ROBOTICS

1

• ROBOTICS
• COE 584
• Reactive Systems

2
Previously, on Robots

• Robots are agents in physical or virtual
  environments
• Persistent, situated, responsive
• Environments have different characteristics
• Static/dynamic, accessible?, deterministic?, .
• Since we are lazy, we want robots to do things
  for us
• Robots must consider task when deciding what to
  do
• Action-selection problem
• What to do now in service of the task?

3
Physical Environments

• Dynamic
• Non-deterministic
• Inaccessible
• Continuous

4
A Crash Course in AI Planning

• Planning An approach to action-selection problem
• Very long history, since the very beginning of AI
• 1971, seminal paper STRIPS (Fikes and Nilsson)
• Still cited and taught today, despite much
  progress
• STRIPS originally developed for SRI robot, Shakey
• This is ironic
• Later on, STRIPS planning was rejected for robot
  control

5
AI Planning Definition State

• On(A,table), On(B,table), On(C,table),
  In-hand(nil)

On(A,B), On(B,table), On(C,table), In-hand(D)
6
AI Planning Definition Operators

• Operators change state of the world
• Preconditions, add-list, delete-list
• Pick-A(?x)
• Preconditions On(A, ?x), In-hand(nil)
• Add In-hand(A)
• Delete In-hand(nil), On(A, ?x)
• Put-A(?y)
• Preconditions In-hand(A), not On(?x, ?y)
• Add On(A,?y), In-hand(nil)
• Delete In-hand(A)

7
STRIPS Planning

• Given
• Initial state of the world
• Operators
• Goal state
• Produce
• Plan Ordered list of instantiated operators
• Will change the world from initial state to goal
  state

8
Planning Example
After Put-C(B)
9
Planning on robots

• Sense initial state using sensors
• Create a full plan given goal state (given task)
• Feed plan, step-by-step to motors
• No need to sense again
• Whats wrong with this?
• (Hint Think about Schoppers paper)

10
Deliberative Control
Sense
Model
Think
Act

• Deliberative
• Has internal state (typically a model of the
  world)
• Uses this internal state to make decisions
• Decisions made between alternatives

11
When plans goes wrong

• Dynamic environment
• State changes even if no operator applied
• Non-deterministic
• State changes not according to operator specs
• Inaccessible
• Cannot sense entire state of the world
• Continuous
• Predicate-based description of world is discrete

12
Reactive control
Sense
Hard Wiring
Act

• Reactive
• No internal state
• Direct connection from sensors to actions
• S-R (stimulus response) systems
• No choices, no alternatives

13
Universal Planning

• Have a plan ready for any possible contingency
• Scouts Be prepared! ?
• From any initial state, know how to get to goal
  state
• Input Operators, goal state
• Do not need to give initial state
• Output Decision tree
• What operator to take, depending on environment
  state
• Not a single ordered list of operators

14
Universal planning algorithm
15
Robot Control AlgorithmUsing Universal Planning

• Robot given task (goal, operators)
• Uses universal planner to create universal plan
• Robot senses environment
• Goal state reached?
• No Execute operator according to decision tree
• Yes (keep persistency)

16
Advantages of Universal Planning

• Guaranteed to use optimal (shortest) plan to goal
• A very good thing!
• Optimal solution to action selection problem
• Robust to failures
• Robust in dynamic and non-deterministic domains

17
Problems with Universal Planning

• Assumes accessibility
• Assumes perfect sensors
• Assumes discrete actions (operators)

18
Universal plan as mapping sensors to actions

• Universal plan can be viewed as a function
• Sensor readings to actions
• u S?A
• Essentially a table For each state, give action
• Schoppers uses a decision-tree representation

19
Problems Planning Time

• What is the planning time?
• Planning time grows with the number of states
• Since we have to enumerate operator for every
  state
• What is the number of states in an environment?
• Worst case
• All possible combinations of sensor readings
• (state predicates)

20
Problems Universal Plan Size

• Plan size grows with the number of possible
  states
• Curse of dimensionality

Pick
Put
X1
Pick
Put
X2
21
Problems Stupid executioner

• Schoppers
• Baby goes around knocking blocks around?
• Ginsberg
• What if baby repeatedly knocks down the same
  block?
• Universal plans may get into cycles
• This is because no deliberation is done
• Universal planner relies on simple executioner
• Sense, consult table, act
• Same as regular planner except for sensing

22
Brooks Subsumption Architecture

• Multiple levels of control Behaviors

Plan changes
Identify objects
Monitor Change
Map
Explore
Wander
Avoid Object
23
Why does this work?

• It breaks the ideal universal plan into behaviors
• avoids the curse of dimensionality
• Behaviors (levels) interact to generate behavior
• Note that programmer is responsible for
  task-oriented design
• Goes both below and above universal plans
• Hand programmed approximate plan
• Not automatically generated

24
Subsuming Layers

• How to make sure overall output is coherent?
• e.g., avoid object is in conflict with explore
• Subsumption hierarchy Higher levels modify lower

Map
Explore
Wander
Avoid Object
25
Coherence using subsumption

• Key principle
• Higher layers control input/outputs of lower
  layers
• In practice
• Can be difficult to design
• a lot depends on programmer
• Single module per layer can be restrictive
• Increasingly challenging to control at higher
  levels

26
Irony

• Ginsbergs article pretty much killed universal
  planning
• Though occasional papers still published
• Reactive control very popular in practice
• But due to theory problem, no more automated
  planners!
• So we get lots of reactive plans, but no planning

27
Irony again

• Ginsberg was right
• Approximating universal plan is possible
• Tends to be useful only in fairly low level
  locomotion control
• Approximation is what Brooks had done
• Which is why he often gets the credit for the
  revolution

28
Starting next week

• Behavior-Based Control
• Expanding on Subsumption