Você está na página 1de 32

Bio Inspire Robotics

Controlling Mobile Robots


with Distributed
Neuro-Biological Systems
Presented By
Sima R. Katre
Guided By
Prof. R. Harinkhede
Introduction

Behavior

How it work

Applications

Future Work

Conclusion


Contents
Bio inspired design.
Learning from Nature and apply.
Biomimicry.
Neuro-Biological system.
Artificial Neuro Network is use in Robotics.
Introduction
Neuroethological robotic systems
Super Robots
Incorporate extensive
processing capabilities
Bulky
Expensive


Inexpensive Robots
Smaller and inexpensive robots
connected to a network of
processing nodes
Concerns
Real-time performance
Unpredictable communication
environment affects robot
performance
Biologically Inspired Robotic Systems
Nature has always been a source of inspiration in the
development of autonomous robotic systems
Ethology
Animal behavior-based simulation
Interaction with the environment is usually oversimplified
Lack of strong biological basis for their working assumptions
Lack of any formal underpinnings for the simulation results

Neuroethology
behavior related to neurobiological structure
Replicate brain models to provide credible and general animal behavior
Provide inspiration for further robotics architectures
More complex and accurate than ethology systems
Enable experimentation
Experimentation requires real-time performance


Neuroscience
(Experiments)
Robotics
Brain Theory
(Modeling)
New Hypothesis
Gaps in Knowledge
Data, Hypotheses
Formal Models
New Ideas
(Results from
Experiments with
Physical Devices)
New Hypotheses

Research Cycle
Structure of the Talk
1. Neuroethological Modeling
Study animal behavior and corresponding neural structure
as inspiration to robotic architectures
2. Embedded Mobile Robots
Develop distributed wireless robot architectures capable of
efficient neural processing
3. Internet Based Robotics
Enable remote robot task development and
experimentation
Neurological Modeling
Neuroproshtesis
Brain Computer Interface
Visual Prosthesis
Photoreceptor
Neural Network
Neuron Network
Distributed
Snapshot
Remote
Creation
Directory
Services
Replication
Migration
DGC
Check-
pointing
Access
Control
System (Meta) Level
Application (Base) Level
mp
neuron
s
mf
input
output
mp - membrane potential : dmp(t)/dt = f(s,mp,t)
mf - firing rate : mf(t) =s(mp(t))
Leaky Integrator : t dm(t)/dt = -m(t) + s
Neuron Model
Axon
Neuron
Dendrite
Soma
Synapse
Spine
Synaptic
Cleft
Axon
Terminal
Receptor
Interacellular
Element
Vescicle
Calcium
Mechanism
NMDA
Receptor
AMPA
Receptor
Pump
Diffusion
Channel Buffer
Dendrites
Axon
Synapses
Soma
Neuron (detailed)
.
Power circuit
LCD Display
sensor
Micro
controller
Motor control
unit
Application Of ANN
PS
Mate
Mate-Pair
S
PS
Prey
Prey-Acq
S
PS
Pred
Pred-Av
S
Moving-Object
S
PS
NMO
Find-Loc
S
Non-Moving-Object
S
PS
MO
+ +
+
-
- -
Perceptual Schema (PS)
Main Schema (S)
Behavior:
Frog and Toad - Rana Computatrix [Arbib 1987, Cervantes 1990]
Mobile visual stimulus
in lateral visual field
(monocular perception)
Mobile visual stimulus
in binocular visual field
(short distance)
Mechanic stimulus
in mouth and pharynx
receptors
Orientation
Binocular
fixation
Attack
Snap
Clean
Stimulus Response
Behavior:
Toad Prey Acquisition [Cervantes 1985]

R4
Visual
R1-R2
R3
Retina
Tectum
PreTectum/Thalamus
Motor Heading Map
Static Object
Recognizer
Prey Recognizer
TH10
T5_2
Static Object
Avoidance
Prey Approach
Forward
Orient
Sidestep
Backward
Tactile
Schema Level
Neural Level
Moving Stimulus Selector
R1-R2
R3
R4
MaxSelector
Predator
Recognizer
Predator Avoid
R1-R2
R3
R4
Depth
Stereo
Neural based Behavior :
Toad Prey Acquisitions and Predator Avoidance
Time consuming processes are carried out in the
(neural) computational system
Neural processing
Image processing

Limited task are carried out in the robot hardware
Sensory input
Motor output
Default behavior


Communication and data transformation is managed by
the adaptive middleware
Embedded Mobile Robots:
Distributed Embedded Architecture
motor motor
servo
camera
CPU
(OOPic)
Transceiver
Power stage
Frame Grabber
Sensors
(tact)
Transceiver PC
Remote Computaional System
Robot
Wireless
Embedded Mobile Robots:
Distributed Embedded Architecture
NSL NSL
NSL NSL
NSL NSL
NSL NSL
ASL ASL
ASL ASL
Video
Server
Video/
Image
Processing
camera
Robot
Wireless
Remote Computational System
Tactile
Server
Motor
Server
tactile
motor
t
r
a
n
s
c
e
i
v
e
r

t
r
a
n
s
c
e
i
v
e
r

NSL Neural Simulation Language
ASL Abstract Schema Language
Embedded Mobile Robots:
Distributed Embedded Architecture
Schema Level 1
data in
data out
Other Processes
Schema Level 2
Schema Level
Neural Level
.
.
.

.
.
.

.
.
.

.
.
.

din
1
din
n
dout
1
dout
m
Schema
Neural
Schema Computational Model

Protocol
Oracle
ARM manager
Protocol
(un)installer
Protocol
loader
Secure compressed
video capture
Security
Protocol
Compression
Protocol
Timeliness
Protocol
set of
protocols
Robots
resident
ARM
Adaptation
Profiler
Battery
Monitors
Communication Performance Monitor
Adaptation
Repository
Communication Manager
Adaptation Manager
Communication Requirement
Protocol
Oracle
Protocol
Oracle
ARM manager
Protocol
(un)installer
Protocol
loader
Secure compressed
video capture
Secure compressed
video capture
Security
Protocol
Compression
Protocol
Timeliness
Protocol
set of
protocols
Robots
resident
ARM
Adaptation
Profiler
Battery
Monitors
Communication Performance Monitor
Adaptation
Repository
Adaptation
Repository
Communication Manager
Adaptation Manager
Communication Requirement
ARM: Example
Video capture
Video processing
Model simulation
Model output
Navigation control
(d ,
r
,
c
)
Embedded Mobile Robots:
Processing cycle
Experimental Results: 2 Preys
(A)
(B)
(C) (D)
Embedded Mobile Robots:
Experimental Results: Prey Acquisition with 10 cm Barrier

(A)
(B) (C) (D)
(E)
(F) (G) (H)
Embedded Mobile Robots:
Experimental Results: Prey Acquisition with 20 cm Barrier

Autonomous Robot 1
Autonomous Robot N
I
n
t
e
r
n
e
t

Wireless
Internet
Server
.
.
.

.
.
.

.
.
.

Remote
Computaional
System
Instance 1
Instance N
Remote
Computational
System
Embedded Mobile Robots:
Distributed Embedded Architecture
Sensors Actuators
Vision
Tact
Legs
Wheels



LEGO
OOPIC
Embedded Mobile Robots:
Robot Hardware
Neuroscience:
Autonomous Biological Agents
Sensors Actuators
Vision
Sound
Smell
Touch
Legs
Wings
Fins


Robotics:
Autonomous Robotic Agents
Sensors Actuators
Vision
Sound
Smell
Touch
Legs
Wings
Fins
Wheels



Applications
Actor in Biological Experiments.
Pest Companies.
Bouncer for preventing Birds Trespassing.
Farmlands.
Future Work

Complete Internet based System
Develop middleware adaptation capabilities
Build smaller robotic systems
Extend to multiple robot tasks
Extend vision system to true moving forms
Extend biological models

Biological inspired mobile robots is one of the best
technology which gives a special and better
enhancement to robotics technology.
It is an more advance technology which is for mobile
robots , it gives a better performance capability to the
mobile robotics technology
As there is concepts of neurons for biological inspired
robotics , this is very flexible and advance robotics
achieve by neuroethology.
Conclusion

Você também pode gostar