# Decision-Driven Semantic Object Exploration for Legged Robots via Confidence-Calibrated Perception and Topological Subgoal Selection

arXiv: https://arxiv.org/abs/2509.20739 · HTML: https://mlsanity.com/paper/2509.20739/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 23 of its 23 references that are in the map.
- First posted on arXiv 25 Sep 2025.

## Builds on (most cited first, 23 of 23)

- [Learning Transferable Visual Models From Natural Language Supervision](https://mlsanity.com/paper/2103.00020/) (2021)
- [GPT-4 Technical Report](https://mlsanity.com/paper/2303.08774/) (2023)
- [Segment Anything](https://mlsanity.com/paper/2304.02643/) (2023)
- [BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Models](https://mlsanity.com/paper/2301.12597/) (2023)
- [Grounding DINO: Marrying DINO with Grounded Pre-Training for Open-Set Object Detection](https://mlsanity.com/paper/2303.05499/) (2023)
- [Qwen-VL: A Versatile Vision-Language Model for Understanding, Localization, Text Reading, and Beyond](https://mlsanity.com/paper/2308.12966/) (2023)
- [ORB-SLAM3: An Accurate Open-Source Library for Visual, Visual-Inertial and Multi-Map SLAM](https://mlsanity.com/paper/2007.11898/) (2020)
- [YOLO-World: Real-Time Open-Vocabulary Object Detection](https://mlsanity.com/paper/2401.17270/) (2024)
- [LM-Nav: Robotic Navigation with Large Pre-Trained Models of Language, Vision, and Action](https://mlsanity.com/paper/2207.04429/) (2022)
- [Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning](https://mlsanity.com/paper/1609.05143/) (2016)
- [Visual Language Maps for Robot Navigation](https://mlsanity.com/paper/2210.05714/) (2022)
- [VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigation](https://mlsanity.com/paper/2312.03275/) (2023)
- [Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigation](https://mlsanity.com/paper/2403.17846/) (2024)
- [Neural Topological SLAM for Visual Navigation](https://mlsanity.com/paper/2005.12256/) (2020)
- [FAST-LIO2: Fast Direct LiDAR-inertial Odometry](https://mlsanity.com/paper/2107.06829/) (2021)
- [Cross-modal Map Learning for Vision and Language Navigation](https://mlsanity.com/paper/2203.05137/) (2022)
- [A Survey on Active Simultaneous Localization and Mapping: State of the Art and New Frontiers](https://mlsanity.com/paper/2207.00254/) (2022)
- [Volumetric Environment Representation for Vision-Language Navigation](https://mlsanity.com/paper/2403.14158/) (2024)
- [ViPlanner: Visual Semantic Imperative Learning for Local Navigation](https://mlsanity.com/paper/2310.00982/) (2023)
- [Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrations](https://mlsanity.com/paper/1805.07095/) (2018)
- [FisheyeDepth: A Real Scale Self-Supervised Depth Estimation Model for Fisheye Camera](https://mlsanity.com/paper/2409.15054/) (2024)
- [OmniColor: A Global Camera Pose Optimization Approach of LiDAR-360Camera Fusion for Colorizing Point Clouds](https://mlsanity.com/paper/2404.04693/) (2024)
- [VL-Nav: Neuro-Symbolic Reasoning-based Vision-Language Navigation](https://mlsanity.com/paper/2502.00931/) (2025)

## Built on by (most cited first, 1 of 1)

- [RAGNav: A Retrieval-Augmented Topological Reasoning Framework for Multi-Goal Visual-Language Navigation](https://mlsanity.com/paper/2603.03745/) (2026)

## Abstract (arXiv)

Conventional navigation pipelines for legged robots remain largely geometry-centric, relying on dense SLAM representations that are fragile under rapid motion and offer limited support for semantic decision making in open-world exploration. In this work, we focus on decision-driven semantic object exploration, where the primary challenge is not map consistency but how noisy and heterogeneous semantic observations can be transformed into stable and executable exploration decisions. We propose a vision-based approach that explicitly addresses this problem through confidence-calibrated semantic evidence arbitration, a controlled-growth semantic topological memory, and a semantic utility-driven subgoal selection mechanism. These components enable the robot to accumulate task-relevant semantic knowledge over time and select exploration targets that balance semantic relevance, reliability, and reachability, without requiring dense geometric reconstruction. Extensive experiments in both simulation and real-world environments demonstrate that the proposed mechanisms consistently improve the quality of semantic decision inputs, subgoal selection accuracy, and overall exploration performance on legged robots.