Robotic manipulation of multiple objects as a POMDP Joni Pajarinen - - PowerPoint PPT Presentation

Robotic manipulation of multiple objects as a POMDP

Joni Pajarinen and Ville Kyrki

Intelligent Robotics group Department of Electrical Engineering and Automation Aalto University, Finland July 13, 2014

Robotic manipulation of multiple objects as a POMDP July 13, 2014 2/5

◮ Setting: Unknown objects in a crowded environment ◮ Challenges: Occlusion, imperfect observations, and

uncertain action success

◮ Objective: perform sequential task, such as moving dirty

• bjects into dishwasher or cleaning up toys

Robotic manipulation of multiple objects as a POMDP July 13, 2014 3/5

Belief

→

Probability

Approach: We model the problem as a partially observable Markov decision process (POMDP)

• 1. Estimate belief over object attributes (e.g. color), estimate

semantic locations (e.g. on table) and occlusions

• 2. Estimate object probabilities

◮ Probability for observing and grasping an object depends

• n a model-free occlusion measure

◮ Our model adapts automatically object grasp probabilities

according to previous grasp successes

• 3. Compute compact POMDP plan and execute action

Robotic manipulation of multiple objects as a POMDP July 13, 2014 4/5

Example application: dirty objects into dishwasher

◮ Robot may move an object into

dishwasher (blue box) or lift an

• bject to see behind the object

◮ Objective is to quickly move dirty

but not clean objects into dishwasher

−1 1 2 3 4 5 6 Planning horizon Reward over ten time steps − − 2 3 4 5 Simple Simple+history POMDP planning

−20 −15 −10 −5 5 10 15 Simple POMDP planning Reward over ten time steps

POMDP approach vs. simple heuristic approach

Robotic manipulation of multiple objects as a POMDP July 13, 2014 5/5

Thank you for your attention