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

arXiv: https://arxiv.org/abs/2005.02878 · HTML: https://mlsanity.com/paper/2005.02878/

## Key facts

- Cited by 8 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 6 May 2020.

## Built on by (most cited first, 8 of 8)

- [Partially Observable Markov Decision Processes in Robotics: A Survey](https://mlsanity.com/paper/2209.10342/) (2022)
- [Towards Optimal Correlational Object Search](https://mlsanity.com/paper/2110.09991/) (2021)
- [A System for Generalized 3D Multi-Object Search](https://mlsanity.com/paper/2303.03178/) (2023)
- [Learning to Look: Seeking Information for Decision Making via Policy Factorization](https://mlsanity.com/paper/2410.18964/) (2024)
- [Scalable Interactive Machine Learning for Future Command and Control](https://mlsanity.com/paper/2402.06501/) (2024)
- [Large-Language-Model-Guided State Estimation for Partially Observable Task and Motion Planning](https://mlsanity.com/paper/2603.03704/) (2026)
- [Language-Conditioned Observation Models for Visual Object Search](https://mlsanity.com/paper/2309.07276/) (2023)
- [Dialogue Object Search](https://mlsanity.com/paper/2107.10653/) (2021)

## Abstract (arXiv)

Robots operating in households must find objects on shelves, under tables, and in cupboards. In such environments, it is crucial to search efficiently at 3D scale while coping with limited field of view and the complexity of searching for multiple objects. Principled approaches to object search frequently use Partially Observable Markov Decision Process (POMDP) as the underlying framework for computing search strategies, but constrain the search space in 2D. In this paper, we present a POMDP formulation for multi-object search in a 3D region with a frustum-shaped field-of-view. To efficiently solve this POMDP, we propose a multi-resolution planning algorithm based on online Monte-Carlo tree search. In this approach, we design a novel octree-based belief representation to capture uncertainty of the target objects at different resolution levels, then derive abstract POMDPs at lower resolutions with dramatically smaller state and observation spaces. Evaluation in a simulated 3D domain shows that our approach finds objects more efficiently and successfully compared to a set of baselines without resolution hierarchy in larger instances under the same computational requirement. We demonstrate our approach on a mobile robot to find objects placed at different heights in two 10m2 × 2m regions by moving its base and actuating its torso.