POMP++: Pomcp-based Active Visual Search in unknown indoor environments

TL;DR

POMP++ introduces a novel planning strategy based on POMCP for online active visual search in unknown indoor environments, achieving significant improvements in success rates over existing methods.

Contribution

It presents a training-free online policy learning approach with a new belief reinvigoration strategy for dynamic environment mapping.

Findings

Achieves >10% success rate improvement over state-of-the-art methods.

Effective in real robotic and simulated indoor environments.

Demonstrates robustness in unknown and dynamically growing spaces.

Abstract

In this paper we focus on the problem of learning online an optimal policy for Active Visual Search (AVS) of objects in unknown indoor environments. We propose POMP++, a planning strategy that introduces a novel formulation on top of the classic Partially Observable Monte Carlo Planning (POMCP) framework, to allow training-free online policy learning in unknown environments. We present a new belief reinvigoration strategy which allows to use POMCP with a dynamically growing state space to address the online generation of the floor map. We evaluate our method on two public benchmark datasets, AVD that is acquired by real robotic platforms and Habitat ObjectNav that is rendered from real 3D scene scans, achieving the best success rate with an improvement of >10% over the state-of-the-art methods.