Abstract
The legged robot is only satisfied with walking on flat ground, it obviously does not take advantage of its locomotion performance, especially in the real environment where the robot may encounter various complex terrains. It is a highly nonlinear system for the quadruped robot, so it is very hard to model the dynamics accurately and achieve high performance locomotion control. In recent years, with the emerging of reinforcement learning, there are more possibilities to improve the locomotion ability of legged robots. To address the problem of how to improve the ability of a quadruped robot to negotiate complex terrains, this paper proposes a method to provide an animal-like eye for a quadruped robot to obtain a control strategy based on reinforcement learning. The method uses only the terrain information in front of the quadruped robot as the input state of the robot, and uses a curriculum training method to make the quadruped robot negotiate complex terrains such as the stairway terrain and the gap terrain constructed in the simulation environment smoothly. Compared with the motion strategy based on proprioception only, the vision-assisted motion strategy is safer and smoother, and we utilize less and simpler visual information than other methods based on visual information.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Kim, D., Di Carlo, J., Katz, B.: Highly dynamic quadruped locomotion via whole-body impulse control and model predictive control. arXiv preprint arXiv:1909.06586 (2019)
Hwangbo, J., et al.: Learning agile and dynamic motor skills for legged robots. Sci. Robot. 4(26), eaau5872 (2019). 2470-9476
Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning quadrupedal locomotion over challenging terrain. Sci. Robot. 5(47), eabc5986 (2020). 2470-9476
Miki, T., Lee, J., Hwangbo, J., Wellhausen, L., Koltun, V., Hutter, M.: Learning robust perceptive locomotion for quadrupedal robots in the wild. Sci. Robot. 7(62), eabk2822 (2022). 2470-9476
Zhang, H., Starke, S., Komura, T., Saito, J.: Mode-adaptive neural networks for quadruped motion control. ACM Trans. Graph. 37(4), 145 (2018). 0730-0301
Jain, D., Iscen, A., Caluwaerts, K.: 2019 IEEE/RSJ International Conference on Intelligent Robots and Systems, IROS 2019, Macau, SAR, China, November 3–8, 2019, pp. 7551–7557. IEEE (2019a). https://doi.org/10.1109/IROS40897.2019.8967913
Xie, Z., Da, X., van de Panne, M., Babich, B., Garg, A.: Dynamics randomization revisited: a case study for quadrupedal locomotion. In: 2021 IEEE International Conference on Robotics and Automation (ICRA), Xi’an, China (2021)
Peng, X., Coumans, E., Zhang, T., Lee, T.-W.E., Tan, J., Levine, S.: Learning agile robotic locomotion skills by imitating animals. Robot. Sci. Syst. 07 (2020). https://doi.org/10.15607/RSS.2020.XVI.064
Ji, G., Mun, J., Kim, H., Hwangbo, J.: Concurrent training of a control policy and a state estimator for dynamic and robust legged locomotion. IEEE Robot. Autom. Lett.  7(2) (2022). 4630-4637
Agarwal, A., Kumar, A., Malik, J., Pathak, D.: Legged locomotion in challenging terrains using egocentric vision. arXiv e-prints (2022)
Kareer, S., Yokoyama, N., Batra, D., Ha, S., Truong, J.: ViNL: visual navigation and locomotion over obstacles. arXiv:2210.14791 (2022)
Loquercio, A., Kumar, A., Malik, J.: Learning visual locomotion with cross-modal supervision. arXiv:2211.03785v1 (2022)
Yang, R., Zhang, M., Hansen, N., Xu, H., Wang, X.: Learning vision-guided quadrupedal locomotion end-to-end with cross-modal transformers. arXiv:2107.03996 (2021)
Torres-Pardo, A., et al.: Legged locomotion over irregular terrains: state of the art of human and robot performance. Bioinspir. Biomim. 17(6) (2022). 1748-3190
Grandia, R., Taylor, A.J., Ames, A.D., Hutter, M.: Multi-layered safety for legged robots via control barrier functions and model predictive control. In: International Conference on Robotics and Automation (ICRA 2021), Xi’an, China (2021)
Hutter, M., et al.: ANYmal-a highly mobile and dynamic quadrupedal robot. In: 2016 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS). IEEE (2016)
Gehring, C., et al.: Practice makes perfect: an optimization-based approach to controlling agile motions for a quadruped robot. IEEE Robot. Autom. Mag. 23(1), 34–43 (2016). 1070-9932
Qi, S., Lin, W., Hong, Z., Chen, H., Zhang, W.: Perceptive autonomous stair climbing for quadrupedal robots. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic (2021)
Zico Kolter, J., Ng, A.Y.: The Stanford LittleDog: a learning and rapid replanning approach to quadruped locomotion. Int. J. Robot. Res. 30(2), 150–174 (2011). 0278-3649
Zucker, M., Andrew Bagnell, J., Atkeson, C.G., Kuffner, J.: An optimization approach to rough terrain locomotion. In: 2010 IEEE International Conference on Robotics and Automation. IEEE (2010)
Zucker, M., et al.: Optimization and learning for rough terrain legged locomotion. Int. J. Robot. Res. 30(2), 175–191 (2011). 0278-3649
Tan, W., et al.: A hierarchical framework for quadruped locomotion based on reinforcement learning. In: 2021 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), Prague, Czech Republic (2021)
Kumar, A., Fu, Z., Pathak, D., Malik, J.: RMA: rapid motor adaptation for legged robots. In: Robotics: Science and Systems XVII (2021). https://doi.org/10.15607/RSS.2021.XVII.011
Makoviychuk, V., et al.:: Isaac Gym: high performance GPU-based physics simulation for robot learning. arXiv preprint arXiv:2108.10470 (2021)
Nikita, R., David, H., Philipp, R., Marco, H.: Learning to walk in minutes using massively parallel deep reinforcement learning. In: Proceedings of Machine Learning Research,  vol. 164,  pp. 91–100 (2022). 2640-3498
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv preprint (2017). https://doi.org/10.48550/arXiv.1707.06347
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.
About this paper
Cite this paper
Wei, X., Wei, Q., An, H., Zhang, Z., Yu, J., Ma, H. (2023). Animal-Like Eye Vision Assisted Locomotion of a Quadruped Based on Reinforcement Learning. In: Yang, H., et al. Intelligent Robotics and Applications. ICIRA 2023. Lecture Notes in Computer Science(), vol 14267. Springer, Singapore. https://doi.org/10.1007/978-981-99-6483-3_14
Download citation
DOI: https://doi.org/10.1007/978-981-99-6483-3_14
Published:
Publisher Name: Springer, Singapore
Print ISBN: 978-981-99-6482-6
Online ISBN: 978-981-99-6483-3
eBook Packages: Computer ScienceComputer Science (R0)