P2 Explore: Efficient Exploration in Unknown Clustered Environment with Floor Plan Prediction

2024-09-17

arXiv.org

AI Summary

To address inefficient exploration and susceptibility to local optima in robots navigating unknown, cluttered indoor environments, this paper proposes a structured-prior-guided hierarchical exploration framework. First, a robust Floor Plan Understanding Network (FPUNet) reconstructs the global layout from noisy sensor data. Second, room-level semantic segmentation and topological connectivity modeling are performed based on the predicted floor plan. Finally, an optimal room visitation sequence is computed over the room-level topological graph to guide frontier point selection at the lower level. This work is the first to deeply integrate robust floor plan prediction with room-level topological planning, overcoming the locality limitations inherent in conventional frontier-driven approaches. Experiments demonstrate that the proposed method reduces path length by 2.18%–34.60% compared to baselines, and FPUNet achieves state-of-the-art performance on floor plan prediction.

Technology Category

• Intelligent Robots: Motion and Path Planning
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling
• Humans and AI: Human-Aware Planning and Behavior Prediction

Application Category

• Graph Algorithms and Modeling for the Web: Representation, reconstruction, and subgraph or motif discovery in Web-related graphs
• Semantics and Knowledge: Scalable techniques for the creation, curation, publication, maintenance, and consumption of large, Web-based, structured, reusable, knowledge graphs and ontologies
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Robot exploration aims at the reconstruction of unknown environments, and it is important to achieve it with shorter paths. Traditional methods focus on optimizing the visiting order of frontiers based on current observations, which may lead to local-minimal results. Recently, by predicting the structure of the unseen environment, the exploration efficiency can be further improved. However, in a cluttered environment, due to the randomness of obstacles, the ability to predict is weak. Moreover, this inaccuracy will lead to limited improvement in exploration. Therefore, we propose FPUNet which can be efficient in predicting the layout of noisy indoor environments. Then, we extract the segmentation of rooms and construct their topological connectivity based on the predicted map. The visiting order of these predicted rooms is optimized which can provide high-level guidance for exploration. The FPUNet is compared with other network architectures which demonstrates it is the SOTA method for this task. Extensive experiments in simulations show that our method can shorten the path length by 2.18% to 34.60% compared to the baselines.

Problem

• Improves robot exploration efficiency in cluttered environments.
• Predicts floor plans to optimize room visiting order.
• Reduces path length significantly compared to baseline methods.

Innovation

• FPUNet predicts noisy indoor environment layouts.
• Room segmentation and topological connectivity extraction.
• Optimized room visiting order for efficient exploration.