Share This Author
Incremental plan aggregation for generating policies in MDPs
A way to generate policies in MDPs by determinizing the given MDP model into a classical planning problem, and using sequential Monte-Carlo simulations of the partial policies before execution, in order to assess the probability of replanning for a policy during execution is described.
RFF : A Robust , FF-Based MDP Planning Algorithm for Generating Policies with Low Probability of Failure
An MDP planning algorithm, called RFF, is presented, for generating offline robust policies in probabilistic domains, that uses a Monte-Carlo simulation in order to compute the probability that a partial policy would fail during execution and has a low probability of failing.
Two-handed gesture recognition and fusion with speech to command a robot
A flexible multimodal interface based on speech and gesture modalities in order to control the authors' mobile robot named Jido is described and a probabilistic and multi-hypothesis interpreter framework is shown to improve the classification rates of multi-modality commands compared to using either modality alone.
Rackham: An Interactive Robot-Guide
- A. Clodic, S. Fleury, V. Montreuil
- EngineeringROMAN - The 15th IEEE International Symposium on…
- 6 September 2006
The focus was to develop and test a methodology to integrate human-robot interaction abilities in a systematic way and to incrementally enhance the robot functional and decisional capabilities based on the observation of the interaction between the public and the robot.
HiPOP: Hierarchical Partial-Order Planning
A new planner, HiPOP (Hierarchical Partial-Order Planner), which is domain-configurable and uses POP techniques to create hierarchical time-flexible plans that follows the given methods.
Robot introspection through learned hidden Markov models
Open Loop Execution of Tree-Search Algorithms
This work investigates the question of avoiding re-planning in subsequent decision steps by directly using sub-trees as action recommender and proposes a method for open loop control via a new algorithm taking the decision of re- planner or not at each time step based on an analysis of the statistics of the sub-tree.
Learning the behavior model of a robot
A general framework for learning from observation data the behavior model of a robot when performing a given task is proposed and it is shown how such a probabilistic model can be learned and used to improve, on line, the robot behavior with respect to a specific environment and user preferences.
A generic framework for anytime execution-driven planning in robotics
- F. Teichteil-Königsbuch, C. Lesire, G. Infantes
- Computer ScienceIEEE International Conference on Robotics and…
- 1 May 2011
This work presents a new generic and anytime planning concept for modular robotic architectures, which manages multiple planning requests at a time, solved in background, while allowing for reactive execution of planned actions at the same time.
Constraint-Based Controller Synthesis in Non-Deterministic and Partially Observable Domains
This approach relaxes some restrictive assumptions made by existing work on controller synthesis with non-determinism and partial observability and is shown to induce potentially significant gains.