Cedric Pradalier Cedric.pradalier@mavt.ethz.ch

loutclankedAI and Robotics

Nov 13, 2013 (3 years and 11 months ago)

76 views


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?