Deep Learning Perspective of Scene Understanding in Autonomous Robots
Not on the map. Why?
Abstract (arXiv)
This paper provides a review of deep learning applications in scene understanding in autonomous robots, including innovations in object detection, semantic and instance segmentation, depth estimation, 3D reconstruction, and visual SLAM. It emphasizes how these techniques address limitations of traditional geometric models, improve depth perception in real time despite occlusions and textureless surfaces, and enhance semantic reasoning to understand the environment better. When these perception modules are integrated into dynamic and unstructured environments, they become more effective in decisionmaking, navigation and interaction. Lastly, the review outlines the existing problems and research directions to advance learning-based scene understanding of autonomous robots.
Key facts. No citing papers in the map yet (data through 7 Oct 2026). Builds on 56 of its 95 references that are in the map. First posted on arXiv 16 Dec 2025.
Builds on
56 of 95 references.
References · 56
- 2022NeRF: Neural Radiance Field in 3D Vision: A Comprehensive Review (Updated Post-Gaussian Splatting)cited by 156
- 2019Convergence of Edge Computing and Deep Learning: A Comprehensive Surveycited by 120
- 2020Empowering Things with Intelligence: A Survey of the Progress, Challenges, and Opportunities in Artificial Intelligence of Thingscited by 110
- 2020Deep Learning for Image and Point Cloud Fusion in Autonomous Driving: A Reviewcited by 107
- 2023An Outlook into the Future of Egocentric Visioncited by 84
- 2024How NeRFs and 3D Gaussian Splatting are Reshaping SLAM: a Surveycited by 72
- 2023A Comprehensive Survey on Applications of Transformers for Deep Learning Taskscited by 70
- 2020Multi-scale Interaction for Real-time LiDAR Data Segmentation on an Embedded Platformcited by 40
- 2024Benchmarking and Improving Bird's Eye View Perception Robustness in Autonomous Drivingcited by 39
- 2023A Survey on Socially Aware Robot Navigation: Taxonomy and Future Challengescited by 35
- 2023Explainable Deep Reinforcement Learning: State of the Art and Challengescited by 33
- 2023Robotic Perception of Transparent Objects: A Reviewcited by 28
38 more
- 2024NavFormer: A Transformer Architecture for Robot Target-Driven Navigation in Unknown and Dynamic Environmentscited by 20
- 2024Video Anomaly Detection in 10 Years: A Survey and Outlookcited by 18
- 2020On Deep Learning Techniques to Boost Monocular Depth Estimation for Autonomous Navigationcited by 17
- 2021Advances in Inference and Representation for Simultaneous Localization and Mappingcited by 16
- 2023Transformer-Based Sensor Fusion for Autonomous Driving: A Surveycited by 14
- 2023Comparing YOLOv8 and Mask R-CNN for instance segmentation in complex orchard environmentscited by 14
- 2024A Review of Transformer-Based Models for Computer Vision Tasks: Capturing Global Context and Spatial Relationshipscited by 11
- 2025Semantic Mapping in Indoor Embodied AI -- A Survey on Advances, Challenges, and Future Directionscited by 11
- 2022Visual SLAM: What are the Current Trends and What to Expect?cited by 10
- 2020A Survey of FPGA-Based Robotic Computingcited by 8
- 2022A Review on Visual-SLAM: Advancements from Geometric Modelling to Learning-based Semantic Scene Understandingcited by 8
- 2024ClearDepth: Enhanced Stereo Perception of Transparent Objects for Robotic Manipulationcited by 7
- 2024Joint Perception and Prediction for Autonomous Driving: A Surveycited by 7
- 2025World Model-Based End-to-End Scene Generation for Accident Anticipation in Autonomous Drivingcited by 7
- 2024Uncertainty-guided Optimal Transport in Depth Supervised Sparse-View 3D Gaussiancited by 6
- 2025Probabilistic Robustness in Deep Learning: A Concise yet Comprehensive Guidecited by 6
- 2022Towards Robust Part-aware Instance Segmentation for Industrial Bin Pickingcited by 5
- 2024Query-based Semantic Gaussian Field for Scene Representation in Reinforcement Learningcited by 5
- 2024Sonar-based Deep Learning in Underwater Robotics: Overview, Robustness and Challengescited by 5
- 2022The Foreseeable Future: Self-Supervised Learning to Predict Dynamic Scenes for Indoor Navigationcited by 4
- 2019Self-supervised learning for autonomous vehicles perception: A conciliation between analytical and learning methodscited by 3
- 2023Multi Object Tracking for Predictive Collision Avoidancecited by 3
- 2024Semantic Enhancement for Object SLAM with Heterogeneous Multimodal Large Language Model Agentscited by 3
- 2025Recent Advances in Transformer and Large Language Models for UAV Applicationscited by 3
- 2021Learning Spatiotemporal Occupancy Grid Maps for Lifelong Navigation in Dynamic Scenescited by 2
- 2023The Past, Current, and Future of Neonatal Intensive Care Units with Artificial Intelligencecited by 2
- 2024SLAM for Indoor Mapping of Wide Area Construction Environmentscited by 2
- 2024NeB-SLAM: Neural Blocks-based Salable RGB-D SLAM for Unknown Scenescited by 2
- 2024Multi-agent Collaborative Perception for Robotic Fleet: A Systematic Reviewcited by 2
- 2024Research on the Spatial Data Intelligent Foundation Modelcited by 2
- 2024Precision and Adaptability of YOLOv5 and YOLOv8 in Dynamic Robotic Environmentscited by 2
- 2024Survey on Fundamental Deep Learning 3D Reconstruction Techniquescited by 2
- 2024Performance Evaluation of YOLOv8 Model Configurations, for Instance Segmentation of Strawberry Fruit Development Stages in an Open Field Environmentcited by 2
- 2024Advances in Transformers for Robotic Applications: A Reviewcited by 2
- 2025Self-Supervised Learning for Robotic Leaf Manipulation: A Hybrid Geometric-Neural Approachcited by 2
- 2025Towards Depth Foundation Model: Recent Trends in Vision-Based Depth Estimationcited by 2
- 2024SSGA-Net: Stepwise Spatial Global-local Aggregation Networks for for Autonomous Drivingcited by 1
- 2024DroneVis: Versatile Computer Vision Library for Dronescited by 1
50 most cited of 56 All 56 (JSON)
Built on by
Not cited yet.