Adaptive Object Exploration and Mapping through Meta-Reinforcement Learning
- 2 March 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Emerging Topics in Computing
- Vol. PP (3) , 1-12
Abstract
Object Exploration and Mapping (OEM) is a novel embodied AI task that requires an agent to autonomously explore unknown environments, simultaneously detect and localize multiple objects, and construct a semantic object-level map. To solve this challenge, we propose a two-stage framework. First, a deep reinforcement learning-based OEM framework (DRL-OEM) is proposed to leverage auxiliary perception tasks and memory-augmented policy learning to guide efficient exploration. Second, we extend the DRL-OEM to Meta-OEM, where a meta-reinforcement learning framework is employed to enhance adaptation to unseen environments with a novel key-behavior-aware prioritized sampling strategy by reusing high-reward transitions. Extensive experiments conducted on customized AI2Thor scenes across diverse layouts and object configurations demonstrate that Meta-OEM significantly outperforms strong baselines, including DRL-OEM, PEARL, and MQL, achieving up to 2× higher success rates and faster convergence during adaptation. Visual and quantitative results confirm its superior object discovery coverage, pose estimation accuracy, and generalization capability in open-world scenarios.Keywords
Funding Information
- National Natural Science Foundation of China (62202137)
- Zhejiang Provincial Natural Science Foundation of China (LMS25F020009)
This publication has 26 references indexed in Scilit:
- DGTR: Distributed Gaussian Turbo-Reconstruction for Sparse-View Vast Scenes2025
- Habitat-Matterport 3D Semantics Dataset2023
- Robust and Accurate Multi-Agent SLAM with Efficient Communication for Smart Mobiles2022
- SOON: Scenario Oriented Object Navigation with Graph-based Exploration2021
- Object-oriented Map Exploration and Construction Based on Auxiliary Task Aided DRL2021
- Habitat: A Platform for Embodied AI Research2019
- Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learning2019
- DenseFusion: 6D Object Pose Estimation by Iterative Dense Fusion2019
- Learning to Compare: Relation Network for Few-Shot Learning2018
- Matterport3D: Learning from RGB-D Data in Indoor Environments2017