Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
97 tokens/sec
GPT-4o
53 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
4 tokens/sec
GPT-4.1 Pro
47 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

N$^2$M$^2$: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments (2206.08737v2)

Published 17 Jun 2022 in cs.RO and cs.AI

Abstract: Despite its importance in both industrial and service robotics, mobile manipulation remains a significant challenge as it requires a 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 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 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 and enables it to tackle a broad 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. Code and videos are publicly available at http://mobile-rl.cs.uni-freiburg.de.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (67)
  1. K. Blomqvist, M. Breyer, A. Cramariuc, J. Förster, M. Grinvald, F. Tschopp, J. J. Chung, L. Ott, J. Nieto, and R. Siegwart, “Go fetch: Mobile manipulation in unstructured environments,” arXiv preprint arXiv:2004.00899, 2020.
  2. J. V. Hurtado, L. Londoño, and A. Valada, “From learning to relearning: A framework for diminishing bias in social robot navigation,” Frontiers in Robotics and AI, vol. 8, p. 69, 2021.
  3. K. Sirohi, R. Mohan, D. Büscher, W. Burgard, and A. Valada, “Efficientlps: Efficient lidar panoptic segmentation,” IEEE Transactions on Robotics, 2021.
  4. F. R. Valverde, J. V. Hurtado, and A. Valada, “There is more than meets the eye: Self-supervised multi-object detection and tracking with sound by distilling multimodal knowledge,” in Proc. of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2021, pp. 11 612–11 621.
  5. J. Duan, S. Yu, H. L. Tan, H. Zhu, and C. Tan, “A survey of embodied ai: From simulators to research tasks,” IEEE Transactions on Emerging Topics in Computational Intelligence, 2022.
  6. A. Younes, D. Honerkamp, T. Welschehold, and A. Valada, “Catch me if you hear me: Audio-visual navigation in complex unmapped environments with moving sounds,” arXiv preprint arXiv:2111.14843, 2021.
  7. N. Vahrenkamp, T. Asfour, and R. Dillmann, “Robot placement based on reachability inversion,” in Int. Conf. on Robotics & Automation, 2013.
  8. F. Paus, P. Kaiser, N. Vahrenkamp, and T. Asfour, “A combined approach for robot placement and coverage path planning for mobile manipulation,” in Int. Conf. on Intelligent Robots and Systems, 2017.
  9. S. Karaman and E. Frazzoli, “Sampling-based algorithms for optimal motion planning,” Int. Journal of Robotics Research, vol. 30, no. 7, pp. 846–894, 2011.
  10. J. Kuffner and S. LaValle, “Rrt-connect: An efficient approach to single-query path planning,” in Int. Conf. on Robotics & Automation, vol. 2, 2000, pp. 995–1001.
  11. F. Burget, M. Bennewitz, and W. Burgard, “Bi2rrt*: An efficient sampling-based path planning framework for task-constrained mobile manipulation,” in Int. Conf. on Intelligent Robots and Systems, 2016.
  12. J. Pankert and M. Hutter, “Perceptive model predictive control for continuous mobile manipulation,” IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 6177–6184, 2020.
  13. M. V. Minniti, R. Grandia, K. Fäh, F. Farshidian, and M. Hutter, “Model predictive robot-environment interaction control for mobile manipulation tasks,” in Int. Conf. on Robotics & Automation, 2021.
  14. F. Xia, C. Li, R. Martín-Martín, O. Litany, A. Toshev, and S. Savarese, “Relmogen: Leveraging motion generation in reinforcement learning for mobile manipulation,” in Int. Conf. on Robotics & Automation, 2021.
  15. J. Wong, A. Tung, A. Kurenkov, A. Mandlekar, L. Fei-Fei, S. Savarese, and R. Martín-Martín, “Error-aware imitation learning from teleoperation data for mobile manipulation,” in Proc. of the Conference on Robot Learning, A. Faust, D. Hsu, and G. Neumann, Eds., vol. 164, 2022, pp. 1367–1378.
  16. F. Schmalstieg, D. Honerkamp, T. Welschehold, and A. Valada, “Learning long-horizon robot exploration strategies for multi-object search in continuous action spaces,” Proceedings of the International Symposium on Robotics Research (ISRR), 2022.
  17. J. Kindle, F. Furrer, T. Novkovic, J. J. Chung, R. Siegwart, and J. Nieto, “Whole-body control of a mobile manipulator using end-to-end reinforcement learning,” arXiv preprint arXiv:2003.02637, 2020.
  18. D. Honerkamp, T. Welschehold, and A. Valada, “Learning kinematic feasibility for mobile manipulation through deep reinforcement learning,” IEEE Robotics and Automation Letters, 2021.
  19. R. Diankov, S. S. Srinivasa, D. Ferguson, and J. Kuffner, “Manipulation planning with caging grasps,” in Int. Conf. on Humanoid Robots.   IEEE, 2008, pp. 285–292.
  20. M. Arduengo, C. Torras, and L. Sentis, “Robust and adaptive door operation with a mobile robot,” Intelligent Service Robotics, vol. 14, no. 3, pp. 409–425, 2021.
  21. J. Liu, P. Balatti, K. Ellis, D. Hadjivelichkov, D. Stoyanov, A. Ajoudani, and D. Kanoulas, “Garbage collection and sorting with a mobile manipulator using deep learning and whole-body control,” in Int. Conf. on Humanoid Robots, 2021, pp. 408–414.
  22. S. Jauhri, J. Peters, and G. Chalvatzaki, “Robot learning of mobile manipulation with reachability behavior priors,” arXiv preprint arXiv:2203.04051, 2022.
  23. F. Burget, A. Hornung, and M. Bennewitz, “Whole-body motion planning for manipulation of articulated objects,” in Int. Conf. on Robotics & Automation, 2013, pp. 1656–1662.
  24. O. Arslan and P. Tsiotras, “Use of relaxation methods in sampling-based algorithms for optimal motion planning,” in Int. Conf. on Robotics & Automation.   IEEE, 2013, pp. 2421–2428.
  25. M. Otte and E. Frazzoli, “Rrtx: Real-time motion planning/replanning for environments with unpredictable obstacles,” in Algorithmic Foundations of Robotics XI.   Springer, 2015, pp. 461–478.
  26. D. Berenson, S. Srinivasa, and J. Kuffner, “Task space regions: A framework for pose-constrained manipulation planning,” Int. Journal of Robotics Research, vol. 30, no. 12, pp. 1435–1460, 2011.
  27. D. Leidner, A. Dietrich, F. Schmidt, C. Borst, and A. Albu-Schäffer, “Object-centered hybrid reasoning for whole-body mobile manipulation,” in Int. Conf. on Robotics & Automation, 2014, pp. 1828–1835.
  28. T. Welschehold, C. Dornhege, F. Paus, T. Asfour, and W. Burgard, “Coupling mobile base and end-effector motion in task space,” in Int. Conf. on Intelligent Robots and Systems, 2018.
  29. J. Sleiman, F. Farshidian, M. V. Minniti, and M. Hutter, “A unified MPC framework for whole-body dynamic locomotion and manipulation,” IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 4688–4695, 2021.
  30. M. Mittal, D. Hoeller, F. Farshidian, M. Hutter, and A. Garg, “Articulated object interaction in unknown scenes with whole-body mobile manipulation,” arXiv preprint arXiv:2103.10534, 2021.
  31. J. Haviland, N. Sunderhauf, and P. Corke, “A holistic approach to reactive mobile manipulation,” IEEE Robotics and Automation Letters, 2022.
  32. R. Ancona, “Redundancy modelling and resolution for robotic mobile manipulators: a general approach,” Advanced Robotics, vol. 31, no. 13, pp. 706–715, 2017.
  33. C. R. Garrett, R. Chitnis, R. Holladay, B. Kim, T. Silver, L. P. Kaelbling, and T. Lozano-Perez, “Integrated task and motion planning,” Annual review of control, robotics, and autonomous systems, vol. 4, 2021.
  34. M. Toussaint, K. R. Allen, K. A. Smith, and J. B. Tenenbaum, “Differentiable physics and stable modes for tool-use and manipulation planning,” in Robotics: Science and Systems, 2018.
  35. C. R. Garrett, T. Lozano-Perez, and L. P. Kaelbling, “Ffrob: Leveraging symbolic planning for efficient task and motion planning,” Int. Journal of Robotics Research, vol. 37, no. 1, pp. 104–136, 2018.
  36. S. Bansal, V. Tolani, S. Gupta, J. Malik, and C. Tomlin, “Combining optimal control and learning for visual navigation in novel environments,” in Proc. of the Conference on Robot Learning, vol. 100, 2020, pp. 420–429.
  37. T. El-Gaaly, C. Tomaszewski, A. Valada, P. Velagapudi, B. Kannan, and P. Scerri, “Visual obstacle avoidance for autonomous watercraft using smartphones,” Autonomous Robots and Multirobot Systems Workshop (ARMS), 2013.
  38. M. Kollmitz, D. Büscher, and W. Burgard, “Predicting obstacle footprints from 2d occupancy maps by learning from physical interactions,” in Int. Conf. on Robotics & Automation, 2020, pp. 10 256–10 262.
  39. R. Guldenring, M. Görner, N. Hendrich, N. J. Jacobsen, and J. Zhang, “Learning local planners for human-aware navigation in indoor environments,” in Int. Conf. on Intelligent Robots and Systems, 2020, pp. 6053–6060.
  40. D. Hoeller, L. Wellhausen, F. Farshidian, and M. Hutter, “Learning a state representation and navigation in cluttered and dynamic environments,” IEEE Robotics and Automation Letters, vol. 6, no. 3, pp. 5081–5088, 2021.
  41. M. Everett, Y. F. Chen, and J. P. How, “Motion planning among dynamic, decision-making agents with deep reinforcement learning,” in Int. Conf. on Intelligent Robots and Systems, 2018, pp. 3052–3059.
  42. U. Patel, N. Kumar, A. J. Sathyamoorthy, and D. Manocha, “Dwa-rl: Dynamically feasible deep reinforcement learning policy for robot navigation in dense mobile crowds,” in Int. Conf. on Robotics & Automation, 2021.
  43. J. Wu, X. Sun, A. Zeng, S. Song, J. Lee, S. Rusinkiewicz, and T. Funkhouser, “Spatial action maps for mobile manipulation,” in Proceedings of Robotics: Science and Systems (RSS), 2020.
  44. T. Chen, S. Gupta, and A. Gupta, “Learning exploration policies for navigation,” in International Conference on Learning Representations, 2019.
  45. Y. Goel, N. Vaskevicius, L. Palmieri, N. Chebrolu, and C. Stachniss, “Predicting dense and context-aware cost maps for semantic robot navigation,” arXiv preprint arXiv:2210.08952, 2022.
  46. H. Oleynikova, Z. Taylor, M. Fehr, R. Siegwart, and J. Nieto, “Voxblox: Incremental 3d euclidean signed distance fields for on-board mav planning,” in Int. Conf. on Intelligent Robots and Systems, 2017.
  47. L. Han, F. Gao, B. Zhou, and S. Shen, “Fiesta: Fast incremental euclidean distance fields for online motion planning of aerial robots,” in Int. Conf. on Intelligent Robots and Systems.   IEEE, 2019, pp. 4423–4430.
  48. K. Ehsani, W. Han, A. Herrasti, E. VanderBilt, L. Weihs, E. Kolve, A. Kembhavi, and R. Mottaghi, “Manipulathor: A framework for visual object manipulation,” in Proc. of the IEEE Conf. on Computer Vision and Pattern Recognition, 2021, pp. 4497–4506.
  49. D. Batra, A. X. Chang, S. Chernova, A. J. Davison, J. Deng, V. Koltun, S. Levine, J. Malik, I. Mordatch, R. Mottaghi et al., “Rearrangement: A challenge for embodied ai,” arXiv preprint arXiv:2011.01975, 2020.
  50. S. Srivastava, C. Li, M. Lingelbach, R. Martín-Martín, F. Xia, K. E. Vainio, Z. Lian, C. Gokmen, S. Buch, K. Liu et al., “Behavior: Benchmark for everyday household activities in virtual, interactive, and ecological environments,” in Proc. of the Conference on Robot Learning, 2022, pp. 477–490.
  51. 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, and D. Batra, “Habitat 2.0: Training home assistants to rearrange their habitat,” arXiv preprint arXiv:2106.14405, 2021.
  52. C. Gan, S. Zhou, J. Schwartz, S. Alter, A. Bhandwaldar, D. Gutfreund, D. L. K. Yamins, J. J. DiCarlo, J. H. McDermott, A. Torralba, and J. B. Tenenbaum, “The threedworld transport challenge: A visually guided task-and-motion planning benchmark for physically realistic embodied AI,” arXiv preprint arXiv:2103.14025, 2021.
  53. L. P. Kaelbling, “Learning to achieve goals,” in Proc. of the 13th Int. Joint Conference on Artificial Intelligence, 1993, pp. 1094–1098.
  54. T. Schaul, D. Horgan, K. Gregor, and D. Silver, “Universal value function approximators,” in Proc. of the 32nd Int. Conf. on Machine Learning, vol. 37, 2015, pp. 1312–1320.
  55. R. S. Sutton, D. Precup, and S. Singh, “Between mdps and semi-mdps: A framework for temporal abstraction in reinforcement learning,” Artificial intelligence, vol. 112, no. 1-2, pp. 181–211, 1999.
  56. P.-L. Bacon, J. Harb, and D. Precup, “The option-critic architecture,” in Proc. of the National Conference on Artificial Intelligence, 2017.
  57. L. P. Kaelbling, “Hierarchical learning in stochastic domains: Preliminary results,” in Proc. of the Int. Conf. on Machine Learning, vol. 951, 1993, pp. 167–173.
  58. C. Li, F. Xia, R. Martin, and S. Savarese, “Hrl4in: Hierarchical reinforcement learning for interactive navigation with mobile manipulators,” in Conference on Robot Learning, 2019.
  59. A. Röfer, G. Bartels, W. Burgard, A. Valada, and M. Beetz, “Kineverse: A symbolic articulation model framework for model-agnostic mobile manipulation,” IEEE Robotics and Automation Letters, 2022.
  60. P. Ruppel, N. Hendrich, S. Starke, and J. Zhang, “Cost functions to specify full-body motion and multi-goal manipulation tasks,” in Int. Conf. on Robotics & Automation.   IEEE, 2018, pp. 3152–3159.
  61. F. Pardo, A. Tavakoli, V. Levdik, and P. Kormushev, “Time limits in reinforcement learning,” in Proc. of the Int. Conf. on Machine Learning, vol. 80, 2018, pp. 4045–4054.
  62. T. Haarnoja, A. Zhou, P. Abbeel, and S. Levine, “Soft actor-critic: Off-policy maximum entropy deep reinforcement learning with a stochastic actor,” in Proc. of the Int. Conf. on Machine Learning, vol. 80, 2018, pp. 1861–1870.
  63. P. Klink, C. D’Eramo, J. R. Peters, and J. Pajarinen, “Self-paced deep reinforcement learning,” Advances in Neural Information Processing Systems, vol. 33, pp. 9216–9227, 2020.
  64. M. Dennis, N. Jaques, E. Vinitsky, A. Bayen, S. Russell, A. Critch, and S. Levine, “Emergent complexity and zero-shot transfer via unsupervised environment design,” in Proc. of the Conf. on Neural Information Processing Systems, 2020.
  65. D. Coleman, I. Sucan, S. Chitta, and N. Correll, “Reducing the barrier to entry of complex robotic software: a moveit! case study,” Journal of Software Engineering for Robotics, vol. 5, no. 1, pp. 3–16, 2014.
  66. T. Welschehold, C. Dornhege, and W. Burgard, “Learning mobile manipulation actions from human demonstrations,” in Int. Conf. on Intelligent Robots and Systems, 2017.
  67. AWS RoboMaker, “aws-robomaker-bookstore-world,” https://github.com/aws-robotics/aws-robomaker-bookstore-world, 2019.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (3)
  1. Daniel Honerkamp (13 papers)
  2. Tim Welschehold (27 papers)
  3. Abhinav Valada (117 papers)
Citations (20)
View on Semantic Scholar

Summary

We haven't generated a summary for this paper yet.

Ai Sparkles Streamline Icon: https://streamlinehq.com Summarize Now