Decision Making: Lessons Learned

• Four sources of uncertainty

  • Environment unpredictable
  • Robot wear and tear
  • Sensors limitations
  • Models inaccurate

• Two implications

  • Need policy instead of simple (open-loop) plan
  • Policy must be conditioned on belief state

• Approaches

  • MDP: Only works with perfect sensors, models
  • POMDPs: general framework, but scaling limitations
  • Augmented MDPs: lower computation, but approximate

Previous slide

Next slide

Back to first slide

View graphic version