Towards Generalization in Target-Driven Visual Navigation by Using Deep Reinforcement Learning
Open accessThe DOI matches its Crossref record; 24 of the 24 references it cites were found in a registry or an index.
Abstract
Among the main challenges in robotics, target-driven visual navigation has gained increasing interest in recent years. In this task, an agent has to navigate in an environment to reach a user specified target, only through vision. Recent fruitful approaches rely on deep reinforcement learning, which has proven to be an effective framework to learn navigation policies. However, current state-of-the-art methods require to retrain, or at least fine-tune, the model for every new environment and object. In real scenarios, this operation can be extremely challenging or even dangerous. For these reasons, we address generalization in target-driven visual navigation by proposing a novel architecture composed of two networks, both exclusively trained in simulation. The first one has the objective of exploring the environment, while the other one of locating the target. They are specifically designed to work together, while separately trained to help generalization. In this article, we test our agent in both simulated and real scenarios, and validate its generalization capabilities through extensive experiments with previously unseen goals and unknown mazes, even much larger than the ones used for training.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Deep Residual Learning for Image Recognition
He, K., Zhang, X., Ren, S., & Sun, J. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.90 · Cited by 235,474
Hochreiter, S., & Schmidhuber, J. (1997) · Neural Computation · doi:10.1162/neco.1997.9.8.1735 · Cited by 102,318
You Only Look Once: Unified, Real-Time Object Detection
Redmon, J., Divvala, S., Girshick, R., & Farhadi, A. (2016) · 2016 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2016.91 · Cited by 53,803
Mastering the game of Go with deep neural networks and tree search
Silver, D., Huang, A., Maddison, C. J., Guez, A., Sifre, L., van den Driessche, G., Schrittwieser, J., Antonoglou, I., Panneershelvam, V., Lanctot, M., et al. (2016) · Nature · doi:10.1038/nature16961 · Cited by 15,612
Playing Atari with Deep Reinforcement Learning
Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., & Riedmiller, M. (2013) · arXiv · doi:10.48550/arxiv.1312.5602 · Cited by 9,471
Asynchronous Methods for Deep Reinforcement Learning
Mnih, V., Badia, A. P., Mirza, M., Graves, A., Lillicrap, T. P., Harley, T., Silver, D., & Kavukcuoglu, K. (2016) · arXiv · doi:10.48550/arxiv.1602.01783 · Cited by 7,132 · cited 4×
“Among the several DRL algorithm, e.g., deep Q-Learning [41], A3C [34], batched A2C [42], GA3C [43], we choose the recent IMPALA (Importance Weighted Actor-Learner Architecture), which, in [44], is used to simultaneously learn a large variety of complex visual tasks.”
MethodInfluentialORB-SLAM2: An Open-Source SLAM System for Monocular, Stereo, and RGB-D Cameras
Mur-Artal, R., & Tardos, J. D. (2017) · IEEE Transactions on Robotics · doi:10.1109/tro.2017.2705103 · Cited by 6,898 · cited 2×
“For example, it is possible to couple a map-based navigation algorithm [1]– [4] or simultaneous localization and mapping (SLAM) systems [5]–[8] with one of the state-of-the-art object detection or image recognition models [9], [10].”
BackgroundGrad-CAM++: Generalized Gradient-Based Visual Explanations for Deep Convolutional Networks
Chattopadhay, A., Sarkar, A., Howlader, P., & Balasubramanian, V. N. (2018) · 2018 IEEE Winter Conference on Applications of Computer Vision (WACV) · doi:10.1109/wacv.2018.00097 · Cited by 3,639
Reinforcement learning in robotics: A survey
Kober, J., Bagnell, J. A., & Peters, J. (2013) · The International Journal of Robotics Research · doi:10.1177/0278364913495721 · Cited by 3,160
Domain randomization for transferring deep neural networks from simulation to the real world
Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., & Abbeel, P. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202133 · Cited by 3,124 · cited 2×
“Like for the Maze level, we follow the approach in [49] to achieve good generalization capabilities across domains.”
MethodA solution to the simultaneous localization and map building (SLAM) problem
Dissanayake, M. W. M. G., Newman, P., Clark, S., Durrant-Whyte, H. F., & Csorba, M. (2001) · IEEE Transactions on Robotics and Automation · doi:10.1109/70.938381 · Cited by 2,661
IMPALA: Scalable Distributed Deep-RL with Importance Weighted Actor-Learner Architectures
Espeholt, L., Soyer, H., Munos, R., Simonyan, K., Mnih, V., Ward, T., Doron, Y., Firoiu, V., Harley, T., Dunning, I., et al. (2018) · arXiv · doi:10.48550/arxiv.1802.01561 · Cited by 1,708
Temporal difference learning and TD-Gammon
Tesauro, G. (1995) · Communications of the ACM · doi:10.1145/203330.203343 · Cited by 1,618
Target-driven visual navigation in indoor scenes using deep reinforcement learning
Zhu, Y., Mottaghi, R., Kolve, E., Lim, J. J., Gupta, A., Fei-Fei, L., & Farhadi, A. (2017) · 2017 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2017.7989381 · Cited by 1,533
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
Peng, X. B., Andrychowicz, M., Zaremba, W., & Abbeel, P. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460528 · Cited by 1,309 · cited 1×
“achieve sim-to-real transfer, which is successfully applied in other robotic tasks [50], [20].”
BackgroundVisual simultaneous localization and mapping: a survey
Fuentes-Pacheco, J., Ruiz-Ascencio, J., & Rendón-Mancha, J. M. (2015) · Artificial Intelligence Review · doi:10.1007/s10462-012-9365-8 · Cited by 883
Deep Image Retrieval: Learning Global Representations for Image Search
Gordo, A., Almazán, J., Revaud, J., & Larlus, D. (2016) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-46466-4_15 · Cited by 787 · cited 1×
“At this point, a triplet loss function is computed as follows [47]:”
MethodQT-Opt: Scalable Deep Reinforcement Learning for Vision-Based Robotic Manipulation
Kalashnikov, D., Irpan, A., Pastor, P., Ibarz, J., Herzog, A., Jang, E., Quillen, D., Holly, E., Kalakrishnan, M., Vanhoucke, V., et al. (2018) · arXiv · doi:10.48550/arxiv.1806.10293 · Cited by 697
CAD2RL: Real Single-Image Flight Without a Single Real Image
Sadeghi, F., & Levine, S. (2017) · Robotics: Science and Systems XIII · doi:10.15607/rss.2017.xiii.034 · Cited by 618
Learning Dexterous In-Hand Manipulation
OpenAI, Andrychowicz, M., Baker, B., Chociej, M., Jozefowicz, R., McGrew, B., Pachocki, J., Petron, A., Plappert, M., Powell, G., et al. (2018) · arXiv · doi:10.48550/arxiv.1808.00177 · Cited by 248
End-to-End Race Driving with Deep Reinforcement Learning
Jaritz, M., de Charette, R., Toromanoff, M., Perot, E., & Nashashibi, F. (2018) · 2018 IEEE International Conference on Robotics and Automation (ICRA) · doi:10.1109/icra.2018.8460934 · Cited by 210
Assessing Generalization in Deep Reinforcement Learning
Packer, C., Gao, K., Kos, J., Krähenbühl, P., Koltun, V., & Song, D. (2018) · arXiv · doi:10.48550/arxiv.1810.12282 · Cited by 114 · cited 1×
“RL algorithms, however, show a great tendency to overfit in the domain in which they are trained [23], [24].”
BackgroundGeneralization and Regularization in DQN
Farebrother, J., Machado, M. C., & Bowling, M. (2018) · arXiv · doi:10.48550/arxiv.1810.00123 · Cited by 92 · cited 1×
“RL algorithms, however, show a great tendency to overfit in the domain in which they are trained [23], [24].”
BackgroundChen, T., Wang, Z., Li, L., Li, D., Li, Z., Chang, X., Bian, P., Liang, G., Wang, Q., & Xie, T. (2025) · Schloss Dagstuhl – Leibniz-Zentrum für Informatik · doi:10.4230/lipics.ecoop.2025.6
Research works printed but not linked: 22
- 10.1109/ICCV.2017.60 · DOI · Paper page
- levine, 2016, End-to-end training of deep visuomotor policies, J Mach Learn Res, 17, 1334
- 10.1109/IROS.2018.8594249 · DOI
- 10.1109/ICRA.2019.8793493 · DOI · Paper page
- 10.1109/LRA.2019.2930426 · DOI
- 10.1023/A:1007634325138 · DOI
- mnih, 2015, Human-level control through deep reinforcement learning, Nature, 518, 529, 10.1038/nature14236 · DOI · Paper page
- 10.1109/70.88137 · DOI · Paper page
- 10.1109/21.44033 · DOI · Paper page
- 10.1177/0278364919887447 · DOI · Paper page
- 10.1109/IROS.2018.8593720 · DOI · Paper page
- sutton, 2018, Reinforcement Learning An Introduction
- greydanus, 0, Visualizing and understanding Atari agents, Proc Int Conf Mach Learn, 1787
- 10.1109/ICRA.2018.8460655 · DOI · Paper page
- 10.1109/CVPR.2017.769 · DOI · Paper page
- 10.1109/LRA.2020.2965857 · DOI
- 10.1109/ICRA.2017.7989385 · DOI · Paper page
- 10.1109/TRO.2018.2878318 · DOI · Paper page
- 10.1109/ROBOT.1995.525695 · DOI
- 10.1023/A:1008824626321 · doi:10.1023/a:1008824626321
- 10.1109/TRO.2016.2624754 · DOI · Paper page
- 10.1007/s11263-015-0816-y · DOI · Paper page
Cited by
Deep reinforcement learning based mobile robot navigation: A review
Zhu, K., & Zhang, T. (2021) · Tsinghua Science and Technology · doi:10.26599/tst.2021.9010012 · Cited by 499
Memory-Augmented Reinforcement Learning for Image-Goal Navigation
Mezghan, L., Sukhbaatar, S., Lavril, T., Maksymets, O., Batra, D., Bojanowski, P., & Alahari, K. (2022) · 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros47612.2022.9981090 · Cited by 61
“In particular, learning to explore unseen environments has been seen through the spectrum of computer vision [32], [33], SLAM-based [34], and RLbased [35], [36] approaches.”
Towards Target-Driven Visual Navigation in Indoor Scenes via Generative Imitation Learning
Wu, Q., Gong, X., Xu, K., Manocha, D., Dong, J., & Wang, J. (2021) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2020.3036597 · Cited by 47
Wang, H., Tan, A. H., & Nejat, G. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3412638 · Cited by 40
“Images of potential victims can be provided to the robots for them to search a disaster environment for these specific individuals, while avoiding collisions with rescue workers, victims, and other robots.”
BackgroundInfluentialE-VAT: An Asymmetric End-to-End Approach to Visual Active Exploration and Tracking
Dionigi, A., Devo, A., Guiducci, L., & Costante, G. (2022) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2022.3150866 · Cited by 28
Self-citation
Metadata
- Authors
- Devo, A., Mezzetti, G., Costante, G., Fravolini, M. L., & Valigi, P.
- Venue
- IEEE Transactions on Robotics
- Published
- 2020-10
- Volume
- 36
- Issue
- 5
- Pages
- 1546-1561
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W3029795912
- Cited by
- 107
- References
- 24
- FWCI
- 5.11
- Type
- journal article
- Language
- en
- Open access
- green
- Licence
- Funders
- Università degli Studi di Perugia (RICBA17MRF, RICBA18MF)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.