Sensor Actuator Network Michiel van de Panne Eugene Fiume - - PowerPoint PPT Presentation

▶

Nov 13, 2022 27 likes •227 views

Sensor Actuator Network Michiel van de Panne Eugene Fiume SIGGRAPH 93 stochastic synthesis of controllers sensory based - no state information non-linear network of weighted connections between a small number of binary sensors and actuators

SLIDE 1

Sensor Actuator Network

Michiel van de Panne Eugene Fiume

SIGGRAPH 93

SLIDE 2

stochastic synthesis of controllers sensory based - no state information

SLIDE 3

non-linear network of weighted connections between a small number of binary sensors and actuators (muscles) internal delays - for dynamic properites determine parameters to get desired behavior generate and test further optimization to refine controllers

SLIDE 4

planar dynamics in vertical plane proportional-erivative controllers for forces & torques binary sensor values rigid links

SLIDE 5

SLIDE 6

need fast dynamics simulator creatures are free bodies in space external ground forces use stiff spring & dampers friction, wind, viscosity are used

SLIDE 7

weighted connections in range -2:2 fully connected nodes # of hidden nodes usually = # sensor nodes

SLIDE 8

time delay fires ‘1’ if weighted input is positive

SLIDE 9

SLIDE 10

Phase 1: random generate & test evaluation metric ‘distance traveled’ for most examples can incorporate other terms average height not falling over tracking of a point-to-follow

SLIDE 11

Phase 2: Fine tuning non-linear stochatic gradient ascent or simulated annealing

SLIDE 12

SLIDE 13

SLIDE 14

SLIDE 15

SLIDE 16

SLIDE 17

SLIDE 18

SLIDE 19

SLIDE 20