mlsanityData to 7 Oct 2026

Target-driven Visual Navigation in Indoor Scenes using Deep Reinforcement Learning

arXiv 1609.05143 ↗First posted 16 Sep 2016cs.CVcited by 351

Not on the map. Why?

Abstract (arXiv)

Two less addressed issues of deep reinforcement learning are (1) lack of generalization capability to new target goals, and (2) data inefficiency i.e., the model requires several (and often costly) episodes of trial and error to converge, which makes it impractical to be applied to real-world scenarios. In this paper, we address these two issues and apply our model to the task of target-driven visual navigation. To address the first issue, we propose an actor-critic model whose policy is a function of the goal as well as the current state, which allows to better generalize. To address the second issue, we propose AI2-THOR framework, which provides an environment with high-quality 3D scenes and physics engine. Our framework enables agents to take actions and interact with objects. Hence, we can collect a huge number of training samples efficiently. We show that our proposed method (1) converges faster than the state-of-the-art deep reinforcement learning methods, (2) generalizes across targets and across scenes, (3) generalizes to a real robot scenario with a small amount of fine-tuning (although the model is trained in simulation), (4) is end-to-end trainable and does not need feature engineering, feature matching between frames or 3D reconstruction of the environment. The supplementary video can be accessed at the following link: https://youtu.be/SmBxMDiOrvs.

Key facts. Cited by 351 papers in the map (data through 7 Oct 2026). First posted on arXiv 16 Sep 2016.

Builds on

No reference list yet.

Built on by

Cited by year (2026 to 7 Oct)

Citing papers per year: 2018: 2; 2019: 3; 2020: 1; 2021: 76; 2022: 64; 2023: 62; 2024: 59; 2025: 51; 2026: 33.

351 papers.

Sort:

By area:

  1. 2021PointCLIP: Point Cloud Understanding by CLIPcited by 461
  2. 2022ProcTHOR: Large-Scale Embodied AI Using Procedural Generationcited by 369
  3. 2018Reinforced Cross-Modal Matching and Self-Supervised Imitation Learning for Vision-Language Navigationcited by 304
  4. 2021A Survey of Embodied AI: From Simulators to Research Taskscited by 256
  5. 2023Diffusion-based Generation, Optimization, and Planning in 3D Scenescited by 237
  6. 2023Affordances from Human Videos as a Versatile Representation for Roboticscited by 221
  7. 2023Habitat 3.0: A Co-Habitat for Humans, Avatars and Robotscited by 220
  8. 2023Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?cited by 215
  9. 2023ViNT: A Foundation Model for Visual Navigationcited by 210
  10. 2022CoWs on Pasture: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigationcited by 194
  11. 2022ZSON: Zero-Shot Object-Goal Navigation using Multimodal Goal Embeddingscited by 177
  12. 2021BEHAVIOR: Benchmark for Everyday Household Activities in Virtual, Interactive, and Ecological Environmentscited by 161
38 more
  1. 2022GNM: A General Navigation Model to Drive Any Robotcited by 161
  2. 2024Deep Reinforcement Learning for Robotics: A Survey of Real-World Successescited by 153
  3. 2022Ditto: Building Digital Twins of Articulated Objects from Interactioncited by 152
  4. 2022PONI: Potential Functions for ObjectGoal Navigation with Interaction-free Learningcited by 149
  5. 2023Large Language Models for Robotics: A Surveycited by 132
  6. 2023Q-Transformer: Scalable Offline Reinforcement Learning via Autoregressive Q-Functionscited by 129
  7. 2023DSVT: Dynamic Sparse Voxel Transformer with Rotated Setscited by 122
  8. 2021SOON: Scenario Oriented Object Navigation with Graph-based Explorationcited by 118
  9. 2021Capturing, Reconstructing, and Simulating: the UrbanScene3D Datasetcited by 117
  10. 2022Vision-and-Language Navigation: A Survey of Tasks, Methods, and Future Directionscited by 116
  11. 2022Habitat-Web: Learning Embodied Object-Search Strategies from Human Demonstrations at Scalecited by 116
  12. 2021Recurrent Model-Free RL Can Be a Strong Baseline for Many POMDPscited by 115
  13. 2022Navigating to Objects in the Real Worldcited by 104
  14. 2021ManipulaTHOR: A Framework for Visual Object Manipulationcited by 101
  15. 2021Stabilizing Deep Q-Learning with ConvNets and Vision Transformers under Data Augmentationcited by 101
  16. 2021Structured Scene Memory for Vision-Language Navigationcited by 95
  17. 2024GOAT-Bench: A Benchmark for Multi-Modal Lifelong Navigationcited by 93
  18. 2024Mobility VLA: Multimodal Instruction Navigation with Long-Context VLMs and Topological Graphscited by 72
  19. 2024HM3D-OVON: A Dataset and Benchmark for Open-Vocabulary Object Goal Navigationcited by 71
  20. 2022Adversarial Motion Priors Make Good Substitutes for Complex Reward Functionscited by 68
  21. 2023OVRL-V2: A simple state-of-art baseline for ImageNav and ObjectNavcited by 68
  22. 2022Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigationcited by 66
  23. 2021Memory-Augmented Reinforcement Learning for Image-Goal Navigationcited by 64
  24. 2021The ThreeDWorld Transport Challenge: A Visually Guided Task-and-Motion Planning Benchmark for Physically Realistic Embodied AIcited by 64
  25. 2021No RL, No Simulation: Learning to Navigate without Navigatingcited by 63
  26. 2021Mind Your Outliers! Investigating the Negative Impact of Outliers on Active Learning for Visual Question Answeringcited by 62
  27. 2021A Survey of Deep RL and IL for Autonomous Driving Policy Learningcited by 59
  28. 2023Multi-Stage Cable Routing through Hierarchical Imitation Learningcited by 59
  29. 2022CAGroup3D: Class-Aware Grouping for 3D Object Detection on Point Cloudscited by 58
  30. 2022ViKiNG: Vision-Based Kilometer-Scale Navigation with Geographic Hintscited by 55
  31. 2022Instance-Specific Image Goal Navigation: Training Embodied Agents to Find Object Instancescited by 53
  32. 2023SayNav: Grounding Large Language Models for Dynamic Planning to Navigation in New Environmentscited by 53
  33. 2021RobustNav: Towards Benchmarking Robustness in Embodied Navigationcited by 52
  34. 2024SAFDNet: A Simple and Effective Network for Fully Sparse 3D Object Detectioncited by 52
  35. 2021VTNet: Visual Transformer Network for Object Goal Navigationcited by 50
  36. 2023Navigating to Objects Specified by Imagescited by 50
  37. 2024GaussNav: Gaussian Splatting for Visual Navigationcited by 49
  38. 2021Learning to Map for Active Semantic Goal Navigationcited by 47

50 most cited of 351 All 351 (JSON)