Skip to Main content Skip to Navigation
Conference papers

Mixed-Initiative Decision Theoretic Planning for Cooperative Control

Abdel-Illah Mouaddib Shlomo Zilberstein Aurélie Beynier 1
1 SMA - Systèmes Multi-Agents
LIP6 - Laboratoire d'Informatique de Paris 6
Abstract : Mixed-initiative cooperative control can help overcome the limitations of autonomous robots by introducing a human operator into the control loop. Developing new computational models for cooperative control presents several key questions : how to account for the different perceptual and action abilities of the robot versus the human operator, the different costs of their actions, and the fact that human operators cannot switch their attention and take over control instantly. We present a decision-theoretic approach to solve these problems using Mixed-Initiative Markov Decision Processes (MI-MDPs). This framework allows us to compute optimal plans that not only tell the robot what actions to perform, but also when to request human attention or transfer control to the human operator. The result is a model with a varying degree of autonomy, particularly suitable for robots exploring a domain with regions that are too complex or risky for autonomous operation. Experimental results confirm the effectiveness of this approach in common scenarios in which fully-autonomous operation or continuous human control are both undesirable.
Document type :
Conference papers
Complete list of metadatas

https://hal.archives-ouvertes.fr/hal-01296708
Contributor : Lip6 Publications <>
Submitted on : Friday, April 1, 2016 - 2:16:27 PM
Last modification on : Thursday, March 21, 2019 - 1:00:45 PM

Identifiers

  • HAL Id : hal-01296708, version 1

Citation

Abdel-Illah Mouaddib, Shlomo Zilberstein, Aurélie Beynier. Mixed-Initiative Decision Theoretic Planning for Cooperative Control. Journées Francophones Planification Décision Apprentissage, Jun 2009, Paris, France. ⟨hal-01296708⟩

Share

Metrics

Record views

105