mlsanityData to 14 Oct 2026

SGN-CIRL: Scene Graph-based Navigation with Curriculum, Imitation, and Reinforcement Learning

arXiv 2506.04505 ↗First posted 4 Jun 2025cs.RO cs.LGcited by 2

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

Abstract (arXiv)

The 3D scene graph models spatial relationships between objects, enabling the agent to efficiently navigate in a partially observable environment and predict the location of the target object.This paper proposes an original framework named SGN-CIRL (3D Scene Graph-Based Reinforcement Learning Navigation) for mapless reinforcement learning-based robot navigation with learnable representation of open-vocabulary 3D scene graph. To accelerate and stabilize the training of reinforcement learning-based algorithms, the framework also employs imitation learning and curriculum learning. The first one enables the agent to learn from demonstrations, while the second one structures the training process by gradually increasing task complexity from simple to more advanced scenarios. Numerical experiments conducted in the Isaac Sim environment showed that using a 3D scene graph for reinforcement learning significantly increased the success rate in difficult navigation cases. The code is open-sourced and available at: https://github.com/Xisonik/Alohagraph.

Key facts. Cited by 2 papers in the map (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 13 of its 18 references that are in the map. First posted on arXiv 4 Jun 2025.

Builds on

13 of 18 references.

References · 13

  1. 2017Graph Attention Networkscited by 8,923
  2. 2024Mobile ALOHA: Learning Bimanual Mobile Manipulation with Low-Cost Whole-Body Teleoperationcited by 391
  3. 2023ConceptGraphs: Open-Vocabulary 3D Scene Graphs for Perception and Planningcited by 365
  4. 2024Hierarchical Open-Vocabulary 3D Scene Graphs for Language-Grounded Robot Navigationcited by 196
  5. 2018Visual Semantic Navigation using Scene Priorscited by 128
  6. 2024SG-Nav: Online 3D Scene Graph Prompting for LLM-based Zero-shot Object Navigationcited by 109
  7. 2020Learning Object Relation Graph and Tentative Policy for Visual Navigationcited by 64
  8. 2024Dynamic Open-Vocabulary 3D Scene Graphs for Long-term Language-Guided Mobile Manipulationcited by 39
  9. 2018Reinforced Imitation: Sample Efficient Deep Reinforcement Learning for Map-less Navigation by Leveraging Prior Demonstrationscited by 38
  10. 2024Beyond Bare Queries: Open-Vocabulary Object Grounding with 3D Scene Graphcited by 32
  11. 2020Robot Navigation with Map-Based Deep Reinforcement Learningcited by 9
  12. 2023Autonomous Exploration and Mapping for Mobile Robots via Cumulative Curriculum Reinforcement Learningcited by 5
1 more
  1. 2022Using Deep Reinforcement Learning with Automatic Curriculum Learning for Mapless Navigation in Intralogisticscited by 3

Built on by

Cited by year

Citing papers per year: 2025: 2.

2 papers.

  1. 2025M3DMap: Object-aware Multimodal 3D Mapping for Dynamic Environmentscited by 1
  2. 2025FOGMACHINE -- Leveraging Discrete-Event Simulation and Scene Graphs for Modeling Hierarchical, Interconnected Environments under Partial Observations from Mobile Agentscited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2026Modernising Reinforcement Learning-Based Navigation for Embodied Semantic Scene Graph Generation
  2. 2025Incorporating Spatial Information into Goal-Conditioned Hierarchical Reinforcement Learning via Graph Representations
  3. 2026Revisiting Topological Graphs for Macro Action based Closed-loop Reinforcement Learning of Vision Language Navigation in Continuous Environment
  4. 2025Hierarchical Reinforcement Learning for Safe Mapless Navigation with Congestion Estimation
  5. 2024PLANRL: A Motion Planning and Imitation Learning Framework to Bootstrap Reinforcement Learning
  6. 2020Evolving Graphical Planner: Contextual Global Planning for Vision-and-Language Navigation
  7. 2026GN0: Toward a Unified Paradigm for Generation, Evaluation, and Policy Learning in Visual-Language Navigation
  8. 2025GUI Exploration Lab: Enhancing Screen Navigation in Agents via Multi-Turn Reinforcement Learning