robotic mapping: an architectural approach

Robotic Mapping:

an architectural approach

S. Bonetti - F. Fiamberti - D. Micucci - F. Tisato D.I.S.Co. University of Milano-Bicocca - Italy

1

D I P A R T I M E N T O

D I I N F O R M A T I C A

S I S T E M I S T I C A

E C O M U N I C A Z I O N E

D I P A R T I M E N T O

D I I N F O R M A T I C A

S I S T E M I S T I C A

E C O M U N I C A Z I O N E

The problem

Building an environment map by means

of a mobile entity based on low-cost

sensors

Low-cost sensors have limited accuracy,

precision and efficiency

2

Our idea

• Use of multiple, heterogeneous sensors

• «smart» management of sensor

activations in a context-aware

approach

3

Our approach

• Our idea has been reified in a modular

architecture which carefully separates the

activities of:

Sensing

Integration

Planning

Control

4

Our prototype

• Directionable Laser Range Finder

• RGB Camera 5

It contextualizes data produced by the associated physical sensor as an occupancy map

SOM: Sensor Occupancy Map

SOM

Map Update

Data

Acquisition

Raw Data

ActivityInitial

ActivityFinal

Sensor Component

cell i j = P H sn

Real environment Occupancy map

6

Sensor Component

Laser orientation

Entity frame of reference

World frame of reference

7

SOM

Map Update

Data

Acquisition

Raw Data

ActivityInitial

ActivityFinal

Sensor Component

Entity frame of reference

World frame of reference

Camera FOV

Edge

8

SOM

Map Update

Data

Acquisition

Raw Data

ActivityInitial

ActivityFinal

WOM (World Occupancy Map) generated by fusing

several SOMs

World Map Builder

9

It integrates and fuses environment representations from different

sensors producing a single environment map

WOM WRMAnalysis &

Planning

It implements the application strategy for the map construction

WRM (World Relevance Map)

Application Strategy

Low relevance High relevance

10

It manages the activation of the associated sensor by evaluating

a trade-off between activation costs and benefits.

SCM (Sensor Cost Map)

– It spatially contextualizes the computational cost (either

static or dynamic) of activations of the associated sensor

SAP (Sensor Activity Planner)

Infinite cost Low cost High cost 11

Camera FOV

SAM (Sensor Attractiveness Map)

– It defines the areas that must be analyzed by the

associated sensor


12

Attractive cell

SOM

Map Update

Raw Data

SAM Analysis

Data Acquisition

SAM

ActivityInitial

ActivityFinal

ActivityInitial

Identification of

Interesting AreasWRM

*

Grid Cell

Coordinate

Sensor Activity

Planification

ActivityFinal

SCM


SOM WRM SCM

SAM

13

SC SAP

Virtual SC

Sensor Component

Virtual Sensor Component

14

SOMMap Update

Data Acquisition

SAM AnalysisSAM

ActivityInitial

ActivityFinal

SCM

Raw Data

SOMMap Update

SOM Analysis and

Processing

SAM AnalysisSAM

ActivityInitial

ActivityFinal

SCM

SOM

Complete architecture

Application

Strategy

World

Map Builder

Sensor

Activities

Planner

Sensor

Component

SAM SCM SOM

Virtual

Sensor

Component

Sensor

Activities

Planner

SAM SCM SOM

Sensor

Activities

Planner

Sensor

Component

SAM SCM SOM

WOM WRM

15

…

…

…

…

A first implementation

Application

Strategy

World

Map Builder

Sensor

Activities

Planner

Sensor

Component

SAM SCM SOM

Sensor

Activities

Planner

Sensor

Component

SAM SCM SOM

WOM WRM

16

A concrete example

Start-up situation

WOM WRM

Laser SOM Camera SOM 17

Activation of both

sensors and update of

the corresponding SOMs

WOM WRM

Laser SOM Camera SOM

A concrete example

18

Update of the world

model and relevance

map

WOM WRM


A concrete example

19

Activation of the laser

sensor

WOM WRM


A concrete example

20

Update of the world

model and choice of a

new strategy

WOM WRM


?

A concrete example

21

Conclusions and comments

• The proposed architecture is:

– Scalable

– Modular

– Open

– Independent of application strategies

• Future developments:

– Extensive experimentations

– Integration with additional sensor typologies

– Application to real-life cases

22

Questions & Answers

• Q1 : what are the problems of software development in robotics that can be considered "solved"?

Allowing for the application of low-cost/low-performance sensors to the

problem of robotic mapping. In fact, such a problem is known to involve large

amounts of data to be elaborated and fused.

• Q2 : what are the solutions to these problems that can be considered best

practice and why?

Separation of concerns, which allows to dominate the problem’s complexity by decomposing the system in sub-components.

• Q3 : to what extent the solutions to these problems are robotic-specific?

The approach is general and should be used every time a system is made of

multiple activities. The specific approach is aimed at solving a robotic-specific

issue.

24

Questions & Answers

• Q4 : what problems of software development in robotics remain to be solved?

The definition of a sensible strategy for every decisional component.

• Q5 : why state-of-the art software technology is not adequate to solve these

problems?

To the knowledge of the authors, no solutions to the robotic mapping problem

exist which exploit both an architectural approach and the use of low-cost

sensors.

• Q6 : what are the promising research directions to solve the open problems?

Performing thorough experimentations to test the validity of the approach

and devise correct strategies for the decisional components.

25

robotic mapping: an architectural approach

Documents