N$^{2}$M$^{2}$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments
Open accessThe DOI matches its Crossref record; 68 of the 68 references it cites were found in a registry or an index.
Abstract
Despite its importance in both industrial and service robotics, mobile manipulation remains a significant challenge as it requires seamless integration of end-effector trajectory generation with navigation skills as well as reasoning over long-horizons. Existing methods struggle to control the large configuration space and to navigate dynamic and unknown environments. In the previous work, we proposed to decompose mobile manipulation tasks into a simplified motion generator for the end-effector in task space and a trained reinforcement learning agent for the mobile base to account for the kinematic feasibility of the motion. In this work, we introduce Neural Navigation for Mobile Manipulation (N$^{2}$M$^{2}$), which extends this decomposition to complex obstacle environments, extends the agent's control to the torso joint and the norm of the end-effector motion velocities, uses a more general reward function and, thereby, enables robots to tackle a much broader range of tasks in real-world settings. The resulting approach can perform unseen, long-horizon tasks in unexplored environments while instantly reacting to dynamic obstacles and environmental changes. At the same time, it provides a simple way to define new mobile manipulation tasks. We demonstrate the capabilities of our proposed approach in extensive simulation and real-world experiments on multiple kinematically diverse mobile manipulators.
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 cited source says what the claim attributes to it.
In the citing paper
“We use this method in our real world evaluation as it generalizes across different robots, tasks, and environments.”
From Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation (2023) · cites this paper as [7]
The check wasn’t confident either way, so it gives no verdict — never disputed.
In the citing paper
“For semantic segmentation, a wide range of models exists, including older methods such as Mask R-CNN [5] as well as newer, transfomer-based methods [6], [7].”
From Learning Hierarchical Interactive Multi-Object Search for Mobile Manipulation (2023) · cites this paper as [7]
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
Soft actor-critic Off-policy maximum entropy deep reinforcement learning with a stochastic actor
Haarnoja, T., Zhou, A., Abbeel, P., & Levine, S. (2018) · arXiv · doi:10.48550/arxiv.1801.01290 · Cited by 5,594
Sampling-based algorithms for optimal motion planning
Karaman, S., & Frazzoli, E. (2011) · The International Journal of Robotics Research · doi:10.1177/0278364911406761 · Cited by 5,275
RRT-connect: An efficient approach to single-query path planning
Kuffner, J. J., & LaValle, S. M. (2000) · Proceedings 2000 ICRA. Millennium Conference. IEEE International Conference on Robotics and Automation. Symposia Proceedings (Cat. No.00CH37065) · doi:10.1109/robot.2000.844730 · Cited by 3,555
Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
Sutton, R. S., Precup, D., & Singh, S. (1999) · Artificial Intelligence · doi:10.1016/s0004-3702(99)00052-1 · Cited by 3,119
Motion Planning Among Dynamic, Decision-Making Agents with Deep Reinforcement Learning
Everett, M., Chen, Y. F., & How, J. P. (2018) · 2018 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2018.8593871 · Cited by 767
Universal Value Function Approximators
Schaul, T., Horgan, D., Gregor, K., & Silver, D. (2015) · Cited by 701
The Option-Critic Architecture
Bacon, P.-L., Harb, J., & Precup, D. (2017) · Proceedings of the AAAI Conference on Artificial Intelligence · doi:10.1609/aaai.v31i1.10916 · Cited by 687
Voxblox: Incremental 3D Euclidean Signed Distance Fields for on-board MAV planning
Oleynikova, H., Taylor, Z., Fehr, M., Siegwart, R., & Nieto, J. (2017) · 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros.2017.8202315 · Cited by 658
A Survey of Embodied AI: From Simulators to Research Tasks
Duan, J., Yu, S., Tan, H. L., Zhu, H., & Tan, C. (2022) · IEEE Transactions on Emerging Topics in Computational Intelligence · doi:10.1109/tetci.2022.3141105 · Cited by 420
Integrated Task and Motion Planning
Garrett, C. R., Chitnis, R., Holladay, R., Kim, B., Silver, T., Kaelbling, L. P., & Lozano-Pérez, T. (2021) · Annual Review of Control, Robotics, and Autonomous Systems · doi:10.1146/annurev-control-091420-084139 · Cited by 409
Research works printed but not linked: 1
- [42] U. Patel, N. Kumar, A. J. Sathyamoorthy, and D. Manocha, 'Dwarl: Dynamically feasible deep reinforcement learning policy for robot navigation in dense mobile crowds,' in Int. Conf. on Robotics & Automation , 2021. -
Cited by
Deep 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
Language-Grounded Dynamic Scene Graphs for Interactive Object Search With Mobile Manipulation
Honerkamp, D., Büchner, M., Despinoy, F., Welschehold, T., & Valada, A. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3441495 · Cited by 162
Self-citationRobot 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 91
Jiang, Y., Zhang, R., Wong, J., Wang, C., Ze, Y., Yin, H., Gökmen, C., Song, S., Wu, J., & Fei-Fei, L. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2503.05652 · Cited by 80
M 2 Diffuser: Diffusion-based Trajectory Optimization for Mobile Manipulation in 3D Scenes
Yan, S., Zhang, Z., Han, M., Wang, Z., Xie, Q., Li, Z., Li, Z., Liu, H., Wang, X., & Zhu, S. C. (2025) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2025.3553454 · Cited by 60
Causal Policy Gradient for Whole-Body Mobile Manipulation
Hu, J., Stone, P., & Mart�n-Mart�n, R. (2023) · Robotics: Science and Systems · doi:10.15607/rss.2023.xix.049 · Cited by 46
Chisari, E., Heppert, N., Welschehold, T., Burgard, W., & Valada, A. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3388850 · Cited by 38
Self-citationReactive Base Control for On-the-Move Mobile Manipulation in Dynamic Environments
Burgess-Limerick, B., Haviland, J., Lehnert, C., & Corke, P. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3354615 · Cited by 37
He, G., Guo, X., Tang, L., Zhang, Y., Mousaei, M., Xu, J., Geng, J., Scherer, S., & Shi, G. (2025) · Robotics: Science and Systems · doi:10.15607/rss.2025.xxi.130 · Cited by 36
DiWA: Diffusion Policy Adaptation with World ModelsPreprint
Chandra, A. L., Nematollahi, I., Huang, C., Welschehold, T., Burgard, W., & Valada, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2508.03645 · Cited by 34
Self-citationMao, W., Zhong, W., Jiang, Z., Dong, F., Zhang, Z., Lan, Z., Li, H., Jia, F., Wang, T., Fan, H., et al. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2412.00171 · Cited by 34
Articulated Object Estimation in the WildPreprint
Werby, A., Büchner, M., Röfer, A., Huang, C., Burgard, W., & Valada, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2509.01708 · Cited by 23
Self-citationWhole-Body Teleoperation for Mobile Manipulation at Zero Added Cost
Honerkamp, D., Mahesheka, H., von Hartz, J. O., Welschehold, T., & Valada, A. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3540582 · Cited by 22
Self-citationLearning Hierarchical Interactive Multi-Object Search for Mobile Manipulation
Schmalstieg, F., Honerkamp, D., Welschehold, T., & Valada, A. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3329619 · Cited by 21
Self-citationThe Treachery of Images: Bayesian Scene Keypoints for Deep Policy Learning in Robotic Manipulation
von Hartz, J. O., Chisari, E., Welschehold, T., Burgard, W., Boedecker, J., & Valada, A. (2023) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2023.3313917 · Cited by 18
Self-citationXie, P., Xia, B., Hu, A., Zhao, Z., Meng, L., Sun, Z., Gao, X., Wang, J., & Meng, M. Q. ‐. (2024) · Journal of Field Robotics · doi:10.1002/rob.22395 · Cited by 17
MORE: Mobile Manipulation Rearrangement Through Grounded Language Reasoning
Mohammadi, M., Honerkamp, D., Büchner, M., Cassinelli, M., Welschehold, T., Despinoy, F., Gilitschenski, I., & Valada, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247596 · Cited by 16
Self-citationTao, Y., Wan, J., Song, Y., Li, X., Wang, B., Wang, T., & Wang, Y. (2024) · Robotics and Computer-Integrated Manufacturing · doi:10.1016/j.rcim.2024.102903 · Cited by 12
Articulated 3D Scene Graphs for Open-World Mobile ManipulationPreprint
Büchner, M., Röfer, A., Engelbracht, T., Welschehold, T., Bauer, Z., Blum, H., Pollefeys, M., & Valada, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2602.16356 · Cited by 12
Self-citationSample-Efficient Deep Reinforcement Learning of Mobile Manipulation for 6-DOF Trajectory Following
Zhou, Y., Feng, Q., Zhou, Y., Lin, J., Liu, Z., & Wang, H. (2025) · IEEE Transactions on Automation Science and Engineering · doi:10.1109/tase.2025.3530162 · Cited by 11
Task-Driven Co-Design of Mobile Manipulators
Schneider, R., Honerkamp, D., Welschehold, T., & Valada, A. (2025) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2025.3573622 · Cited by 11
Self-citationLu, Z., & Wang, Y. (2024) · Journal of Field Robotics · doi:10.1002/rob.22394 · Cited by 11
Pre-Grasp Approaching on Mobile Robots: A Pre-Active Layered Approach
Naik, L., Kalkan, S., & Krüger, N. (2024) · IEEE Robotics and Automation Letters · doi:10.1109/lra.2024.3358077 · Cited by 10
BaSeNet: A Learning-based Mobile Manipulator Base Pose Sequence Planning for Pickup Tasks
Naik, L., Kalkan, S., Sørensen, S. L., Kjærgaard, M. B., & Krüger, N. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802615 · Cited by 10
Opening Articulated Structures in the Real WorldPreprint
Gupta, A., Zhang, M. M., Sathua, R., & Gupta, S. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2402.17767 · Cited by 10
Bayesian Optimization for Sample-Efficient Policy Improvement in Robotic Manipulation
Röfer, A., Nematollahi, I., Welschehold, T., Burgard, W., & Valada, A. (2024) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros58592.2024.10802400 · Cited by 9
Self-citationPerceptive Pedipulation with Local Obstacle Avoidance
Stolle, J., Arm, P., Mittal, M., & Hutter, M. (2024) · IEEE-RAS International Conference on Humanoid Robots (Humanoids) · doi:10.1109/humanoids58906.2024.10769896 · Cited by 9
He, C., Sun, G., Bai, Y., Lu, J., Zhao, J., & Sartoretti, G. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2512.04381 · Cited by 8
SLAC: Safe and Efficient Real-Robot Reinforcement Learning via Unsupervised Simulation Pre-TrainingPreprint
Hu, J., Stone, P., & Martín-Martín, R. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2506.04147 · Cited by 8
Manipulation on-the-move: Mobile manipulation in dynamic, unstructured environments
Burgess-Limerick, B. (2024) · Queensland University of Technology · doi:10.5204/thesis.eprints.250817 · Cited by 6
Demonstrating MOSART: Opening Articulated Structures in the Real World
Gupta, A., Zhang, M. M., Sathua, R., & Gupta, S. (2025) · Robotics: Science and Systems · doi:10.15607/rss.2025.xxi.033 · Cited by 6
Neural Randomized Planning for Whole Body Robot MotionPreprint
Lu, Y., Ma, Y., Hsu, D., & Cai, P. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2405.11317 · Cited by 5
Relational Semantic Reasoning on 3D Scene Graphs for Open World Interactive Object SearchPreprint
Mahdi, I., Cassinelli, M., Despinoy, F., Welschehold, T., & Valada, A. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2603.05642 · Cited by 3
Self-citationDesigning for Difference: How Human Characteristics Shape Perceptions of Collaborative RobotsPreprint
Livanec, S., Londoño, L., Gorki, M., Röfer, A., Valada, A., & Kiesel, A. (2025) · arXiv (Cornell University) · doi:10.48550/arxiv.2507.16480 · Cited by 2
Self-citationZhang, J., Sun, S., Liu, K., Zhou, C., Zhao, X., Tan, M., & Huang, Y. (2025) · Conference proceedings/Conference proceedings - IEEE International Conference on Systems, Man, and Cybernetics · doi:10.1109/smc58881.2025.11342982 · Cited by 2
Honerkamp, D., Guttikonda, S., & Valada, A. (2022) · arXiv (Cornell University) · doi:10.48550/arxiv.2209.09646 · Cited by 2
Self-citationResearch on Autonomous Positioning Method for Inspection Robot Based on Distributed 2D LiDARs
Huang, F. Y., Liu, J. Q., & Fang, D. H. (2024) · IEEE Access · doi:10.1109/access.2024.3520162 · Cited by 2
Context-Aware Behavior Learning with Heuristic Motion Memory for Underwater Manipulation
Buchholz, M., Carlucho, I., Grimaldi, M., Koskinopoulou, M., & Pétillot, Y. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247719 · Cited by 2
CenterArt: Joint Shape Reconstruction and 6-DoF Grasp Estimation of Articulated ObjectsPreprint
Mokhtar, S., Chisari, E., Heppert, N., & Valada, A. (2024) · arXiv (Cornell University) · doi:10.48550/arxiv.2404.14968 · Cited by 2
Self-citationCOWBOY: A Scalable Sim-to-Real Framework for Learning Contextual Whole-Body ManipulationPreprint
Yang, J., Liu, J., Liu, R., Wang, A. E., Shaw, K., Pathak, D., & Salakhutdinov, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.28948 · Cited by 2
Visual Loop Closure Detection Through Deep Graph Consensus
Büchner, M., Dahiya, L., Dorer, S., Ramtekkar, V., Nishimiya, K., Cattaneo, D., & Valada, A. (2025) · IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS) · doi:10.1109/iros60139.2025.11247208 · Cited by 1
Self-citationPixel-UMI: Learning Environment-Aware Whole-Body Manipulation from Sensorized Human DemonstrationsPreprint
Liu, J., Tao, T., Pathak, D., & Salakhutdinov, R. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2611.03647 · Cited by 1
Whole-Body Mobile Manipulation using Offline Reinforcement Learning on Sub-optimal ControllersPreprint
Jauhri, S., Prasad, V., & Chalvatzaki, G. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2604.12509 · Cited by 1
Zhong, P., Liu, L., Chen, B., Wu, T., Xia, J., Mu, C., & Wang, J. (2026) · International Joint Conference on Artificial Intelligence · doi:10.24963/ijcai.2026/697 · Cited by 1
2023 Index IEEE Transactions on Robotics Vol. 39
(2023) · IEEE Transactions on Robotics · doi:10.1109/tro.2023.3343423
SimVLA: Zero-Shot Sim-to-Real VLA Learning for Mobile ManipulationPreprint
Baik, K., & Lee, Y. S. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2610.11248
Chen, B., Liu, L., Yan, S., Yang, H., Zhong, P., & Wang, J. (2026) · Proceedings - IEEE International Conference on Robotics and Automation/Proceedings · doi:10.1109/icra57385.2026.11696390
Distance-Aware World Model-Based Reinforcement Learning for Mobile Manipulation Behaviors
Feng, X., & Horii, T. (2026) · IEEE Access · doi:10.1109/access.2026.3695694
Hwang, C., Wu, H., Pu, S., Cheng, Z., & Wu, T. (2025) · Asian Journal of Control · doi:10.1002/asjc.3886
Vehicle-Arm Coordination-Based Active 3D Reconstruction using Deep Reinforcement Learning
Liu, L., Zhong, P., Chen, B., Kang, J., Yang, H., & Wang, Y. (2025) · International Joint Conference on Neural Networks (IJCNN) · doi:10.1109/ijcnn64981.2025.11228166
Li, Y., Song, Z., Li, Y., Song, Z., Chen, K., Zheng, C., Bi, Z., Cao, J., Calinon, S., Shi, F., et al. (2026) · arXiv (Cornell University) · doi:10.48550/arxiv.2601.18548
Learning Vision-Based Control for Autonomous Roadside Mowing
Li, Q., Renner, M., & Berns, K. (2026) · International Conference on Ubiquitous Robots (UR) · doi:10.1109/ur69537.2026.11626814
Electronic Skin-Enabled Obstacle Avoidance for Mobile Manipulators in Human-Robot Collaboration
Liu, Z., Liu, L., Li, Y., & Li, M. (2026) · IEEE/ASME International Conference on Advanced Intelligent Mechatronics · doi:10.1109/aim65483.2026.11658047
A Robust Closed-Loop Seam Tracking Method for Mobile Welding via Cooperative Base-Arm Control
Zhao, W., & Li, J. (2026) · Asian Control Conference (ASCC) · doi:10.1109/ascc70886.2026.11702031
Metadata
- Authors
- Honerkamp, D., Welschehold, T., & Valada, A.
- Affiliations
- University of Freiburg (DE)
- Venue
- IEEE Transactions on Robotics
- Published
- 2023-10
- Volume
- 39
- Issue
- 5
- Pages
- 3601-3619
- ISSN
- 1552-3098 (ISSN-L)
- 1941-0468
- OpenAlex
- W4382365724
- Cited by
- 30
- References
- 67
- Citations by year
- 2026: 4 · 2025: 10 · 2024: 13 · 2023: 3
- FWCI
- 2.66
- Type
- journal article
- Language
- en
- Open access
- green
- arxiv.org
- Licence
- Locations
- IEEE Transactions on Robotics (publishedVersion)
- arXiv (Cornell University) (submittedVersion)
- arXiv (Cornell University)
- Topics
- Physical Sciences › Computer Science › Artificial Intelligence › Reinforcement Learning in Robotics
- Physical Sciences › Engineering › Control and Systems Engineering › Robot Manipulation and Learning
- Physical Sciences › Engineering › Control and Systems Engineering › Control and Dynamics of Mobile Robots
- Keywords
- mobile manipulation, reinforcement learning, dynamic environments, unknown environments, dynamic obstacles, long-horizon navigation, kinematic feasibility, task decomposition, mobile manipulators
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.