

Autonomous Systems Lab

3

Outline


Autonomous Systems Lab



Brief summary of the space
-
related activities



Hardware platforms

◦
Eurobot EGP Prototype

◦
ExoMars breadboard



Embedded Software

◦
Lowering friction requirements using optimised torque distribution

◦
Learning what’s come ahead

Zürich

Autonomous Systems Lab

4


Lab of Pr. Siegwart

◦
www.asl.ethz.ch

◦
ETH Zürich
–

Switzerland

◦
20 PhD / 40 Total



Education

◦
Lectures:

Bachelor / Master

◦
Project supervision



Research

◦
Vision:

Create machines that know what they do

◦
Three research line:


The design of robotic and mechatronic systems


Navigation and mapping


Product design methodologies and innovation

Autonomous Systems Lab


Zürich

Autonomous Systems Lab

Overview, Crab,

Eurobot EGP Prototype

Exomars Breadboard

Zürich

Autonomous Systems Lab

6

◦
Micro Air Vehicles

◦
Walking and Running

Quadruped Robots

◦
Service Robots

◦
Autonomous Robots/Cars

for Inner City Environments

◦
Inspection Robots

◦
Space Robots for Planetary

Exploration

◦
Autonomous sailing/electric

boats

ASL
–

ETH Zurich

Zürich

Autonomous Systems Lab

7


Nanokhod





Shrimp & Solero

◦
Passive suspension

systems

◦
6 motorized wheels

◦
2 steering


◦
Very good terrainability!



ASL rovers background

Zürich

Autonomous Systems Lab

8


RCL
-
E






RCL
-
C






CRAB

Exomars: Pre
-
study phase A

Zürich

Autonomous Systems Lab

9


Platform

◦
Passive suspension

◦
6 Motorized wheels

◦
4 Steering





Mobile robots

◦
Confronted to environments

which are unknown

◦
Difficulty to:


Model before
-
hand the

environment of the rover.


Predict its terrain interaction

characteristics.




CRAB rover

Zürich

Autonomous Systems Lab

10

ExoMars Breadboard

Zürich

Autonomous Systems Lab

11

ExoMars Breadboard

Zürich

Autonomous Systems Lab

12


Authorization denied…

Test plan and results

Zürich

Autonomous Systems Lab

13



Eurobot:

◦
Multi
-
arm astronaut assistant

◦
Developed by Thales (and others?) for ESA



EGP = Eurobot Ground Prototype

◦
Put some wheels and perception under the Eurobot

◦
Experiment on the concept of an astronaut assistant

EGP Rover Prototype

Picture from Didot et al. IROS’07

Zürich

Autonomous Systems Lab

14



Ability to carry and power Eurobot (150Kg)


Ability to transport an astronaut in full EVA (100Kg)


Power autonomy for multiple hours, fast recharge

◦
150kg of lead
-
acid batteries


Ability to perceive its surrounding, plan path, follow an astronaut, using a stereo
-
pair


Rough terrain capabilities (15 deg slopes, 15cm steps)


Cheap !!!


EGP Rover
–

Requirements

Zürich

Autonomous Systems Lab

15

Mechanical design

Zürich

Autonomous Systems Lab

16

Mechanical design

Zürich

Autonomous Systems Lab

17

Implementation

Zürich

Autonomous Systems Lab

18

Suspension

Zürich

Autonomous Systems Lab

19

Integration

880kg, without astronaut…

Zürich

Autonomous Systems Lab

20

Integration


Zürich

Autonomous Systems Lab

Optimised Torque Control

Learning what comes ahead

Zürich

Autonomous Systems Lab

22

Optimised torque control


Principle

◦
It is possible to put more torque on
wheel with more load


Requirements

◦
Measurement of contact point on each
wheel


◦
Static model to deduce the wheel load
from the contact points and the rover
state


Results submitted to IROS’10

Zürich

Autonomous Systems Lab

23

Control loop

Zürich

Autonomous Systems Lab

24

Test setup and hardware

Zürich

Autonomous Systems Lab

25

Results

Zürich

Autonomous Systems Lab

26

Results


Zürich

Autonomous Systems Lab


Ambroise Krebs

ambroise.krebs@mavt.ethz.ch


Zürich

Autonomous Systems Lab

29


Two types of sensors needed

◦
Remote sensors
→

Remote Terrain Perception data

◦
Local sensors
→


Rover
-
Terrain Interaction data


Data association


Prediction

◦
What are the Rover
-
Terrain Interaction characteristics?

Approach: Basic concept

?

Zürich

Autonomous Systems Lab

30

Delay

Approach: Architecture overview


RTILE

Rover
-
Terrain Interactions Learned from Experiments

SOFTWARE

HARDWARE

Actuators

Controller

Path Planning

Prediction

Learning

Database

ProBT

Near to far

Local Sensors

Remote Sensors

Obst. Det.

Trafficability & Terrainability

Traversability

Zürich

Autonomous Systems Lab

31

Outline

SOFTWARE

HARDWARE

Actuators

Controller

Path Planning

Prediction

Learning

Database

ProBT

Near to far

Delay

Local Sensors

Remote Sensors

Obst. Det.

Zürich

Autonomous Systems Lab

32


Data acquisition: 2D example










Grid based approach

◦
Remote


Image acquisition

◦
Local


Position of the wheels

◦
Samples


When learning occurs

Near to far

Samples

can be used for the learning mechanism.

Remote

Local

Features association

Zürich

Autonomous Systems Lab

33

Bayesian model


Goal

◦
Local features predicted based on remote features




Bayesian model

◦
Joint distribution and decomposition

◦
Introduce abstraction classes and




Question


→

Class association

Local classification

Remote classification

Zürich

Autonomous Systems Lab

37

Outline

SOFTWARE

HARDWARE

Actuators

Controller

Path Planning

Prediction

Learning

Database

ProBT

Near to far

Delay

Local Sensors

Remote Sensors

Obst. Det.

Zürich

Autonomous Systems Lab

38

Prediction


Process

Remote Subspace

Local Subspace

F
r

= 0.5

Prediction

20%

50%

30%

Zürich

Autonomous Systems Lab

39


Path planner
–

E*

◦
Wavefront propagation


Navigation function

◦
Gradient descent

◦
Propagation cost





Process




Adaptive navigation

assumption

T

= 1

Image acquisition

F
l

prediction

Propagation costs

Zürich

Autonomous Systems Lab

40

Outline

Zürich

Autonomous Systems Lab

41


Rover
-
Terrain Interaction metric

◦


◦
The smaller, the better


Remote feature space

◦
Camera

◦
Color description



Trajectory adaptation



Absolute cost method

◦
Idea of tradeoff between


What can be gained in terms of , meaning


The deviation it imposes from the default trajectory

◦
Dynamically adapts to the terrain representation



Propagation costs function

Very bad

Very good

Good

Start

Goal

?

Zürich

Autonomous Systems Lab

42

RTILE: Results


Adaptive navigation


Test environment in Fluntern

◦
3 terrains


Grass


softest

(best)



Tartan


Asphalt


hardest (worst)

•
Automatically driven

•
6 cm/s

•
No prior

•
Learning every 6 m

Zürich

Autonomous Systems Lab

43

RTILE: Results
“
complete
´



Test of the complete approach

Waypoints

x [m]

y [m]

0

0.0

0.0

1

15.0

0.0

2

15.0

-
15.0

3

0.0

-
15.0

4

0.0

-
2.5

5

12.5

-
2.5

6

12.5

-
15.0

Zürich

Autonomous Systems Lab

45

Summary


RTILE: Rover
-
Terrain Interactions Learned from Experiments

◦
End
-
to
-
end approach


Online learning


Navigation adapted accordingly


Integrated within the CRAB platform


◦
Tradeoff distance vs M
RTI


20% M
RTI

improvement


10% longer distance


◦
Terrain description


Consistent interaction with E*


Dynamical adaptation of the propagation costs

RTILE improves the rover behavior

Zürich

Autonomous Systems Lab

46

Future work


Improvements

◦
Add feature spaces (subspaces) for a better terrain description

◦
Use additional sensors


Local:


Tactile wheels, Microphones, and so on
…


Remote:


Google earth map (
increase FOV
), Lidar

◦
Improved features


Remote:


Fourier based, Co
-
occurrence matrix, and so on
…

◦
Learning


Clustering step (GWR)



Outlook

◦
Energetic description

◦
Learn as well the behavior of the rover

Zürich

Autonomous Systems Lab

47

Questions?