mlsanityData to 14 Oct 2026

AION: Aerial Indoor Object-Goal Navigation Using Dual-Policy Reinforcement Learning

arXiv 2601.15614 ↗First posted 22 Jan 2026cs.ROcited by 0

On the map: Deep reinforcement learning methods → RL for robot navigation and UAV control

Abstract (arXiv)

Object-Goal Navigation (ObjectNav) requires an agent to autonomously explore an unknown environment and navigate toward target objects specified by a semantic label. While prior work has primarily studied zero-shot ObjectNav under 2D locomotion, extending it to aerial platforms with 3D locomotion capability remains underexplored. Aerial robots offer superior maneuverability and search efficiency, but also introduce new challenges in spatial perception, dynamic control, and safety assurance. In this paper, we propose AION for vision-based aerial ObjectNav without relying on external localization or global maps. AION is an end-to-end dual-policy reinforcement learning (RL) framework that decouples exploration and goal-reaching behaviors into two specialized policies. We evaluate AION on the AI2-THOR benchmark and further assess its real-time performance in IsaacSim using high-fidelity drone models. Experimental results show that AION achieves superior performance across comprehensive evaluation metrics in exploration, navigation efficiency, and safety. The project is available at https://github.com/Zichen-Yan/AION.

Key facts. No citing papers in the map yet (data through 14 Oct 2026). Placed in RL for robot navigation and UAV control, one of 15 directions in Deep reinforcement learning methods. Builds on 31 of its 37 references that are in the map. First posted on arXiv 22 Jan 2026.

Builds on

31 of 37 references.

Closest ancestors · 1

Same direction, newest first

  1. 2024TDANet: Target-Directed Attention Network For Object-Goal Visual Navigation With Zero-Shot Ability12 Apr

Other references · 30

  1. 2021Learning Transferable Visual Models From Natural Language Supervisioncited by 33,744
  2. 2023DINOv2: Learning Robust Visual Features without Supervisioncited by 7,974
  3. 2023BLIP-2: Bootstrapping Language-Image Pre-training with Frozen Image Encoders and Large Language Modelscited by 6,137
  4. 2015You Only Look Once: Unified, Real-Time Object Detectioncited by 4,852
  5. 2016Asynchronous Methods for Deep Reinforcement Learningcited by 2,258
  6. 2017AI2-THOR: An Interactive 3D Environment for Visual AIcited by 869
  7. 2020Object Goal Navigation using Goal-Oriented Semantic Explorationcited by 429
  8. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 380
  9. 2022Visual Language Maps for Robot Navigationcited by 365
  10. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 228
  11. 2023VLFM: Vision-Language Frontier Maps for Zero-Shot Semantic Navigationcited by 205
  12. 2018Visual Semantic Navigation using Scene Priorscited by 128
18 more
  1. 2023ESC: Exploration with Soft Commonsense Constraints for Zero-shot Object Navigationcited by 127
  2. 2023AerialVLN: Vision-and-Language Navigation for UAVscited by 121
  3. 2023L3MVN: Leveraging Large Language Models for Visual Target Navigationcited by 120
  4. 2022Navigating to Objects in the Real Worldcited by 106
  5. 2018Learning to Learn How to Learn: Self-Adaptive Visual Navigation Using Meta-Learningcited by 93
  6. 2023Bridging Zero-shot Object Navigation and Foundation Models through Pixel-Guided Navigation Skillcited by 77
  7. 2024CityNav: A Large-Scale Dataset for Real-World Aerial Navigationcited by 42
  8. 2025UAV-ON: A Benchmark for Open-World Object Goal Navigation with Aerial Agentscited by 33
  9. 2022Stubborn: A Strong Baseline for Indoor Object Navigationcited by 32
  10. 2022Zero-shot object goal visual navigationcited by 31
  11. 2024Prioritized Semantic Learning for Zero-shot Instance Navigationcited by 31
  12. 2025UAV-Flow Colosseo: A Real-World Benchmark for Flying-on-a-Word UAV Imitation Learningcited by 31
  13. 2025ApexNav: An Adaptive Exploration Strategy for Zero-Shot Object Navigation with Target-centric Semantic Fusioncited by 30
  14. 2022Search for or Navigate to? Dual Adaptive Thinking for Object Navigationcited by 20
  15. 2025FrontierNet: Learning Visual Cues to Explorecited by 12
  16. 2023Pegasus Simulator: An Isaac Sim Framework for Multiple Aerial Vehicles Simulationcited by 10
  17. 2025IndoorUAV: Benchmarking Vision-Language UAV Navigation in Continuous Indoor Environmentscited by 10
  18. 2025LoGoPlanner: Localization Grounded Navigation Policy with Metric-aware Visual Geometrycited by 6

Built on by

Not cited yet.

Similar, not cited

Close in wording, no citation either way

  1. 2025SIGN: Safety-Aware Image-Goal Navigation for Autonomous Drones via Reinforcement Learning
  2. 2026VLN on the Fly: An Onboard Vision-Language Navigation Stack for Aerial Robots
  3. 2025Reinforcement Learning for Autonomous Point-to-Point UAV Navigation
  4. 2026Reinforcement Learning for Active Perception in Autonomous Navigation
  5. 2026APEX: A Decoupled Memory-based Explorer for Asynchronous Aerial Object Goal Navigation
  6. 2025Autonomous UAV Flight Navigation in Confined Spaces: A Reinforcement Learning Approach
  7. 2026Self-Predictive Representation for Autonomous UAV Object-Goal Navigation
  8. 2025LEARN: Learning End-to-End Aerial Resource-Constrained Multi-Robot Navigation