1. 16.412J/6.835 Intelligent Embedded Systems Prof. Brian Williams Rm 37-381 Rm NE43-838 Williams@mit.edu Prof. Brian Williams Rm 37-381 Rm NE43-838 Williams@mit.edu MW 11-12:30, Rm 33-418

2. Outline Course Objectives and Assignments Types of Reasoning Kinds of Intelligent Embedded Systems A Case Study: Space Explorers Course Objectives and Assignments Types of Reasoning Kinds of Intelligent Embedded Systems A Case Study: Space Explorers

3. Course Objective 1 To understand fundamental methods for creating the major components of intelligent embedded systems. Accomplished by:  First ten lectures on basic methods  ~ 5 problem sets during the first ten lectures to exercise basic understanding of methods. To understand fundamental methods for creating the major components of intelligent embedded systems. Accomplished by:  First ten lectures on basic methods  ~ 5 problem sets during the first ten lectures to exercise basic understanding of methods. Plan Execute Monitor & Diagnosis

4. Basic Method Lectures Decision Theoretic Planning Reinforcement Learning Partial Order Planning Conditional Planning and Plan Execution Propositional Logic and Inference Model-based Diagnosis Temporal Planning and Execution Bayesian Inference and Learning More Advanced: Graph-based and Model-based Planning Combining Hidden Markov Models and Symbolic Reasoning Decision Theoretic Planning Reinforcement Learning Partial Order Planning Conditional Planning and Plan Execution Propositional Logic and Inference Model-based Diagnosis Temporal Planning and Execution Bayesian Inference and Learning More Advanced: Graph-based and Model-based Planning Combining Hidden Markov Models and Symbolic Reasoning

5. Course Objective 2 To dive into the recent literature, and collectively synthesize, clearly explain and evaluate the state of the art in intelligent embedded systems. Accomplished by:  Weekly thought questions (~ 2 page answers)  Group lecture on advance topic  45 minute lecture  Short tutorial article on method 1-3 methods  Demo of example reasoning algorithm  Groups of size ~3. To dive into the recent literature, and collectively synthesize, clearly explain and evaluate the state of the art in intelligent embedded systems. Accomplished by:  Weekly thought questions (~ 2 page answers)  Group lecture on advance topic  45 minute lecture  Short tutorial article on method 1-3 methods  Demo of example reasoning algorithm  Groups of size ~3.

6. Course Objective 3 To apply one or more reasoning elements to create a simple agent that is driven by Goals or Rewards Accomplished by:  Final project during last third of course  Implement and demonstrate one or more reasoning methods on a simple embedded system.  Short final presentation on project.  Final project report. To apply one or more reasoning elements to create a simple agent that is driven by Goals or Rewards Accomplished by:  Final project during last third of course  Implement and demonstrate one or more reasoning methods on a simple embedded system.  Short final presentation on project.  Final project report. Plan Execute Monitor & Diagnosis

7. Outline Course Objectives and Assignments Types of Reasoning (Slides compliments of Prof Malik, Berkeley) Kinds of Intelligent Embedded Systems A Case Study: Space Explorers Course Objectives and Assignments Types of Reasoning (Slides compliments of Prof Malik, Berkeley) Kinds of Intelligent Embedded Systems A Case Study: Space Explorers

8. Agents and Intelligence Prof Malik, Berkeley

9. Reflex agents Compliments of Prof Malik, Berkeley

10. Reflex agent with state Compliments of Prof Malik, Berkeley

11. Goal-oriented agent Compliments of Prof Malik, Berkeley

12. Utility-based agent Compliments of Prof Malik, Berkeley

13. Outline Course Objectives and Assignments Types of Reasoning Kinds of Intelligent Embedded Systems A Case Study: Space Explorers Course Objectives and Assignments Types of Reasoning Kinds of Intelligent Embedded Systems A Case Study: Space Explorers

14. Immobile Robots: Intelligent Offices and Ubiquitous Computing

15. Ecological Life Support For Mars Exploration

16. courtesy NASA The MIR Failure

17. courtesy NASA Ames

18. MIT Spheres courtesy Prof. Dave Miller, MIT Space Systems Laboratory

19. courtesy JPL Distributed Spacecraft Interferometers to search for Earth-like Planets Around Other Stars

20. courtesy JPL ``Our vision in NASA is to open the Space Frontier... We must establish a virtual presence, in space, on planets, in aircraft and spacecraft.’’ - Daniel S. Goldin, NASA Administrator, May 29, 1996 A Goldin Era of Robotic Space Exploration

21. Cooperative Exploration Distributed Planning Group, JPL Model-based Embedded and Robotic Systems Group, MIT

22. MIT Model Based Embedded and Robotics Group Autonomous Vehicles Testbed

23. Robotic Vehicles ATRV Rovers Monster Trucks Blimps Spheres Simulated Air/Space Vehicles ATRV Rovers Monster Trucks Blimps Spheres Simulated Air/Space Vehicles

24. Indoor test range Aim & Scope: indoor experiments for target site exploration cooperative exploration

25. Scenario Cooperative Target Site Exploration: Heterogeneous rover team and blimps explore science sites determined by remote sensing exploration feature path planned/taken way point exploration region identified feature goal position Tasks: small scout rovers (ATRV Jr) explore terrain as described in earlier scenarios blimps provide additional fine grain air surveillance scout rovers identify features for further investigation by sample rover (ATRV) scout rovers provide refined terrain mapping for path planning of the larger sample rover Scenario Research Objective Extend coordination to heterogeneous team …

26. Cryobot & Hydrobot courtesy JPL Exploring life under Europa

27. Outline Course Objectives and Assignments Types of Reasoning Kinds of Intelligent Embedded Systems A Case Study: Space Explorers Course Objectives and Assignments Types of Reasoning Kinds of Intelligent Embedded Systems A Case Study: Space Explorers

28. Cassini Maps Titan courtesy JPL 7 year cruise ~ 150 - 300 ground operators ~ 1 billion $ 7 years to build A Capable Robotic Explorer: Cassini 150 million $ 2 year build 0 ground ops Faster, Better, Cheaper

29. courtesy JPL ``Our vision in NASA is to open the Space Frontier... We must establish a virtual presence, in space, on planets, in aircraft and spacecraft.’’ - Daniel S. Goldin, NASA Administrator, May 29, 1996

30. Four launches in 7 months Mars Climate Orbiter: 12/11/98 Mars Polar Lander: 1/3/99 Stardust: 2/7/99 QuickSCAT: 6/19/98 courtesy of JPL

31. Vanished: Mars Polar Lander Mars Observer courtesy of JPL Spacecraft require commonsense…

32. Traditional spacecraft commanding

33. Houston, We have a problem... courtesy of NASA Quintuple fault occurs (three shorts, tank-line and pressure jacket burst, panel flies off). Mattingly works in ground simulator to identify new sequence handling severe power limitations. Mattingly identifies novel reconfiguration, exploiting LEM batteries for power. Swaggert & Lovell work on Apollo 13 emergency rig lithium hydroxide unit.

34. Self Repairing Explorers: Deep Space 1