Multi-Agent Systems on Arduino & iOS

Multi-Agent Systems (MAS) is one type of Artificial Intelligence used in computing. In this presentation I am explaining how they can be used to control Arduino Robot.

This slides were presented on my presentation "Multi-Agentní Systémy - vybudujme si populaci na stole či v kapse!" at DevFest 2014 (more info at http://devfest.cz/program/)

Video from my lecture (in czech language) is accessible here: https://youtu.be/JIGxJtDX2fA?list=PLcyrRW-49oISXNKAbmTu2hd19QPzvvNVE

Transcript

1. Tomáš Jukin @Inza Multi-Agent Systems on Arduino & iOS
2. Znáte Half-Life?
5. Table
7. Robot
11. Tomáš Jukin @Inza www.juicymo.cz @JuicymoCZ
12. Tomáš Jukin @Inza
13. Tomáš Jukin @Inza #MachineRoom at #DevFestCZ MachineRoom
15. Movement Agent
16. Movement Agent Turning Agent
17. Movement Agent Turning Agent Border Agent
19. When to use MAS? And for what?
20. When to use MAS? “When the solution is complex algorithm …”
21. When to use MAS? “… which is difficult / impossible to design or code”
22. When to use MAS? Lets split complex behavior to simple agents
23. HOW to use MAS? A) MANY agents in ONE robot form population of ONE robot ! B) ONE agent per ONE robot form population of MANY robots
24. A) MANY agents per robot ! B) ONE agent per robot, 
 MANY robots HOW to use MAS?
25. A) MAS controls one robot ! B) MAS controls MANY robots HOW to use MAS?
26. Today I will talk about A) MANY agents in ONE robot form population of ONE robot MAS controls one robot HOW to use MAS?
27. When to use MAS? Agents do not need to know HOW to solve the problem
28. When to use MAS? Let them accumulate money instead ;) (for example)
29. When to use MAS? Let the emergence do the dirty work for us!
30. Any dangers? Emergence is not a cute girl…
31. To tune it properly can be tricky…
32. Examples? Airplane navigation Robot control Network diagnostics Predictive systems Simulations Computer Games AI
33. MASculptor Leden 2014 Objective-C Open Source
34. MASculptor example screenshots, few info iOS agnostic demo iOS6 only
35. Swift
36. What is an agent?
37. Co je to agent? Agent je entita zkonstruována za účelem kontinuálně a do jisté míry autonomně plnit své cíle v adekvátním prostředí na základě vnímání prostřednictvím senzorů a prováděním akcí prostřednictvím aktuátorů. Agent přitom ovlivňuje podmínky v prostředí tak, aby se přibližoval k plnění cílů. “ ”
38. Co je to agent? Agent je entita zkonstruována za účelem kontinuálně a do jisté míry autonomně plnit své cíle v adekvátním prostředí na základě vnímání prostřednictvím senzorů a prováděním akcí prostřednictvím aktuátorů. Agent přitom ovlivňuje podmínky v prostředí tak, aby se přibližoval k plnění cílů. “ ”
39. Co je to agent? Agent Prostředí Senzory Aktuátory
40. Co je to agent? Agent Prostředí Senzory Aktuátory Vnitřní architektura Znalostní báze Řídíci jednotka
41. Rozdíl je ve vnitřní architektuře Agent Prostředí Senzory Aktuátory Vnitřní architektura
42. Naive (communicating) agent Reactive agent Deliberative (planning) agent Hybrid agent (reactive + planning)
43. performReasoning() { // ... } WorldState1 -> Action1 WorldState2 -> Action2 WorldState3 -> Action3 else -> idle Behavior Pattern Table Abstract Method Desire > Goal > Intents > Plan > Steps 1) Generate (choose) Plan 2) Execute Reactive + Deliberative WorldState1 -> Action1 WorldState2 -> Action2 WorldState3 -> Action3 else -> Deliberative 1) Generate (choose) Plan 2) Execute
44. What is an MAS?
45. What is MAS? Multi-Agent System is a system which uses group or population of agents interacting with environment in order to achieve global goal. Typically individual agents do not have a clue about the global goal. They have their own goals. The global goal is achieved by emergence.
46. What is MAS? Multi-Agent System is a system which uses group or population of agents interacting with environment in order to achieve global goal. Typically individual agents do not have a clue about the global goal. They have their own goals. The global goal is achieved by emergence.
48. #Probee Robot
49. #Probee Robot 3x UltraSonic Sensor (Forward / Backward / Turret) 4x DC Motor 1x Motor Controller (Left / Right) 1x Arduino UNO (= brain) 1x Bluetooth Module 1x 2x16 I2C LCD (= status display)
50. MachineRoom
51. How our MAS in #Probee Robot works?
52. MAS in #Probee Robot Written in Wiring/Processing (C dialect) Running on 8bit processor 32KB program memory, 2KB RAM
53. Concurrency vs. Parallelism
54. Parallelism time →
55. Parallelism Agent 1 Agent 2 Agent 3 time →
56. Parallelism Agent 1 Agent 2 Agent 3 How much work can be done in parallel? ! Every agent… time →
57. Concurrency time →
58. Concurrency time → Agent 1 Agent 2 Agent 3
59. Concurrency time → Agent 1 Agent 2 Agent 3 How much work is actually computed in parallel? ! Only one (serialization)
60. MAS in #Probee Robot Written in Wiring/Processing (C dialect) Running on 8bit processor 32KB program memory, 2KB RAM
61. MAS in #Probee Robot Written in Wiring/Processing (C dialect) Running on 8bit processor 32KB program memory, 2KB RAM Parallelism 4
62. MAS in #Probee Robot Written in Wiring/Processing (C dialect) Running on 8bit processor 32KB program memory, 2KB RAM Parallelism 4 Concurrency 1 (serialization)
63. MAS in #Probee Robot Written in Wiring/Processing (C dialect) Running on 8bit processor 32KB program memory, 2KB RAM Parallelism 4 Concurrency 1 (serialization) Agents 4
65. A1 Stopper Agent
66. A1 Stopper Agent A2 Communicating Agent
67. A1 Stopper Agent A2 Communicating Agent A3 Planner Agent
68. A1 Stopper Agent A2 Communicating Agent A3 Planner Agent A4 Movement Agent
69. Stop when collision would happen Connect with user (send sensor data, receive motor data) “Plan” the next action Control movement based on orders from A2/A3
70. A1 Stopper A2 Communicator A3 Planner A4 Mover Environment Sensors Actuators Sensors Actuators Sensors Actuators Sensors Actuators
71. A1 Stopper A2 Communicator A3 Planner A4 Mover Sensors Actuators Sensors Actuators Sensors Actuators Sensors Actuators Environment Blackboard Motors Bluetooth a1_vars a2_vars a4_vars Ultrasonic Sensors a3_vars
74. MAS run even on places you do not expect! M
75. Anyone can make Software, try Hardware as well! A
76. Seize the opportunity and make your MAS today! S
78. M
79. A M
80. S A M
81. S A MAS run even on places you do not expect! M
82. S Anyone can make Software, try Hardware as well! A MAS run even on places you do not expect! M
83. Seize the opportunity and make your MAS today! S Anyone can make Software, try Hardware as well! A MAS run even on places you do not expect! M
84. Interested? Build or Implement YOUR own MAS! You can start right now… …with any language… …or on Arduino!
85. Questions?
86. Tomáš Jukin @Inza www.juicymo.cz @JuicymoCZ
87. Photo Credits All photos used are CC from Flickr !