Papers
Topics
Authors
Recent
Gemini 2.5 Flash
Gemini 2.5 Flash
80 tokens/sec
GPT-4o
59 tokens/sec
Gemini 2.5 Pro Pro
43 tokens/sec
o3 Pro
7 tokens/sec
GPT-4.1 Pro
50 tokens/sec
DeepSeek R1 via Azure Pro
28 tokens/sec
2000 character limit reached

Learning to walk in confined spaces using 3D representation (2403.00187v1)

Published 29 Feb 2024 in cs.RO

Abstract: Legged robots have the potential to traverse complex terrain and access confined spaces beyond the reach of traditional platforms thanks to their ability to carefully select footholds and flexibly adapt their body posture while walking. However, robust deployment in real-world applications is still an open challenge. In this paper, we present a method for legged locomotion control using reinforcement learning and 3D volumetric representations to enable robust and versatile locomotion in confined and unstructured environments. By employing a two-layer hierarchical policy structure, we exploit the capabilities of a highly robust low-level policy to follow 6D commands and a high-level policy to enable three-dimensional spatial awareness for navigating under overhanging obstacles. Our study includes the development of a procedural terrain generator to create diverse training environments. We present a series of experimental evaluations in both simulation and real-world settings, demonstrating the effectiveness of our approach in controlling a quadruped robot in confined, rough terrain. By achieving this, our work extends the applicability of legged robots to a broader range of scenarios.

Learning to Walk in Confined Spaces Using 3D Representation: An Overview

The paper "Learning to Walk in Confined Spaces Using 3D Representation" addresses a significant challenge in the field of robotics: enabling legged robots to navigate confined and unstructured environments effectively. This research leverages reinforcement learning and 3D volumetric representations within a two-layer hierarchical policy framework to enhance the locomotion capabilities of legged robots, particularly in environments with overhanging obstacles.

Methodological Approach

The authors develop a hierarchical policy framework to control a quadruped robot. The framework is composed of a low-level policy focused on robust locomotion across varied terrains, and a high-level policy aimed at enabling spatial awareness and navigational capabilities in complex environments.

  1. Low-Level Policy:
    • Trained using the Proximal Policy Optimization (PPO) algorithm, this policy emphasizes following 6D commands (combining lateral and angular velocity with body orientation and height) to achieve smooth traversal over uneven surfaces.
    • It utilizes proprioceptive and exteroceptive inputs, including height samples around each foot, to navigate effectively.
  2. High-Level Policy:
    • This policy also utilizes PPO for training and employs spherical scans to capture local geometry for effective decision-making in confined spaces.
    • Commands generated by the high-level policy direct the low-level policy, balancing spatial navigation with robust traversal.
  3. Hierarchical Structure:
    • The low-level teacher policy is distilled into a student policy that can manage noisy observations.
    • Similarly, the high-level teacher policy, initially trained with spherical scans, is distilled into a student policy that interprets noisy voxel data, enabling flexibility in sensor configurations.

Experimental Evaluation

The methodology was validated both in simulation and through real-world deployments.

  • Simulation: A procedural terrain generator was implemented using the Wave Function Collapse method. This allowed the creation of diverse terrain configurations, testing the policy's abilities in different confined space scenarios. Results showed high success rates in navigating complex obstacle configurations compared to baseline strategies.
  • Real-World Tests: Deployments included environments resembling a collapsed building, with complex terrains comprising loose gravel and unstable structures. The robot adapted its posture dynamically, showcasing the policy's robustness and adaptability.

Implications and Future Directions

The research demonstrates significant advancements in robotic locomotion within confined and challenging environments. By enabling a legged robot to autonomously navigate and adjust its posture based on environmental cues, the paper successfully extends the operational range of such robots to scenarios where traditional platforms may fail.

Future developments could focus on enhancing cognitive capabilities for more dynamic environments and integrating advanced perception techniques for even more nuanced spatial understanding. Exploration of the integration of these systems into larger, multi-robot frameworks could pave the way for fully autonomous exploratory missions in extreme environments, including disaster sites and extraterrestrial landscapes.

In summary, this research presents a comprehensive approach to improving legged robot mobility in unstructured settings and represents a significant methodological contribution to the field of robotics.

Definition Search Book Streamline Icon: https://streamlinehq.com
References (43)
  1. J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter, “Learning quadrupedal locomotion over challenging terrain,” Science Robotics, vol. 5, no. 47, 2020.
  2. T. Miki, J. Lee, J. Hwangbo, L. Wellhausen, V. Koltun, and M. Hutter, “Learning robust perceptive locomotion for quadrupedal robots in the wild,” Science Robotics, vol. 7, no. 62, p. eabk2822, 2022. [Online]. Available: https://www.science.org/doi/abs/10.1126/scirobotics.abk2822
  3. P. Arm, G. Waibel, J. Preisig, T. Tuna, R. Zhou, V. Bickel, G. Ligeza, T. Miki, F. Kehl, H. Kolvenbach et al., “Scientific exploration of challenging planetary analog environments with a team of legged robots,” Science robotics, vol. 8, no. 80, p. eade9548, 2023.
  4. M. Tranzatto, M. Dharmadhikari, L. Bernreiter, M. Camurri, S. Khattak, F. Mascarich, P. Pfreundschuh, D. Wisth, S. Zimmermann, M. Kulkarni, V. Reijgwart, B. Casseau, T. Homberger, P. De Petris, L. Ott, W. Tubby, G. Waibel, H. Nguyen, C. Cadena, R. Buchanan, L. Wellhausen, N. Khedekar, O. Andersson, L. Zhang, T. Miki, T. Dang, M. Mattamala, M. Montenegro, K. Meyer, X. Wu, A. Briod, M. Mueller, M. Fallon, R. Siegwart, M. Hutter, and K. Alexis, “Team CERBERUS wins the DARPA subterranean challenge: Technical overview and lessons learned,” Jul. 2022.
  5. M. Tranzatto, T. Miki, M. Dharmadhikari, L. Bernreiter, M. Kulkarni, F. Mascarich, O. Andersson, S. Khattak, M. Hutter, R. Siegwart, and K. Alexis, “CERBERUS in the DARPA subterranean challenge,” Sci Robot, vol. 7, no. 66, p. eabp9742, May 2022.
  6. A. Bouman, M. F. Ginting, N. Alatur, M. Palieri, D. D. Fan, T. Touma, T. Pailevanian, S.-K. Kim, K. Otsu, J. Burdick, and A.-A. Agha-mohammadi, “Autonomous spot: Long-Range autonomous exploration of extreme environments with legged locomotion,” Oct. 2020.
  7. N. Kottege, J. Williams, B. Tidd, F. Talbot, R. Steindl, M. Cox, D. Frousheger, T. Hines, A. Pitt, B. Tam, B. Wood, L. Hanson, K. Lo Surdo, T. Molnar, M. Wildie, K. Stepanas, G. Catt, L. Tychsen-Smith, D. Penfold, L. Overs, M. Ramezani, K. Khosoussi, F. Kendoul, G. Wagner, D. Palmer, J. Manderson, C. Medek, M. O’Brien, S. Chen, and R. C. Arkin, “Heterogeneous robot teams with unified perception and autonomy: How team CSIRO data61 tied for the top score at the DARPA subterranean challenge,” Feb. 2023.
  8. L. Han, Q. Zhu, J. Sheng, C. Zhang, T. Li, Y. Zhang, H. Zhang, Y. Liu, C. Zhou, R. Zhao, J. Li, Y. Zhang, R. Wang, W. Chi, X. Li, Y. Zhu, L. Xiang, X. Teng, and Z. Zhang, “Lifelike agility and play on quadrupedal robots using reinforcement learning and generative pre-trained models,” Aug. 2023.
  9. Z. Zhuang, Z. Fu, J. Wang, C. G. Atkeson, S. Schwertfeger, C. Finn, and H. Zhao, “Robot parkour learning,” in 7th Annual Conference on Robot Learning, 2023.
  10. D. Hoeller, N. Rudin, D. Sako, and M. Hutter, “Anymal parkour: Learning agile navigation for quadrupedal robots,” arXiv preprint arXiv:2306.14874, 2023.
  11. Y. Kim, H. Oh, J. Lee, J. Choi, G. Ji, M. Jung, D. Youm, and J. Hwangbo, “Not only rewards but also constraints: Applications on legged robot locomotion,” Aug. 2023.
  12. R. Buchanan, L. Wellhausen, M. Bjelonic, T. Bandyopadhyay, N. Kottege, and M. Hutter, “Perceptive whole-body planning for multilegged robots in confined spaces,” Journal of Field Robotics, vol. 38, no. 1, pp. 68–84, 2021.
  13. R. Buchanan, T. Bandyopadhyay, M. Bjelonic, L. Wellhausen, M. Hutter, and N. Kottege, “Walking posture adaptation for legged robot navigation in confined spaces,” IEEE Robotics and Automation Letters, vol. 4, no. 2, pp. 2148–2155, 2019.
  14. R. Yang, M. Zhang, N. Hansen, H. Xu, and X. Wang, “Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers,” in International Conference on Learning Representations, 2022. [Online]. Available: https://openreview.net/forum?id=nhnJ3oo6AB
  15. W. Yu, D. Jain, A. Escontrela, A. Iscen, P. Xu, E. Coumans, S. Ha, J. Tan, and T. Zhang, “Visual-Locomotion: Learning to walk on complex terrains with vision,” in Proceedings of the 5th Conference on Robot Learning, ser. Proceedings of Machine Learning Research, A. Faust, D. Hsu, and G. Neumann, Eds., vol. 164.   PMLR, 2022, pp. 1291–1302.
  16. A. Agarwal, A. Kumar, J. Malik, and D. Pathak, “Legged locomotion in challenging terrains using egocentric vision,” Sep. 2022.
  17. R. Yang, G. Yang, and X. Wang, “Neural volumetric memory for visual locomotion control,” in Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition, 2023, pp. 1430–1440.
  18. M. Zucker, J. A. Bagnell, C. G. Atkeson, and J. Kuffner, “An optimization approach to rough terrain locomotion,” in 2010 IEEE International Conference on Robotics and Automation.   IEEE, 2010, pp. 3589–3595.
  19. P. D. Neuhaus, J. E. Pratt, and M. J. Johnson, “Comprehensive summary of the institute for human and machine cognition’s experience with LittleDog,” The International Journal of Robotics Research, vol. 30, no. 2, pp. 216–235, 2011.
  20. P. Fankhauser, M. Bloesch, and M. Hutter, “Probabilistic terrain mapping for mobile robots with uncertain localization,” IEEE Robotics and Automation Letters, vol. 3, no. 4, pp. 3019–3026, 2018.
  21. T. Miki, L. Wellhausen, R. Grandia, F. Jenelten, T. Homberger, and M. Hutter, “Elevation mapping for locomotion and navigation using gpu,” in 2022 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2022, pp. 2273–2280.
  22. G. Erni, J. Frey, T. Miki, M. Mattamala, and M. Hutter, “Mem: Multi-modal elevation mapping for robotics and learning,” in 2023 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).   IEEE, 2023, pp. 11 011–11 018.
  23. J. Z. Kolter, Y. Kim, and A. Y. Ng, “Stereo vision and terrain modeling for quadruped robots,” in 2009 IEEE International Conference on Robotics and Automation.   IEEE, 2009, pp. 1557–1564.
  24. I. Havoutis, J. Ortiz, S. Bazeille, V. Barasuol, C. Semini, and D. G. Caldwell, “Onboard perception-based trotting and crawling with the hydraulic quadruped robot (HyQ),” in 2013 IEEE/RSJ International Conference on Intelligent Robots and Systems.   IEEE, 2013, pp. 6052–6057.
  25. D. Kim, D. Carballo, J. Di Carlo, B. Katz, G. Bledt, B. Lim, and S. Kim, “Vision aided dynamic exploration of unstructured terrain with a small-scale quadruped robot,” in 2020 IEEE International Conference on Robotics and Automation (ICRA).   IEEE, 2020, pp. 2464–2470.
  26. F. Jenelten, T. Miki, A. E. Vijayan, M. Bjelonic, and M. Hutter, “Perceptive locomotion in rough terrain–online foothold optimization,” IEEE Robotics and Automation Letters, vol. 5, no. 4, pp. 5370–5376, 2020.
  27. F. Jenelten, R. Grandia, F. Farshidian, and others, “TAMOLS: Terrain-aware motion optimization for legged systems,” IEEE Transactions on, 2022.
  28. R. Grandia, F. Jenelten, S. Yang, and others, “Perceptive locomotion through nonlinear Model-Predictive control,” IEEE Transactions, 2023.
  29. J. Tan, T. Zhang, E. Coumans, A. Iscen, Y. Bai, D. Hafner, S. Bohez, and V. Vanhoucke, “Sim-to-real: Learning agile locomotion for quadruped robots,” in Robotics: Science and Systems, 2018.
  30. J. Hwangbo, J. Lee, A. Dosovitskiy, D. Bellicoso, V. Tsounis, V. Koltun, and M. Hutter, “Learning agile and dynamic motor skills for legged robots,” Sci Robot, vol. 4, no. 26, Jan. 2019.
  31. X. B. Peng, E. Coumans, T. Zhang, T.-W. Lee, J. Tan, and S. Levine, “Learning agile robotic locomotion skills by imitating animals,” Robotics: Science and Systems, 2020.
  32. N. Rudin, D. Hoeller, P. Reist, and M. Hutter, “Learning to walk in minutes using massively parallel deep reinforcement learning,” in Conference on Robot Learning.   PMLR, 2022, pp. 91–100.
  33. J. Siekmann, K. Green, J. Warila, A. Fern, and J. Hurst, “Blind bipedal stair traversal via sim-to-real reinforcement learning,” in Robotics: Science and Systems, 2021.
  34. S. Gangapurwala, M. Geisert, R. Orsolino, M. Fallon, and I. Havoutis, “RLOC: Terrain-aware legged locomotion using reinforcement learning and optimal control,” arXiv preprint arXiv:2012.03094, 2020.
  35. K. Caluwaerts, A. Iscen, J. C. Kew, W. Yu, T. Zhang, D. Freeman, K.-H. Lee, L. Lee, S. Saliceti, V. Zhuang et al., “Barkour: Benchmarking animal-level agility with quadruped robots,” arXiv preprint arXiv:2305.14654, 2023.
  36. D. Hoeller, N. Rudin, C. Choy, and others, “Neural scene representation for locomotion on structured terrain,” IEEE Robotics and, 2022.
  37. C. S. Imai, M. Zhang, Y. Zhang, M. Kierebiński, R. Yang, Y. Qin, and X. Wang, “Vision-Guided quadrupedal locomotion in the wild with Multi-Modal delay randomization,” pp. 5556–5563, Oct. 2022.
  38. J. Schulman, F. Wolski, P. Dhariwal, A. Radford, and O. Klimov, “Proximal policy optimization algorithms,” arXiv preprint arXiv:1707.06347, 2017.
  39. H. Oleynikova, Z. Taylor, M. Fehr, R. Siegwart, and J. Nieto, “Voxblox: Incremental 3d euclidean signed distance fields for on-board mav planning,” in IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), 2017.
  40. A. Hornung, K. M. Wurm, M. Bennewitz, C. Stachniss, and W. Burgard, “Octomap: an efficient probabilistic 3d mapping framework based on octrees.” Auton. Robots, vol. 34, no. 3, pp. 189–206, 2013. [Online]. Available: http://dblp.uni-trier.de/db/journals/arobots/arobots34.html#HornungWBSB13
  41. M. Gumin, “WaveFunctionCollapse,” https://github.com/mxgmn/WaveFunctionCollapse.
  42. J. Hwangbo, J. Lee, and M. Hutter, “Per-contact iteration method for solving contact dynamics,” IEEE Robotics and Automation Letters, vol. 3, no. 2, pp. 895–902, 2018. [Online]. Available: www.raisim.com
  43. V. Makoviychuk, L. Wawrzyniak, Y. Guo, M. Lu, K. Storey, M. Macklin, D. Hoeller, N. Rudin, A. Allshire, A. Handa, and Gavriel State, “Isaac gym: High performance GPU-Based physics simulation for robot learning,” Aug. 2021.
User Edit Pencil Streamline Icon: https://streamlinehq.com
Authors (4)
  1. Takahiro Miki (22 papers)
  2. Joonho Lee (104 papers)
  3. Lorenz Wellhausen (13 papers)
  4. Marco Hutter (165 papers)
Citations (12)
Youtube Logo Streamline Icon: https://streamlinehq.com