Corpus ID: 218516551

Multi-Resolution POMDP Planning for Multi-Object Search in 3D

@article{Zheng2020MultiResolutionPP,
  title={Multi-Resolution POMDP Planning for Multi-Object Search in 3D},
  author={Kaiyu Zheng and Yoonchang Sung and G. Konidaris and Stefanie Tellex},
  journal={ArXiv},
  year={2020},
  volume={abs/2005.02878}
}
Robots operating in household environments must find objects on shelves, under tables, and in cupboards. Previous work often formulate the object search problem as a POMDP (Partially Observable Markov Decision Process), yet constrain the search space in 2D. We propose a new approach that enables the robot to efficiently search for objects in 3D, taking occlusions into account. We model the problem as an object-oriented POMDP, where the robot receives a volumetric observation from a viewing… Expand

References

SHOWING 1-10 OF 36 REFERENCES
Multi-Object Search using Object-Oriented POMDPs
  • 6
  • PDF
Online Planning for Target Object Search in Clutter under Partial Observability
  • 15
  • Highly Influential
  • PDF
Act to See and See to Act: POMDP planning for objects search in clutter
  • J. Li, David Hsu, Wee Sun Lee
  • Engineering, Computer Science
  • 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)
  • 2016
  • 25
  • Highly Influential
  • PDF
Searching for physical objects in partially known environments
  • 7
  • PDF
Active Visual Object Search in Unknown Environments Using Uncertain Semantics
  • 81
  • Highly Influential
Efficient Object Search With Belief Road Map Using Mobile Robot
  • 17
Nonmyopic View Planning for Active Object Classification and Pose Estimation
  • 72
  • PDF
Mechanical Search: Multi-Step Retrieval of a Target Object Occluded by Clutter
  • 35
  • PDF
Sensor planning in 3d object search: its formu-lation and complexity
  • 27
  • Highly Influential
  • PDF
Monte-Carlo Planning in Large POMDPs
  • 770
  • Highly Influential
  • PDF
...
1
2
3
4
...