mo va on
play

Mo#va#on' Goal:' Improve(Autonomous(Robot(Control( - PowerPoint PPT Presentation

Apr 12, 2023 •201 likes •570 views

Mo#va#on' Goal:' Improve(Autonomous(Robot(Control( Evolve'adap#ve'control:' changes'to'a'control'signal' changes'in'the'environment' changes'in'dynamics'(morphology)' Not'behaviors'

  1. Mo#va#on' Goal:' Improve(Autonomous(Robot(Control( • Evolve'adap#ve'control:' – changes'to'a'control'signal' – changes'in'the'environment' – changes'in'dynamics'(morphology)' • Not'behaviors' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 1'

  2. Mo#va#on':'Robo#c'Fish' Industrial+ Biological+ Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 2'

  3. Outline' Robo#c' Adap#ve' Velocity' Flow'Tank' Future' Fish'Design' Control' Study' Applica#on' Work' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 3'

  4. Small'Robo#c'Fish' • S#ckleback'size' – robot ':'7'cm' – real' ':'4'to'6'cm' • Electrical'components' – 32Wbit'ARM'μWcontroller' – 3Waxis'accelerometer' – 3Waxis'gyroscope' – 2'light'sensors' – 2.4'GHz'wireless' – magne#c'motor' REPLACE'PICTURE' – 1'hour'ba[ery'life' – NOT 'tethered' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 4'

  5. Design'Process' Robot+Prototype+ Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 5'

  6. Design'Process' Robot'Prototype' Dynamic+Modeling+ [Wang'2012,'Clark'2012]' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 6'

  7. Design'Process' Robot'Prototype' Dynamic'Modeling' Parameter+Iden<fica<on+ Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 7'

  8. Design'Process' Control'System' Robot'Prototype' – r ':'desired'system'output' Dynamic'Modeling' – y':'actual'system'output' – e':'system'output'error' Parameter'Iden#fica#on' – u':'control'signal' Control+Design+ r' e' u' y' Controller' System' +' _' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 8'

  9. Design'Process' Robot'Prototype' Dynamic'Modeling' Parameter'Iden#fica#on' Control'Design' Simula<on+ [Clark'2013]' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 9'

  10. Design'Process' Robot'Prototype' Dynamic'Modeling' Parameter'Iden#fica#on' Control'Design' Simula#on' Physical+Experiments+ Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 10'

  11. Design'Process' Repeat'to'refine' Robot'Prototype' – reduce'modeling'error' Dynamic'Modeling' – improve'parameter' es#mates' Parameter'Iden#fica#on' – model'noisy'sensors' Control'Design' Repeat'for'new'robot' Simula#on' – different'parameters' – different'sensors' Physical'Experiments' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 11'

  12. Outline' Robo#c' Adap#ve' Velocity' Flow'Tank' Future' Fish'Design' Control' Study' Applica#on' Work' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 12'

  13. Adap#ve'Control':'MRAC' y p' Reference' Model' _' e' y ' +' u' r' Controller' System' Adap#ve' Law' θ' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 13'

  14. ModelWFree'Adap#ve'Control' d' r' e' u' +' x' y' MFA' System' +' _' Controller' +' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 14'

  15. ModelWFree'Adap#ve'Control' d' r' e' u' x' +' y' MFA' System' Controller' +'_' +' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 15'

  16. Adap#ve'Neural'Network' Network'Ac#va#on' – feedWforward'network' – propagated'error' – sigmoid'ac#va#on' Network'Update' – minimize'error' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 16'

  17. Adap#ve'Neural'Network' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 17'

  18. Parameters' Network'values' Network'topology' – hidden'layer'bias' – number'of'input'nodes' – hidden'layer'bias'weights' – number'of'hidden'nodes' – output'layer'bias' Control'values' – output'layer'bias'weight' – gain' Learning'Values' – error'bounds' – learning'rate' – ac#va#on'period' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 18'

  19. Outline' Robo#c' Adap#ve' Velocity' Flow'Tank' Future' Fish'Design' Control' Study' Applica#on' Work' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 19'

  20. Simula#on'Study' Swim'at'a'given'(changing)'speed' Adapt'to:' – different'control'signals' – changing'fin'flexibili#es' – changing'fin'lengths' Evalua#on' – simulate'for'60'seconds'with'a'varying'control'signal' – fitness'='mean'absolute'error' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 20'

  21. UnWtuned'Parameters' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 21'

  22. Single'Trial'Evolu#on' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 22'

  23. Mul#Wtrial'Evolu#on'' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 23'

  24. Mul#Wtrial'Evolu#on'' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 24'

  25. Changing'Dynamics' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 25'

  26. Outline' Robo#c' Adap#ve' Velocity' Flow'Tank' Future' Fish'Design' Control' Study' Applica#on' Work' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 26'

  27. Sta#on'Keeping' Video'of'new'fish' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 27'

  28. SISO'to'MIMO' d 1 ' _' y 1 ' e 1 ' u 1 ' r 1' +' +' MFA' +' Controller' (frequency)' (x'accelera#on)' x 1 ' (IMU'xWaxis)' System' x 2 ' e 2 ' (y'accelera#on)' (IMU'yWaxis)' (bias)' MFA' u 2 ' +' +'_' Controller' r 2' +' y 2 ' d 2 ' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 28'

  29. SISO'to'MIMO' d 1 ' u 1 ' _' y 1 ' e 1 ' r 1' +' +' MFA' (frequency)' Controller' +' (x'accelera#on)' (IMU'xWaxis)' x 1 ' Coupler' System' Coupler' x 2 ' (y'accelera#on)' (IMU'yWaxis)' +' MFA' (bias)' e 2 ' +'_' Controller' r 2' y 2 ' u 2 ' +' d 2 ' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 29'

  30. Outline' Robo#c' Adap#ve' Velocity' Flow'Tank' Future' Fish'Design' Control' Study' Applica#on' Work' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 30'

  31. Future'Work':'HighWlevel'Control' • Higher'level'control' – FSM' – ANN' d' r' e' +' HighWlevel' u' x' y' MFA' Control' System' +'_' Controller' +' (behaviors)' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 31'

  32. Future'Work':'Failure' • When'MFA'fails' – the'error'signal'gets'to'high' – combine'with'SelfWmodeling' [Rose'2013,'Bongard'2006]' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 32'

  33. Conclusions' • Increase'adaptability'of'autonomous'robots' – control'signals,'morphology,'noise' • Decrease'modeling'effort' – evolve'online/onboard' • Help'cross'the'reality'gap'in'tradi#onal'ER' – handle'disparity'between'simula#on'and'reality' • Requires'higherWlevel'control'for'behaviors' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 33'

  34. ' The'authors'gratefully'acknowledge'the'contribu#ons'and' feedback'on'the'work'provided'by:' • Jared'Moore,'' • Jianxun'Wang,'and'' • the'BEACON'Center'at'Michigan'State'University.'' This'work'was'supported'in'part'by'Na#onal'Science'Founda#on' grants'IISW1319602,'CCFW1331852,'CNSW1059373,'CNSW0915855,' and'DBIW0939454,'and'by'a'grant'from'Michigan'State'University.' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 34'

  35. Thank'You' Ques#ons?' Robo#c' Adap#ve' Velocity' Flow'Tank' Future' Fish'Design' Control' Study' Applica#on' Work' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 35'

  36. References' [Wang'2012]':' Dynamic(modeling(of(robo:c(fish(with(a(flexible(caudal(fin .' • – In'Proceedings'of'the'ASME'2012'5th'Annual'Dynamic'Systems'and'Control'Conference,' joint'with'the'JSME'2012'11th'Mo#on'and'Vibra#on'Conference,'Ft.'Lauderdale,'Florida,' USA,'October'2012.' [Clark'2012]':' Evolu:onary(design(and(experimental(valida:on(of(a(flexible( • caudal(fin(for(robo:c(fish.(( – In'Proceedings'of'the'Thirteenth'Interna#onal'Conference'on'the'Synthesis'and' Simula#on'of'Living'Systems,'pages'325–332,'East'Lansing,'Michigan,'USA,'July'2012.' [Bongard'2006]':' Resilient(machines(through(con:nuous(selfBmodeling.( • – Science'314.5802'(2006):'1118W1121.' [Rose'2013]':'Just'Keep'Swimming:'Accoun#ng'for'Uncertainty'in'SelfW • Modeling'Aqua#c'Robots' – In'Proceedings'of'the'6th'Interna#onal'Workshop'on'Evolu#onary'and'Reinforcement' Learning'for'Autonomous'Robot'Systems,'Taormina,'Italy,'September'2013' Anthony'J.'Clark''|''ALIFE'2014':'EPS'Workshop' 36'

Recommend

More recommend