Presentation is loading. Please wait.

Presentation is loading. Please wait.

Outline Deep Space One and Remote Agent Model-based Execution OpSat and the ITMS Model-based Reactive Planning Space Robotics.

Similar presentations


Presentation on theme: "Outline Deep Space One and Remote Agent Model-based Execution OpSat and the ITMS Model-based Reactive Planning Space Robotics."— Presentation transcript:

1 Outline Deep Space One and Remote Agent Model-based Execution OpSat and the ITMS Model-based Reactive Planning Space Robotics

2 Modes Controlled Through Interactions driver computer bus control remote terminal driver remote terminal How do we open a valve?

3 Modes Controlled Through Interactions driver computer bus control remote terminal driver remote terminal MRMI Command Configuration goals Model goal statecurrent state Reactive Planner

4 computer bus control remote terminal remote terminal driver Modes Controlled Through Interactions Irreversible actions should be avoided by reactive planners. Component schematics tend not to have loops  goals are serializable Solution: Work goals from outputs to inputs. Achieve goals serially.

5 computer bus control remote terminal remote terminal driver Modes Controlled Through Interactions Irreversible actions should be avoided by reactive planners. Component schematics tend not to have loops  goals are serializable Solution: Work goals from outputs to inputs. Achieve goals serially.

6 computer bus control remote terminal remote terminal driver Modes Controlled Through Interactions Irreversible actions should be avoided by reactive planners. Component schematics tend not to have loops  goals are serializable Solution: Work goals from outputs to inputs. Achieve goals serially.

7 Irreversible actions should be avoided by reactive planners. Component schematics tend not to have loops. Solution: Work goals from outputs to inputs. Achieve goals serially. Compile devices into distributed policies –prime implicate generation –strongly connected components computer bus control remote terminal remote terminal driver Modes Controlled Through Interactions vlv = closed & vcmdin = open  next (vlv = open) vlv = open & flowin = pos  flowout = pos Closed Open Stuck open Stuck closed vcmdin = openvcmdin = close

8 Indirect controllability inflow = outflow Closed Open cmd = opencmd = close cmd =off On Off cmd= oncmd = off cmd = reset vcmd in = vcmd out vcmd out (Driver) = cmd(Valve) Device states are not directly controllable

9 Compilation rt = on driver = on vcmd in (cu) = open rt = on driver = on vcmd in (cu) = close inflow = outflow Closed Open cu = on dcmd =off On Off rt = on dcmd= on rt = on dcmd = off rt = on dcmd(cu) = reset vcmd in = vcmd out vcmd out (Driver) = cmd(Valve) Remove intermediate variables using implicate generation –becomes a STRIPS-like problem –implicate generation done using conflict directed best first search

10 Compilation driver = on cmd= open driver = on cmd = close inflow = outflow Closed Open cmd =off On Off cmd= oncmd = off cmd= reset vcmd in = vcmd out vcmd out (Driver) = cmd(Valve) Remove intermediate variables using implicate generation –becomes a STRIPS-like problem –implicate generation done using conflict directed best first search

11 Concurrent policies rt = on driver = on vcmd in (cu) = open rt = on driver = on vcmd in (cu) = close Closed Open fail Goal fail rt = on driver = on cmd = open idle rt = on driver = on cmd = close Current Open Closed Stuck Open Closed Convert resulting transition system into a local policy  Encoding is extremely compact Ensure only reversible transitions are taken

12 Concurrent policies driver = on cmd = open driver = on cmd = close Closed Open fail Goal fail driver = on cmd = open idle driver = on cmd = close Current Open Closed Stuck Open Closed Convert resulting transition system into a local policy  Encoding is extremely compact Ensure only reversible transitions are taken

13 Irreversible actions should be avoided by reactive planners. Component schematics tend not to have loops. Solution: Work goals from outputs to inputs. Achieve goals serially. Compile devices into distributed policies –prime implicate generation –strongly connected components computer bus control remote terminal remote terminal driver Modes Controlled Through Interactions Closed Open Stuck open Stuck closed dr = on, dcmdin = open dr=on vcmdin = close

14 Irreversible actions should be avoided by reactive planners. Component schematics tend not to have loops. Solution: Work goals from outputs to inputs. Achieve goals serially. Compile devices into distributed policies –prime implicate generation –strongly connected components computer bus control remote terminal remote terminal driver Modes Controlled Through Interactions Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close

15 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal:

16 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal:

17 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: cmd = on

18 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: cmd = on

19 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: cmd = close

20 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: Driver Fails! cmd = close

21 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: cmd = reset

22 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: cmd = close

23 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: cmd = off

24 Goal Current open closed open closed stuckfail idle dr = on cmd=open dr = on cmd=close Goal Current onoff on off reset failure cmd=reset idle cmd = on cmd = off cmd=reset off Cmd closed Goal: Success! cmd = off

25 Complexity of Reactive Planning Worst Case per action: Depth * Sub-goal branch factor Average Cost per action:Sub-goal branch factor Valve 1 = openValve 2 = openDrv 1 = offDrv 2 = off Drv 1 = on CU = on Drv 2 = on CU = on

26 Complexity Analysis Details Average Cost per action:Subgoal branch factor –Avg cost = compute time / plan length –Each edge of the goal/subgoal tree is traversed twice. Compute time = 2 * E * B. –Each node of the goal / subgoal tree generates one action. plan length = N –Avg cost = O(E/N) –In the worst case E < = 2 * N. –Average Cost per action = O(B* N/N) = O(B) Subgoals

27 Outline Deep Space One and Remote Agent Model-based Execution OpSat and the ITMS Model-based Reactive Planning Space Robotics

28 Current Livingstone Testbeds

29 TechSat21 & Gflops Testbed MIT SSL Spheres MIT SSL Portable Satellite Assistant Ames

30 Capabilities Demonstration Space Station Module Oxygen:................15% Nitrogen:...............79% Carbon Dioxide:....05% Other:....................01% Temperature:........68F Pressure:..............14lbs Humidity:...............50% courtesy Yuri Gawdiak, NASA Ames

31 Conclusions Space is opening its doorway to a new generation of agile, highly independent explorers. To survive decades of operation they must orchestrate complex regulatory and immune systems. Model-based autonomy supports rapid prototyping through model-based programming and executives. A model-based executive is a kind of stochastic optimal controller that makes extensive use of deduction to observe and control on the fly. The core is OPSAT, a real-time, combinatorial optimization algorithm with logical feasibility constraints. Fast, model-based reactive planning is achieved through knowledge compilation and by exploiting structural and safety constraints.

32


Download ppt "Outline Deep Space One and Remote Agent Model-based Execution OpSat and the ITMS Model-based Reactive Planning Space Robotics."

Similar presentations


Ads by Google