Embedded Systems for Evolutionary Robotics

1
Embedded Systems forEvolutionary Robotics
Hod Lipson Mechanical Aerospace
Engineering Computing Information
Science Cornell University
2
The design process of nature

• Biology provides inspiring designs
• We can mimic these principles in machines
• Vision, Control, Sensing, Actuation, Structure
• But these principles are a result of unique
  biological constraints
• Instead, mimic the design process itself
• The evolutionary process that lead to these
  designs

3
Evolutionary Robotics

• Evolutionary Computation methods applied to
  design of autonomous machines
• Morphology control
• Why?
• Augment human design process
• Automate autonomous adaptation
• design in-situ
• May shed light on animal adaptation

4
A simple evolutionary process
Genotype (e.g. DNA)
Phenotype (body brain)

• Initialize a population of machines
• Repeat
• Evaluate (test)
• Select (e.g. by fitness)
• Replicate (e.g. duplication)
• Vary (e.g. mutation)
• Until good solutions found

01011010010
10010101010
11101011101
10101001000
00100101001
00010111101
11111001001
11010101001
5
Example Evolving brains
6
A gradient-Following brain
Bongard et al (2002)
7
(No Transcript)
8
Camera View
Camera
9
Nonaped
Zykov Lipson (2004)
10
Nonaped
Zykov Lipson (2004)
11
Alternative Body Plans
12
Compare Evolvability of Body Plans
13
Evolving controllers with some morphological
parameters
Paul et al (2001)
Paul Bongard (2002)
14
Evolving Bodies and Brains

• Genetic operators small mutations
• Connect/remove small bar or unconnected neuron
• Change bar length or neuron synapse
• Split bar/vertex
• Connect/disconnect neuron to bar (actuator)

15
Evolving for Locomotion

• Population Starts with empty/null designs. Size
  200 1000 machines
• Genotype/phenotype bars/actuators, and neurons
• Fitness function distance center of mass moved
  during 12 cycles of the neural net
• Selection function fitness proportionate
• Genetic operators small mutations
• Connect/remove small bar or unconnected neuron
• Change bar length or neuron synapse
• Split bar/vertex
• Connect/disconnect neuron to bar (actuator)
• Replacement function random.
• Evolution dynamics Steady state 100 10000
  generations. Various dynamics of convergence and
  divergence. Parallel implementation yields
  natural evolution drive for simplicity

16
Phylogenetic Trees
Hod Lipson Evolutionary Design
17
Evolved Bodies Brains
Lipson Pollack (2001)
18
Evolved Bodies Brains
19
Transfer to realityUsing 3D Printer
20
Evolving in simulation
Simulator
Evolve Controller In Simulation
Download
Try it in reality!
21
Evolving in simulation
Evolve Controller In Reality
Try it !
22
Evolving in simulation
Simulator
Co-Evolution
Evolve Controller
Evolve Simulator
Download
Try it in reality!
Collect Sensor Data
23
Analysis for Synthesis
With Victor Zykov, Josh Bongard and Nicolas
Esteves
24
Autonomous diagnosis repair

Recovery Actions

Diagnosti
c
Models

Diagnostic Actions

Initialize
candid
ate

Initialize
diagnosis
Initialize
candidate

recovery actions

with
model pool
with
diagnosis actions

with
possible actions

available models

possible actions

Test model predictions
Update

Models

Test model predictions
for each candidate action

Using
Data

for each candidate action

Update actions to achieve
Make Predictions

Update actions to
recovery
in
consensus

generate
disagreement

among model predictions

among model predictions

Collect Sensor Data

Select action with
Select action with
acceptable worst
-
case
acceptable worst
-
case
safety

safety

Compare to predictions
to actual data, eliminate
and refine models

Perform action on target
Perform action on target
system

system

25
More diagnostics Environment
With Josh Bongard
26
Parametric morphological estimation
27
PC104 Embedded legged platform
28
Evolutionary Robotics

• Evolutionary search for
• Evolve bodies brains
• Design automation
• In-Situ adaptation
• Understanding biological adaptation
• Challenges
• Crossing the reality gap
• Approach
• Co-evolve simulator with controller
• Enabled by sufficient on-board CPU for
  self-simulation