Navigating to objects in the real world
Open accessThe DOI matches its Crossref record; 106 of the 106 references it cites were found in a registry or an index.
Abstract
Semantic navigation is necessary to deploy mobile robots in uncontrolled environments such as homes or hospitals. Many learning-based approaches have been proposed in response to the lack of semantic understanding of the classical pipeline for spatial navigation, which builds a geometric map using depth sensors and plans to reach point goals. Broadly, end-to-end learning approaches reactively map sensor inputs to actions with deep neural networks, whereas modular learning approaches enrich the classical pipeline with learning-based semantic sensing and exploration. However, learned visual navigation policies have predominantly been evaluated in sim, with little known about what works on a robot. We present a large-scale empirical study of semantic visual navigation methods comparing representative methods with classical, modular, and end-to-end learning approaches across six homes with no prior experience, maps, or instrumentation. We found that modular learning works well in the real world, attaining a 90% success rate. In contrast, end-to-end learning does not, dropping from 77% sim to a 23% real-world success rate because of a large image domain gap between sim and reality. For practitioners, we show that modular learning is a reliable approach to navigate to objects: Modularity and abstraction in policy design enable sim-to-real transfer. For researchers, we identify two key issues that prevent today’s simulators from being reliable evaluation benchmarks—a large sim-to-real gap in images and a disconnect between sim and real-world error modes—and propose concrete steps forward.
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.
Claims other papers make about this one
Each is checked against this paper’s own text: does it say what the citing paper says it does?
The source backs part of the claim, not all of it — or backs it for a different population, condition or comparison.
In the citing paper
“Low-level navigation policies are typically derived from deterministic path planning conditioned on environmental constraints and high-level spatial goals52.”
From Brain-inspired spatial intelligence for embodied agents (2026) · cites this paper as [52]
Experimental — accuracy not yet measured
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 · cited 3×
“Depth features were computed with a ResNet50 pretrained on point goal navigation (44).”
MethodHuman-level control through deep reinforcement learning
Mnih, V., Kavukcuoglu, K., Silver, D., Rusu, A. A., Veness, J., Bellemare, M. G., Graves, A., Riedmiller, M., Fidjeland, A. K., Ostrovski, G., et al. (2015) · Nature · doi:10.1038/nature14236 · Cited by 30,357 · cited 1×
“Inspired by seminal proofs of concept in autonomous driving [26, 27] and early successes of pixel-to-action deep reinforcement learning [28, 29], early applications of end-to-end learning to semantic navigation include [30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40].”
BackgroundHe, K., Gkioxari, G., Dollar, P., & Girshick, R. (2017) · 2017 IEEE International Conference on Computer Vision (ICCV) · doi:10.1109/iccv.2017.322 · Cited by 29,137
Empirical Evaluation of Gated Recurrent Neural Networks on Sequence Modeling
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014) · arXiv · doi:10.48550/arxiv.1412.3555 · Cited by 11,008 · cited 4×
“RGB, depth, and semantic frames are then fed into a GRU [109] along with other low dimensional features — the robot pose, a learnable goal object embedding, the fraction of the visual input occupied by the goal category, and the previous action — to predict a distribution over next actions.”
BackgroundInfluentialContinuous control with deep reinforcement learning
Lillicrap, T. P., Hunt, J. J., Pritzel, A., Heess, N., Erez, T., Tassa, Y., Silver, D., & Wierstra, D. (2015) · arXiv · doi:10.48550/arxiv.1509.02971 · Cited by 10,782 · cited 1×
“Inspired by seminal proofs of concept in autonomous driving [26, 27] and early successes of pixel-to-action deep reinforcement learning [28, 29], early applications of end-to-end learning to semantic navigation include [30, 31, 32, 33, 34, 35, 36, 37, 38, 39, 40].”
BackgroundA robust layered control system for a mobile robot
Brooks, R. (1986) · IEEE Journal on Robotics and Automation · doi:10.1109/jra.1986.1087032 · Cited by 7,799
KinectFusion: Real-time dense surface mapping and tracking
Newcombe, R. A., Fitzgibbon, A., Izadi, S., Hilliges, O., Molyneaux, D., Kim, D., Davison, A. J., Kohi, P., Shotton, J., & Hodges, S. (2011) · 2011 10th IEEE International Symposium on Mixed and Augmented Reality · doi:10.1109/ismar.2011.6092378 · Cited by 4,008 · cited 1×
“Among approaches that can operate in unseen environments, classical approaches typically build a geometric map of the environment using depth sensors [12, 13, 14], and later a monocular RGB camera [15, 16, 17], while simultaneously localizing the robot relative to its growing map.”
BackgroundMonoSLAM: Real-time single camera SLAM
Davison, A. J., Reid, I. D., Molton, N. D., & Stasse, O. (2007) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2007.1049 · Cited by 3,959 · cited 1×
“Among approaches that can operate in unseen environments, classical approaches typically build a geometric map of the environment using depth sensors [12, 13, 14], and later a monocular RGB camera [15, 16, 17], while simultaneously localizing the robot relative to its growing map.”
BackgroundThe dynamic window approach to collision avoidance
Fox, D., Burgard, W., & Thrun, S. (1997) · IEEE Robotics & Automation Magazine · doi:10.1109/100.580977 · Cited by 3,771 · cited 1×
“Navigation has been studied in robotics literature for over three decades [2, 3, 4, 5, 6, 7, 8, 9, 10, 11, 12, 13].”
BackgroundA fast marching level set method for monotonically advancing fronts.
Sethian, J. A. (1996) · Proceedings of the National Academy of Sciences · doi:10.1073/pnas.93.4.1591 · Cited by 3,221 · cited 1×
“Planner Given a long-term goal output by the frontier or semantic exploration policy, we used the fast marching method (112) as in (63) to plan a path and the first low-level action along this path deterministically.”
Method
Research works printed but not linked: 16
- H. P. Moravec Obstacle avoidance and navigation in the real world by a seeing robot rover thesis Stanford University Palo Alto CA (1980).
- S. Thrun Robotic mapping: A survey in Exploring Artificial Intelligence in the New Millennium (Morgan Kaufmann Publishers Inc. 2002) pp. 1–35.
- U. Muller J. Ben E. Cosatto B. Flepp Y. Cun Off-road obstacle avoidance through end-to-end learning in Advances in Neural Information Processing Systems (MIT Press 2005) vol. 18.
- P. Mirowski R. Pascanu F. Viola H. Soyer A. Ballard A. Banino M. Denil R. Goroshin L. Sifre K. Kavukcuoglu D. Kumaran R. Hadsell Learning to navigate in complex environments ” paper presented at the 5th International Conference on Learning Representations Toulon France 24 to 26 2017 (ICLR 2017).
- A. Dosovitskiy V. Koltun “Learning to act by predicting the future ” paper presented at the 5th International Conference on Learning Representations Toulon France 24 to 26 2017 (ICLR 2017).
- P. Mirowski M. K. Grimes M. Malinowski K. M. Hermann K. Anderson D. Teplyashin K. Simonyan K. Kavukcuoglu A. Zisserman R. Hadsell Learning to navigate in cities without a map in Advances in Neural Information Processing Systems (Curran Associates Inc. 2018) vol. 31 pp. 2419–2430.
- E. Parisotto R. Salakhutdinov Neural map: Structured memory for deep reinforcement learning in International Conference on Learning Representations (ICLR) (2018).
- D. S. Chaplot E. Parisotto R. Salakhutdinov Active neural localization in International Conference on Learning Representations (ICLR) (2018).
- D. S. Chaplot D. P. Gandhi A. Gupta R. R. Salakhutdinov Object goal navigation using goal-oriented semantic exploration in Advances in Neural Information Processing Systems (Curran Associates Inc. 2020) vol. 33 p. 4247.
- M. Hahn D. S. Chaplot S. Tulsiani M. Mukadam J. M. Rehg A. Gupta No RL no simulation: Learning to navigate without navigating in Advances in Neural Information Processing Systems (Curran Associates Inc. 2021) vol. 34.
- X. Liu, H. Palacios, C. Muise, A planning based neural-symbolic approach for embodied instruction following. Interactions 9, 17 (2022).
- D. S. Chaplot M. Dalal S. Gupta J. Malik R. Salakhutdinov SEAL: Self-supervised Embodied Active Learning using exploration and 3D consistency in Advances in Neural Information Processing Systems (Curran Associates Inc. 2021).
- E. Kolve R. Mottaghi W. Han E. V. Bilt L. Weihs A. Herrasti M. Deitke K. Ehsani D. Gordon Y. Zhu A. Kembhavi A. Gupta A. Farhadi AI2-THOR: An interactive 3D environment for visual AI. arXiv:1712.05474 [cs.CV] (26 August 2022). · arXiv
- D. Kalashnikov A. Irpan P. Pastor J. Ibarz A. Herzog E. Jang D. Quillen E. Holly M. Kalakrishnan V. Vanhoucke S. Levine “Scalable deep reinforcement learning for vision-based robotic manipulation ” paper presented at the 2nd Annual Conference on Robot Learning (CoRL 2018) Zürich Switzerland 29 to 31 October 2018 pp. 651–673.
- A. Szot A. Clegg E. Undersander E. Wijmans Y. Zhao J. Turner N. Maestre M. Mukadam D. Chaplot O. Maksymets A. Gokaslan V. Vondrus S. Dharur F. Meier W. Galuba A. Chang Z. Kira V. Koltun J. Malik M. Savva D. Batra Habitat 2.0: Training home assistants to rearrange their habitat in Advances in Neural Information Processing Systems (Curran Associates Inc. 2021) vol. 34 p. 251.
- A. Murali T. Chen K. V. Alwala D. Gandhi L. Pinto S. Gupta A. Gupta PyRobot: An open-source robotics framework for research and benchmarking. arXiv:1906.08236 [cs.RO] (19 June 2019). · arXiv
Cited by
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
Chen, B., Xu, Z., Kirmani, S., Ichter, B., Sadigh, D., Guibas, L., & Xia, F. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01370 · Cited by 281
“When applying these spatial concepts to reasoning, prior works often focus on explicit spatial scene memories [26, 27] or spatial scene graphs [29, 30, 59, 60].”
MethodDeep Reinforcement Learning for Robotics: A Survey of Real-World Successes
Tang, C., Abbatematteo, B., Hu, J., Chandra, R., Martín-Martín, R., & Stone, P. (2025) · Annual Review of Control, Robotics, and Autonomous Systems · doi:10.1146/annurev-control-030323-022510 · Cited by 177
SpatialVLM: Endowing Vision-Language Models with Spatial Reasoning Capabilities
Chen, B., Xu, Z., Kirmani, S., Ichter, B., Driess, D., Florence, P., Sadigh, D., Guibas, L., & Xia, F. (2024) · arXiv · doi:10.48550/arxiv.2401.12168 · Cited by 269
“When applying these spatial concepts to reasoning, prior works often focus on explicit spatial scene memories [26, 27] or spatial scene graphs [29, 30, 59, 60].”
MethodFoundation models in robotics: Applications, challenges, and the future
Firoozi, R., Tucker, J., Tian, S., Majumdar, A., Sun, J., Liu, W., Zhu, Y., Song, S., Kapoor, A., Hausman, K., et al. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649241281508 · Cited by 238
“Semantic navigation [142] seeks to address this question by presenting an empirical analysis of semantic visual navigation methods.”
NoMaD: Goal Masked Diffusion Policies for Navigation and Exploration
Sridhar, A., Shah, D., Glossop, C., & Levine, S. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610665 · Cited by 471
“However, policies trained in simulation tend to transfer poorly to real-world environments [16, 22], and our experiments reveal that even the best exploration policies trained on real-world data perform poorly in complex indoor and outdoor environments.”
BackgroundCLIP-Fields: Weakly Supervised Semantic Fields for Robotic Memory
(Mahi)Shafiullah, N., Paxton, C., Pinto, L., Chintala, S., & Szlam, A. (2023) · Robotics: Science and Systems XIX · doi:10.15607/rss.2023.xix.074 · Cited by 82
“In order to perform a variety of complex tasks in human environments, robots often rely on a spatial semantic memory [2, 19, 11].”
BackgroundSelf-citationEmbodied Intelligence: A Synergy of Morphology, Action, Perception and Learning
Liu, H., Guo, D., & Cangelosi, A. (2025) · ACM Computing Surveys · doi:10.1145/3717059 · Cited by 200
“Reference [57] constructs an actual physical scene to comprehensively evaluate the performance difference of different methods in the simulation and physical environments.”
ETPNav: Evolving Topological Planning for Vision-Language Navigation in Continuous Environments
An, D., Wang, H., Wang, W., Wang, Z., Huang, Y., He, K., & Wang, L. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2024.3386695 · Cited by 103
Khanna, M., Mao, Y., Jiang, H., Haresh, S., Shacklett, B., Batra, D., Clegg, A., Undersander, E., Chang, A. X., & Savva, M. (2024) · 2024 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr52733.2024.01550 · Cited by 63
“This progress is supported by simulation platforms that enable systematic, safe, and scalable training and evaluation of embodied AI agents before deployment to the real world [19, 21, 34, 36, 37].”
BackgroundSelf-citationHow Far Are We From AGI: Are LLMs All We Need?
Feng, T., Jin, C., Liu, J., Zhu, K., Tu, H., Cheng, Z., Lin, G., & You, J. (2024) · Transactions on machine learning research · doi:10.48550/arxiv.2405.10313 · Cited by 94
Robot learning in the era of foundation models: a survey
Xiao, X., Liu, J., Wang, Z., Zhou, Y., Qi, Y., Jiang, S., He, B., & Cheng, Q. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.129963 · Cited by 89
GaussNav: Gaussian Splatting for Visual Navigation
Lei, X., Wang, M., Zhou, W., & Li, H. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3538496 · Cited by 101
“Gervet et al. [68] conduct a Sim2Real transfer of both modular and end-to-end systems, demonstrating that modularity effectively mitigates the visual Sim2Real gap that impairs the performance of end-to-end policies.”
A Survey of Embodied Learning for Object-centric Robotic Manipulation
Zheng, Y., Yao, L., Su, Y., Zhang, Y., Wang, Y., Zhao, S., Zhang, Y., & Chau, L. (2025) · Machine Intelligence Research · doi:10.1007/s11633-025-1542-8 · Cited by 89
Dynamem: Online Dynamic Spatio-Semantic Memory for Open World Mobile Manipulation
Liu, P., Guo, Z., Warke, M., Chintala, S., Paxton, C., Shafiullah, N. M. M., & Pinto, L. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127619 · Cited by 70
“This line of query follows Open-Vocabulary Navigation systems [5, 21], which builds upon prior object and point goal navigation literature [12, 14, 22– 28] which attempted navigation to points, or fixed set of objects and object categories.”
Self-citationCAST: Counterfactual Labels Improve Instruction Following in Vision-Language-Action Models
Glossop, C., Chen, W., Bhorkar, A., Shah, D., & Levine, S. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3726383 · Cited by 53
“These instructions cover a wider range of behaviors than commonly studied in object navigation [15], [34], [50] and atomic instruction-following literature [24], and focus on steer-ability rather than long-horizon navigation.”
PEANUT: Predicting and Navigating to Unseen Targets
Zhai, A. J., & Wang, S. (2023) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01003 · Cited by 65
“To leverage semantic priors for goal selection, SemExp [10] built a top-down semantic map and used it to train an RL-based policy that minimizes distance to target objects, winning the 2020 Habitat ObjectNav Challenge.”
A Survey of Object Goal Navigation
Sun, J., Wu, J., Ji, Z., & Lai, Y. (2024) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2024.3378010 · Cited by 82
“Then they use an instance grounding module to select the final instance prediction from several ground truth candidates provided by the simulator.”
The Reality Gap in Robotics: Challenges, Solutions, and Best Practices
Aljalbout, E., Xing, J., Romero, A., Akinola, I., Garrett, C. R., Heiden, E., Gupta, A. K., Hermans, T., Narang, Y., Fox, D., et al. (2025) · Annual Review of Control Robotics and Autonomous Systems · doi:10.1146/annurev-control-031924-100130 · Cited by 75
Navigating to Objects Specified by Images
Krantz, J., Gervet, T., Yadav, K., Wang, A., Paxton, C., Mottaghi, R., Batra, D., Malik, J., Lee, S., & Singh Chaplot, D. (2023) · 2023 IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51070.2023.01002 · Cited by 34
“This method takes the semantic segmentation form of modular ObjectNav [9, 18].”
BackgroundMethodInfluentialSelf-citationEmbodied AI: A Survey on the Evolution from Perceptive to Behavioral Intelligence
Yifan, C., Wei, M., Wang, X., Liu, Y., Wang, J., Song, H., Ma, L., Di, D., Sun, C., Liu, K., et al. (2025) · SmartBot · doi:10.1002/smb2.70003 · Cited by 43
Open-Ended Instructable Embodied Agents with Memory-Augmented Large Language Models
Sarch, G., Wu, Y., Tarr, M., & Fragkiadaki, K. (2023) · Findings of the Association for Computational Linguistics: EMNLP 2023 · doi:10.18653/v1/2023.findings-emnlp.226 · Cited by 25
Semantic Mapping in Indoor Embodied AI -- A Survey on Advances, Challenges, and Future Directions
Raychaudhuri, S., & Chang, A. X. (2025) · Transactions on machine learning research · doi:10.48550/arxiv.2501.05750 · Cited by 40
Zero-Shot Object Navigation with Vision-Language Models Reasoning
Wen, C., Huang, Y., Huang, H. M., Huang, Y., Yuan, S., Hao, Y., Lin, H., Liu, Y.-S., & Fang, Y. (2024) · Lecture notes in computer science · doi:10.1007/978-3-031-78456-9_25 · Cited by 45
NaviDiffusor: Cost-Guided Diffusion Model for Visual Navigation
Zeng, Y., Ren, H., Wang, S., Huang, J., & Cheng, H. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11127466 · Cited by 41
“These works demonstrate remarkable performance, offering opportunities to learn semantic priors for goal-directed exploration [25], while they require large datasets and extensive training to be transferable to new scenes.”
ViHOPE: Visuotactile In-Hand Object 6D Pose Estimation With Shape Completion
Li, H., Dikhale, S., Iba, S., & Jamali, N. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3313941 · Cited by 33
“…in isolation, and weights are frozen; ii) The shape completion module ( G + F ) is trained; iii) The pose estimator ( T t + T r ) is trained while freezing the shape completion module; iv) the shape completion module in unfrozen and trained end-to-end ( G + F + T t + T r ), similar to [34], [35].”
MethodYang, R., Kim, Y., Hendrix, R., Kembhavi, A., Wang, X., & Ehsani, K. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802201 · Cited by 41
“On one hand, agents have been trained to efficiently explore and navigate environments [6, 11, 19, 47], while on the other, substantial progress has been made in performing complex manipulation tasks, such as handling articulated objects with static arms in tabletop settings [26, 32, 40, 51].”
AutoNeRF: Training Implicit Scene Representations with Autonomous Agents
Marza, P., Matignon, L., Simonin, O., Batra, D., Wolf, C., & Chaplot, D. S. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802101 · Cited by 24
“Among these methods, modular learning meth-ods have been very effective at various embodied tasks [1], [4], [11].”
Self-citationHuang, J., Chen, K., Zhou, J., Lin, X., Abbeel, P., Dou, Q., & Liu, Y. (2025) · IEEE/ASME Transactions on Mechatronics · doi:10.1109/tmech.2025.3532653 · Cited by 26
“However,these approachesrelyondual-armoperationswithtwo-fingergrippers [29],[30],[31],[32],[33],[34],limitingthescopeofrobotic manipulationtasks,suchasopeningabottlecap[35],whichis challengingtoachieve.”
g3D-LF: Generalizable 3D-Language Feature Fields for Embodied Tasks
Wang, Z., & Lee, G. H. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.01324 · Cited by 43
“However, these navigation models are often limited to specific objects, making open-vocabulary navigation challenging and hindering generalization in real-world applications [17].”
Chen, B., Kang, J., Zhong, P., Cui, Y., Lu, S., Liang, Y., & Wang, J. (2023) · IEEE Transactions on Circuits and Systems for Video Technology · doi:10.1109/tcsvt.2023.3324380 · Cited by 27
“Perceiving the environment through a fine-grained semantic map representation is helpful for navigation tasks [24].”
BackgroundMethodInfluentialFast and Comfortable Robot-to-Human Handover for Mobile Cooperation Robot System
Meng, C., Zhang, T., Zhao, D. X., & Lam, T. L. (2024) · Cyborg and Bionic Systems · doi:10.34133/cbsystems.0120 · Cited by 22
“These improvements are largely attributed to sophisticated learning or optimization techniques [8,9].”
BackgroundCorNav: Autonomous Agent with Self-Corrected Planning for Zero-Shot Vision-and-Language Navigation
Liang, X., Ma, L., Guo, S., Han, J., Xu, H., Ma, S., & Liang, X. (2024) · Findings of the Association for Computational Linguistics: ACL (Findings of ACL) · doi:10.18653/v1/2024.findings-acl.745 · Cited by 24
MonoNav: MAV Navigation via Monocular Depth Estimation and Reconstruction
Simon, N., & Majumdar, A. (2024) · Springer proceedings in advanced robotics · doi:10.1007/978-3-031-63596-0_37 · Cited by 29
Resilient Timed Elastic Band Planner for Collision‐Free Navigation in Unknown Environments
Kulathunga, G., Yılmaz, A., Huang, Z., Hroob, I., Arunachalam, H., Guevara, L., Klimchik, A. S., Cielniak, G., & Hanheide, M. (2025) · Journal of Field Robotics · doi:10.1002/rob.22602 · Cited by 17
“This approach leverages the strengths of the TEB planner along with the proposed recovery strategy, all while maintaining a moderate computational load.”
Habitat 3.0: A Co-Habitat for Humans, Avatars, and Robots
Puig, X., Undersander, E., Szot, A., Cote, M. D., Yang, T.-Y., Partsey, R., Desai, R., Clegg, A. W., Hlavac, M., Min, S. Y., et al. (2023) · arXiv · doi:10.48550/arxiv.2310.13724 · Cited by 15
“…are largely hermits – existing within and navigating through virtual worlds as solitary occupants (Batra et al., 2020; Anderson et al., 2017; Zhu et al., 2017; Chen et al., 2020; Krantz et al., 2020; Ku et al., 2020; Wani et al., 2020; Xia et al., 2020; Deitke et al., 2020; Gervet et al., 2023) 2 .”
BackgroundSelf-citationAdachi, M., Honda, K., Xue, J., Sudo, H., Ueda, Y., Yuda, Y., Wada, M., & Miyamoto, R. (2023) · Journal of Robotics and Mechatronics · doi:10.20965/jrm.2023.p1419 · Cited by 16
Sun, L., Kanezaki, A., Caron, G., & Yoshiyasu, Y. (2025) · Advanced Engineering Informatics · doi:10.1016/j.aei.2025.103135 · Cited by 23
“For instance, our tests were conducted in a Japanese-style house, which differs significantly from the American-style houses used in [14].”
BackgroundMethodResultInfluentialMOPA: Modular Object Navigation with PointGoal Agents
Raychaudhuri, S., Campari, T., Jain, U., Savva, M., & Chang, A. X. (2024) · IEEE Winter Conference on Applications of Computer Vision · doi:10.1109/wacv57701.2024.00566 · Cited by 27
“6 shows that our OracleSem and Pred-Sem agents outperform ModLearn [23], an approach using learned semantic exploration (SemExp) with FMM as the low-level navigation module, on Success (rows 1 vs 2 and 3 vs 4,5).”
BackgroundMethodInfluentialYang, B., Yuan, X., Ying, Z., Zhang, J., Song, B., Song, Y. H., Zhou, F., & Sheng, W. (2024) · Advanced Engineering Informatics · doi:10.1016/j.aei.2024.102671 · Cited by 15
AerialVG: A Challenging Benchmark for Aerial Visual Grounding by Exploring Positional Relations
Liu, J., Chen, Q., Wang, Z., Tang, Y., Zhang, Y., Yan, C., Wang, D., Li, X., & Zhao, B. L. (2025) · IEEE/CVF International Conference on Computer Vision (ICCV) · doi:10.1109/iccv51701.2025.00492 · Cited by 22
“…like SLAM [1, 11] or depth estimation [12], has seen increasing interest in the context of VLMs. Earlier research focused on explicit spatial scene representations, such as spatial memory [15, 16] or spatial scene graphs [19, 43], to help machines understand and reason about spatial relations.”
Exploitation-Guided Exploration for Semantic Embodied Navigation
Wasserman, J., Chowdhary, G. V., Gupta, A., & Jain, U. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610117 · Cited by 25
HOZ++: Versatile Hierarchical Object-to-Zone Graph for Object Navigation
Zhang, S., Song, X., Yu, X., Bai, Y., Guo, X., Li, W., & Jiang, S. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3552987 · Cited by 23
“Conversely, the modular methods perform well in complex environments [11], [58] and generalize well from sim-to-real [65].”
USA-Net: Unified Semantic and Affordance Representations for Robot Memory
Bolte, B., Wang, A., Yang, J. C., Mukadam, M., Kalakrishnan, M., & Paxton, C. (2023) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros55552.2023.10341737 · Cited by 15
“While many solutions for complex vision-language navigation tasks build either a 2D or 3D map [3], [10], [23], these approaches build their maps explicitly, specifically updating obstacle locations and object classes.”
BackgroundYenamandra, S., Ramachandran, A., Khanna, M., Yadav, K., Vakil, J., Melnik, A., Büttner, M., Harz, L., Brown, L., Nandi, G. C., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2407.06939 · Cited by 14
“This makes simulation-based challenges quite appealing, but unfortunately it’s not so clear how well simulations transfer to the real world Deitke et al. [2022]; in fact, there’s strong evidence they do not transfer particularly well Gervet et al. [2022].”
BackgroundSelf-citationDong, Q., Zhang, X., Zhang, S., Wang, Z., Ma, Z., & Xi, H. (2026) · IEEE Transactions on Industrial Electronics · doi:10.1109/tie.2025.3639779 · Cited by 13
“The works in [27], [38] employ modular reinforcement learning frameworks for efficient visual exploration in unknown environments and provide systematic evaluations across realistic settings.”
Co-Optimizing Reconfigurable Environments and Policies for Decentralized Multiagent Navigation
Gao, Z., Yang, G., & Prorok, A. (2025) · IEEE Transactions on Robotics · doi:10.1109/tro.2025.3588449 · Cited by 11
“SPL is the gold standard to measure the performance of robot navigation in literature [54], [55], [56] defined as where s i is a binary indicator for the success of agent A i , p i is the traveled distance, and (cid:11) i is the shortest distance.”
SemNav-HRO: A target-driven semantic navigation strategy with human–robot–object ternary fusion
Chen, B., Lu, S., Zhong, P., Cui, Y., Liang, Y., & Wang, J. (2023) · Engineering Applications of Artificial Intelligence · doi:10.1016/j.engappai.2023.107370 · Cited by 11
Unifying Foundation Models with Quadrotor Control for Visual Tracking Beyond Object Categories
Saviolo, A., Rao, P., Radhakrishnan, V., Xiao, J., & Loianno, G. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610111 · Cited by 15
Towards Physically Realizable Adversarial Attacks in Embodied Vision Navigation
Chen, M., Tu, J., Qi, C., Dang, Y., Zhou, F., Wei, W., & Yin, J. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11246438 · Cited by 14
“Embodied vision navigation [1], [2] refers to an agent moving towards a target object or a designated location in an unseen environment.”
Constrained Environment Optimization for Prioritized Multi-Agent Navigation
Gao, Z., & Prorok, A. (2023) · IEEE Open Journal of Control Systems · doi:10.1109/ojcsys.2023.3316090 · Cited by 9
Learning to Navigate Efficiently and Precisely in Real Environments
Bono, G., Poirier, H., Antsfeld, L., Monaci, G., Chidlovskii, B., & Wolf, C. (2024) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52733.2024.01689 · Cited by 13
“Actions taken — Figure 9 shows histograms of the actions taken by the action in simulation and in real on Office/20.”
InfluentialVisual semantic navigation with real robots
Gutiérrez-Álvarez, C., Ríos-Navarro, P., Flor-Rodríguez-Rabadán, R., Acevedo-Rodríguez, F. J., & López-Sastre, R. J. (2024) · Applied Intelligence · doi:10.1007/s10489-024-06115-4 · Cited by 10
Vashisht, A., Gandhi, G. C., Kalra, S., & Saini, D. K. (2025) · Computers & Electrical Engineering · doi:10.1016/j.compeleceng.2025.110375 · Cited by 9
Socially Aware Object Goal Navigation With Heterogeneous Scene Representation Learning
Chen, B., Zhu, H., Yao, S., Lu, S., Zhong, P., Sheng, Y., & Wang, J. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3414253 · Cited by 15
“Inspired by existing work [5], [11], we propose a novel HSR learning method by representing scenes as semantic maps and heterogeneous scene graphs for HRO ternary feature fusion.”
BackgroundMethodAim My Robot: Precision Local Navigation to Any Object
Meng, X., Yang, X., Jung, S., Ramos, F. T., Jujjavarapu, S. S., Paul, S. K., & Fox, D. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3542323 · Cited by 10
“Object-goal and instance-goal navigation: Object-goal navigation typically refers to a robot navigating to any object of the specified category (e.g., couch) [15], [33], [34].”
Xie, F., Schwertfeger, S., & Blum, H. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3653280 · Cited by 12
“For example, [9] construct a 2D semantic map from projecting Mask-RCNN-based instance seg-mentations.”
SysNav: Multi-Level Systematic Cooperation Enables Real-World, Cross-Embodiment Object Navigation
Zhu, H., Li, Z., Liu, Z., Guo, K., Lin, Z., Cai, Y., Chen, G., Lv, C., Wang, W., Oh, J., et al. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3713730 · Cited by 10
“Frontier-based meth-ods[9],[16],[24],[25],[26]recordfrontiersongridmapsandin-corporatesemanticcuesforexploration.”
Active Neural Mapping at Scale
Kuang, Z., Yan, Z., Zhao, H., Zhou, G., & Zha, H. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801913 · Cited by 14
“This is usually achieved in a modular [25], [26] or end-to-end [27], [28] fashion.”
TANGO: Training-free Embodied AI Agents for Open-world Tasks
Ziliotto, F., Campari, T., Serafini, L., & Ballan, L. (2025) · IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings - IEEE Computer Society Conference on Computer Vision and Pattern Recognition/Proceedings · doi:10.1109/cvpr52734.2025.02291 · Cited by 53
“The main contribution of this paper is to extend these ideas to embodied visual navigation, that usually require heavy end-to-end learning, although modular approaches have recently shown promising results [7, 17].”
Map-based Modular Approach for Zero-shot Embodied Question Answering
Sakamoto, K., Azuma, D., Miyanishi, T., Kurita, S., & Kawanabe, M. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10801314 · Cited by 14
“Recent studies of semantic visual navigation [13] indicate that modular learning approaches are effective in real-world scenarios, whereas end-to-end learning approaches fail due to a significant domain gap in visual observations between simulations and reality.”
Sakaguchi, T., Taniguchi, A., Hagiwara, Y., Hafi, L. E., Hasegawa, S., & Taniguchi, T. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802697 · Cited by 10
“[ 16].”
NavWM: A Unified Navigation World Model for Foresight-Driven Planning
Mei, Y., Guo, L., Ming-ming, Y., Zhao, G., He, X., & Liu, J. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37372-4_21 · Cited by 7
An Object-Driven Navigation Strategy Based on Active Perception and Semantic Association
Guo, Y., Sun, J., Zhang, R., Jiang, Z., Mi, Z., Yao, C., Ban, X., & Obaidat, M. S. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3418269 · Cited by 11
“Given that learning-based methods require a large amount of data annotation and generally achieve poor generalization on test set [12], some scholars have proposed modular methods, which mainly consist of a series of modules that form a navigation strategy [13], [14].”
BackgroundReinforcement Learning and Control
Imran, A., & Gopalakrishnan, K. (2025) · Apress eBooks · doi:10.1007/979-8-8688-0989-7_7 · Cited by 6
Development and Adaptation of Robotic Vision in the Real World: The Challenge of Door Detection
Antonazzi, M., Luperto, M., Borghese, N. A., & Basilico, N. (2025) · Journal of Field Robotics · doi:10.1002/rob.70084 · Cited by 8
“This limitation is something we empirically assess in our experimental campaign.”
Sun, L., & Yoshiyasu, Y. (2025) · Image and Vision Computing · doi:10.1016/j.imavis.2025.105522 · Cited by 8
ForesightNav: Learning Scene Imagination for Efficient Exploration
Shah, H., Xing, J., Messikommer, N., Sun, B., Pollefeys, M., & Scaramuzza, D. (2025) · IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW) · doi:10.1109/cvprw67362.2025.00519 · Cited by 15
“In [15], it is shown that modular approaches that use an intermediate scene representation outperform end-to-end approaches and transfer the best from sim to real, which further reinforces our decision to use GeoSem Maps as an intermediate representation.”
SemNav: Enhancing visual semantic navigation in robotics through semantic segmentation
Flor-Rodríguez-Rabadán, R., Gutiérrez-Álvarez, C., Acevedo-Rodríguez, F. J., Lafuente-Arroyo, S., & López-Sastre, R. J. (2026) · Applied Intelligence · doi:10.1007/s10489-026-07275-1 · Cited by 5
“In fact, only a few studies have attempted to evaluate VSN solutions in real-world settings [23], [24], [12].”
DISCOVERSE: Efficient Robot Simulation in Complex High-Fidelity Environments
Jia, Y., Wang, G., Dong, Y., Wu, J., Zeng, Y., Lin, H., Wang, Z., Ge, H., Gu, W., Ding, K., et al. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247559 · Cited by 10
“The underlying physical engines [1], [22] enable high-throughput simulation of accurate contact, collision, and deformation dynamics, empowering a variety of complex robotic tasks [11], [20], [23].”
Bio-inspired cognitive navigation for robots
Hao, Z., Guo, B., Ding, Y., Li, L., Liu, S., Gao, T., Liu, S., & Yu, Z. (2026) · Nature Reviews Electrical Engineering · doi:10.1038/s44287-026-00294-7 · Cited by 7
“Although general-purpose foundation models have shown promise in reasoning through chain-of-thought processes, their application to vision–language navigation is hindered by data scarcity 133 and domain-shift gaps that compromise real-world adaptation 134 .”
Salience Interest Option: Temporal abstraction with salience interest functions
Zhu, X., Zhao, L., & Zhu, W. (2024) · Neural Networks · doi:10.1016/j.neunet.2024.106342 · Cited by 5
Measure for Semantics and Semantically Constrained Pose Optimization: A Review
Xia, L., Li, S., Yi, L., Ruan, H., & Zhang, D. (2024) · IEEE Transactions on Instrumentation and Measurement · doi:10.1109/tim.2024.3428639 · Cited by 7
“However, object-level image understanding needs semantic observation [10].”
BackgroundHSPNav: Hierarchical Scene Prior Learning for Visual Semantic Navigation Towards Real Settings
Kang, J., Chen, B., Zhong, P., Yang, H., Sheng, Y., & Wang, J. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610061 · Cited by 10
“As justified in [1], the reason is that directly processing sophisticated visual images may lead to poor 9438 Authorized licensed use limited to the terms of the applicable license agreement with IEEE.”
BackgroundInfluentialNoise Analysis and Modeling of the PMD Flexx2 Depth Camera for Robotic Applications
Cai, Y., Plozza, D., Marty, S., Joseph, P., & Magno, M. (2024) · IEEE International Conference on Omni-layer Intelligent Systems (COINS) · doi:10.1109/coins61597.2024.10622644 · Cited by 5
“Restrictions apply. operating conditions, thereby reducing the sim-to-real gap [21].”
BackgroundChen, B., Kang, J., Zhong, P., Liang, Y., Sheng, Y., & Wang, J. (2024) · ACM International Conference on Multimedia (ACM MM) · doi:10.1145/3664647.3681248 · Cited by 14
“Object Navigation (ObjectNav) task [3, 25] requires an agent to navigate through a previously unknown 3D scenario to find an object instance, according to a semantic label.”
InfluentialProbable Object Location (POLo) Score Estimation for Efficient Object Goal Navigation
Wang, J., & Soh, H. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610671 · Cited by 8
“However, end-to-end methods, in general, suffer from low sampling efficiency [20] and limited generalizability when applied to real-world scenarios [21].”
BackgroundFARM: Find Anything using Relational Spatial MemoryPreprint
He, S., Huang, L., Lilja, A., Hubel, F., Frey, J., Pavone, M., Sastry, S., Malik, J., & Tomlin, C. J. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2606.15476 · Cited by 5
“For instance, when it comes to memory creation, closed-vocabulary semantic SLAM and 3D scene graphs [4, 5, 6, 7, 8, 9, 10, 11] provide spatial and semantic structures but do not generalize to the open vocabularies that users naturally need.”
Self-citation(2023) · doi:10.1109/iros55552.2023.10341959 · Cited by 4
“However, the focus of [33] and our work are different in that we focus on the need of/method for self-supervised real-world in-situ training.”
BackgroundWang, H., Sun, B., Xing, J., Yang, F., Hutter, M., Shah, D., Scaramuzza, D., & Pollefeys, M. (2026) · Lecture notes in computer science · doi:10.1007/978-3-032-37432-5_11 · Cited by 5
Senden, M., van Albada, S. J., Pezzulo, G., Falotico, E., Hashim, I., Kröner, A., Kurth, A. C., Lanillos, P., Narayanan, V., Pennartz, C. M. A., et al. (2023) · National Science Review · doi:10.1093/nsr/nwad318 · Cited by 6
Silwal, S., Yadav, K., Wu, T., Vakil, J., Majumdar, A., Arnaud, S., Chen, C., Berges, V.-P., Batra, D., Rajeswaran, A., et al. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610218 · Cited by 11
“There have been a number of approaches which attempt to bridge this domain gap [12], [13], [14], [15], [16], [17], [18].”
BackgroundSelf-citationLearning Hierarchical Graph-Based Policy for Goal-Reaching in Unknown Environments
Cui, Y., Ye, S., Xu, X., Sha, H., Wang, C., Lin, L., Liu, Z., Xiong, R., & Wang, Y. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3396059 · Cited by 4
“Note that our method utilizes the path-extended graph as a compact map representation and integrates it into a hierarchical framework for higher scalability and stability in long-horizon tasks. involving selecting positions of interest like frontiers and next-best viewpoints [26].”
MethodLiu, H., Liu, X., Huang, K., & Guo, D. (2025) · Machine learning · doi:10.1007/978-981-96-5871-8_1 · Cited by 4
Generalized Object SearchPreprint
Zheng, K. (2023) · arXiv (Cornell University) · doi:10.48550/arxiv.2301.10121 · Cited by 6
Bogenberger, B., Harrison, O., Dahanaggamaarachchi, O., Brunke, L., Qian, J., Zhou, S., & Schoellig, A. P. (2026) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2026.3656790 · Cited by 12
“Semantic exploration refers to the task of using semantic cues to efficiently explore an unknown (or changed) environment [19] to support, for instance, mapping.”
Learning-Based Multi-Robot Active SLAM: A Conceptual Framework and Survey
Lv, B., & Duan, S. (2026) · Applied Sciences · doi:10.3390/app16031412 · Cited by 5
Zhu, H., Jiang, X., Zhang, X., Xu, H., Su, D., Chen, Z., & Zhu, X. (2026) · Sustainability · doi:10.3390/su18073469 · Cited by 3
Temporally extended successor feature neural episodic control
Zhu, X. (2024) · Scientific Reports · doi:10.1038/s41598-024-65687-w · Cited by 3
RGBD-based Image Goal Navigation with Pose Drift: A Topo-metric Graph based Approach
Ye, S., Cui, Y., Sha, H., Lu, S., Zhang, Y., Xiong, R., & Wang, Y. (2024) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57147.2024.10610727 · Cited by 4
“Recent research results show that modular systems normally achieve better performance compared to end-to-end methods in both generalizability and stability, and learning-based techniques can further improve these methods in practical applications [1] [2].”
ResultLi, W., Liao, M., & Zou, W. (2024) · Expert Systems with Applications · doi:10.1016/j.eswa.2024.125964 · Cited by 3
Multi-Agent Exploration With Similarity Score Map and Topological Memory
Lee, E. S., & Kim, Y. M. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3471456 · Cited by 4
“The pretrained vision models, trained on a large image dataset, provide a broad understanding of visual features essential for robot navigation tasks [11], [22], [32], [33].”
MethodReal-World Instance-Specific Image Goal Navigation: Bridging Domain Gaps via Contrastive Learning
Sakaguchi, T., Taniguchi, A., Hagiwara, Y., Hafi, L. E., Hasegawa, S., & Taniguchi, T. (2024) · IEEE International Conference on Robotic Computing (IRC) · doi:10.1109/irc63610.2024.00032 · Cited by 2
“The end-to-end method suffers from sample inefficiency [1] and poor sim-to-real transfer [14].”
Domain Randomization for Object Detection: A Survey
Fan, J., Xie, Y., & Li, Z. (2025) · International Conference on Advanced Electronic Materials, Computers and Software Engineering (AEMCSE) · doi:10.1109/aemcse65292.2025.11042418 · Cited by 2
“One of the most significant applications of object detection lies in robotics, where it plays a pivotal role in autonomous navigation and manipulation [23].”
Knowledge-Driven Visual Target Navigation: Dual Graph Navigation
Li, S., Meng, Z., Pei, J., Chen, J., Dong, B., Li, G., Liu, S., & Wang, F. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128296 · Cited by 3
“In contrast, unlike the direct RGBD-based policy framework, our method uses abstractions of input images to reduce domain gaps across datasets [33].”
Mei, Z., Dixit, A., Booker, M., Zhou, E., Storey-Matsutani, M., Ren, A. Z., Shorinwa, O., & Majumdar, A. (2025) · The International Journal of Robotics Research · doi:10.1177/02783649251378151 · Cited by 10
“The assurance obtained from Section V allows for the use of a simple filtering scheme that aggregates bounding box detections over time.”
XR-based visual enhancing cues for human spatial navigation: A systematic literature review
Zhou, X., Zhang, Y., Yu, H., Du, Q., & Yu, X. (2025) · International Journal of Industrial Ergonomics · doi:10.1016/j.ergon.2025.103835 · Cited by 3
DHRN: A robot autonomous navigation method in crowds based on heterogeneous framework
Song, X., Zhang, Y., Dong, T., & Li, F. (2025) · Neurocomputing · doi:10.1016/j.neucom.2025.132375 · Cited by 3
A Visual Target Navigation Method for Quadrotor Based on Large Language Model in Unknown Environment
Liu, Y., Ma, Z., Guo, J., Sun, H., Niu, Y., Zhang, H., & Wang, M. (2026) · Drones · doi:10.3390/drones10020134 · Cited by 3
StereoNavNet: Learning to Navigate using Stereo Cameras with Auxiliary Occupancy Voxels
Li, H., Padır, T., & Jiang, H. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802385 · Cited by 2
“Then we pass this depth map into the ResNet encoder to produce the geometric obstacle feature h o [21, 23, 24].”
InfluentialData-Efficient Learning from Human Interventions for Mobile Robots
Peng, Z., Liu, Z., & Zhou, B. (2025) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra55743.2025.11128012 · Cited by 4
“In the human following task, we employ a modular setup where an object detector and tracker provide bounding box inputs of the target person, similar to methods used in [46], [47].”
Metadata
- Authors
- Gervet, T., Chintala, S., Batra, D., Malik, J., & Chaplot, D. S.
- Affiliations
- Carnegie Mellon University, Pittsburgh, PA, USA.
- Meta (United States) (US)
- Georgia Institute of Technology (US)
- Venue
- Science Robotics
- Published
- 2023-06-28
- Volume
- 8
- Issue
- 79
- Pages
- eadf6991-eadf6991
- ISSN
- 2470-9476 (ISSN-L)
- OpenAlex
- W4382362889
- Cited by
- 125
- References
- 83
- Citations by year
- 2026: 17 · 2025: 50 · 2024: 44 · 2023: 14
- FWCI
- 11.06
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- cc-by
- Locations
- Science Robotics (publishedVersion)
- PubMed (publishedVersion)
- arXiv (Cornell University) (submittedVersion, cc-by)
- arXiv (Cornell University) (cc-by)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Computer Science › Computer Vision and Pattern Recognition › Robotics and Sensor-Based Localization
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Keywords
- mobile robots, object navigation, sim-to-real transfer, modular learning, end-to-end learning, exploration, domain gap, family environment
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.