{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,15]],"date-time":"2026-01-15T01:49:10Z","timestamp":1768441750254,"version":"3.49.0"},"reference-count":52,"publisher":"MDPI AG","issue":"2","license":[{"start":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T00:00:00Z","timestamp":1768348800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Sensors"],"abstract":"<jats:p>In recent years, while progress has been made in barrier-free design, the complete elimination of physical barriers such as uneven road surfaces and stairs remains difficult, and wheelchair passengers continue to face significant mobility constraints. This study aims to verify the effectiveness of a transformable quadruped wheelchair that can switch between two modes of movement: walking and wheeled travel. Specifically, reinforcement learning using Proximal Policy Optimization (PPO) was used to acquire walking strategies for uneven terrain and wheeled travel strategies for flat terrain. NVIDIA Isaac Sim was used for simulation. To evaluate the stability of both modes, we performed a frequency analysis of the passenger\u2019s acceleration data. As a result, we observed periodic vibrations around 2 Hz in the vertical direction in walking mode, while in wheeled mode, we confirmed extremely small vibrations and stable running. Furthermore, we distilled these two strategies into a single mode-conditional strategy and conducted long-distance running experiments involving mode transformation. The results demonstrated that by adaptively switching between walking and wheeled modes depending on the terrain, mobility efficiency was significantly improved compared to continuous operation in a single mode. This study demonstrates the effectiveness of an approach that involves learning multiple specialized strategies and switching between them as needed to efficiently traverse diverse environments using a transformable robot.<\/jats:p>","DOI":"10.3390\/s26020566","type":"journal-article","created":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:12:04Z","timestamp":1768403524000},"page":"566","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Transformable Quadruped Wheelchair: Unified Walking and Wheeled Locomotion via Mode-Conditioned Policy Distillation"],"prefix":"10.3390","volume":"26","author":[{"given":"Atsuki","family":"Akamisaka","sequence":"first","affiliation":[{"name":"Department of Intelligent Systems, Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6973-7340","authenticated-orcid":false,"given":"Katashi","family":"Nagao","sequence":"additional","affiliation":[{"name":"Department of Intelligent Systems, Graduate School of Informatics, Nagoya University, Nagoya 464-8603, Japan"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"1968","published-online":{"date-parts":[[2026,1,14]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","unstructured":"Akamisaka, A., and Nagao, K. (2025, January 14\u201318). Acquisition and Evaluation of Walking and Wheel Movement for a Transformable Quadruped Wheelchair Using Reinforcement Learning. Proceedings of the 2025 International Conference on Simulation, Modeling, and Programming for Autonomous Robots (SIMPAR), Palermo, Italy.","DOI":"10.1109\/SIMPAR62925.2025.10979006"},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"211","DOI":"10.3109\/17483107.2014.898159","article-title":"Power Wheelchair Driving Challenges in the Community: A Users\u2019 Perspective","volume":"10","author":"Torkia","year":"2015","journal-title":"Disabil. Rehabil. Assist. Technol."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"918","DOI":"10.1080\/01691864.2017.1378591","article-title":"ANYmal\u2014Toward Legged Robots for Harsh Environments","volume":"31","author":"Hutter","year":"2017","journal-title":"Adv. Robot."},{"key":"ref_4","unstructured":"Unitree Robotics (2024, March 24). Unitree B2 Go Beyond the Limits. Available online: https:\/\/m.unitree.com\/b2\/."},{"key":"ref_5","doi-asserted-by":"crossref","unstructured":"Di Carlo, J., Wensing, P.M., Katz, B., Bledt, G., and Kim, S. (2018, January 1\u20135). Dynamic Locomotion in the MIT Cheetah 3 Through Convex Model-Predictive Control. Proceedings of the 2018 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Madrid, Spain.","DOI":"10.1109\/IROS.2018.8594448"},{"key":"ref_6","doi-asserted-by":"crossref","unstructured":"Li, W., Wei, L., and Zhang, X. (2022). A Wheels-on-Knees Quadruped Assistive Robot to Carry Loads. Appl. Sci., 12.","DOI":"10.3390\/app12189239"},{"key":"ref_7","doi-asserted-by":"crossref","unstructured":"Akamisaka, A., and Nagao, K. (2023, January 25\u201328). Autonomous Stair Ascending and Descending by Quadruped Wheelchairs. Proceedings of the 2023 20th International Conference on Ubiquitous Robots (UR), Honolulu, HI, USA.","DOI":"10.1109\/UR57808.2023.10202377"},{"key":"ref_8","doi-asserted-by":"crossref","unstructured":"Akamisaka, A., and Nagao, K. (2024). Transformable Quadruped Wheelchairs Capable of Autonomous Stair Ascent and Descent. Sensors, 24.","DOI":"10.3390\/s24113675"},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"1601","DOI":"10.1016\/j.mechmachtheory.2011.07.005","article-title":"Wheelchair.q, a Motorized Wheelchair with Stair Climbing Ability","volume":"46","author":"Quaglia","year":"2011","journal-title":"Mech. Mach. Theory"},{"key":"ref_10","unstructured":"Sutton, R.S., and Barto, A.G. (2018). Reinforcement Learning: An Introduction, A Bradford Book."},{"key":"ref_11","unstructured":"Rusu, A.A., Colmenarejo, S.G., G\u00fcl\u00e7ehre, \u00c7., Desjardins, G., Kirkpatrick, J., Pascanu, R., Mnih, V., Kavukcuoglu, K., and Hadsell, R. (2015). Policy Distillation. arXiv."},{"key":"ref_12","unstructured":"Maurya, S.K. (2019, January 30\u201331). Design and Application of Crawler Robot. Proceedings of the 6th National Conference on Advancements in Simulation and Experimental Techniques in Mechanical Engineering (NCASEme), Chandigarh, India."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"3626","DOI":"10.1109\/LRA.2020.2979661","article-title":"Rolling in the Deep\u2014Hybrid Locomotion for Wheeled-Legged Robots Using Online Trajectory Optimization","volume":"5","author":"Bjelonic","year":"2020","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"1595","DOI":"10.1109\/LRA.2019.2896758","article-title":"CENTAURO: A Hybrid Locomotion and High Power Resilient Manipulation Platform","volume":"4","author":"Kashiri","year":"2019","journal-title":"IEEE Robot. Autom. Lett."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"eaau5872","DOI":"10.1126\/scirobotics.aau5872","article-title":"Learning Agile and Dynamic Motor Skills for Legged Robots","volume":"4","author":"Hwangbo","year":"2019","journal-title":"Sci. Robot."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"eabc5986","DOI":"10.1126\/scirobotics.abc5986","article-title":"Learning Quadrupedal Locomotion over Challenging Terrain","volume":"5","author":"Lee","year":"2020","journal-title":"Sci. Robot."},{"key":"ref_17","unstructured":"Heess, N., TB, D., Sriram, S., Lemmon, J., Merel, J., Wayne, G., Tassa, Y., Erez, T., Wang, Z., and Eslami, S.M.A. (2017). Emergence of Locomotion Behaviours in Rich Environments. arXiv."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"679","DOI":"10.1512\/iumj.1957.6.56038","article-title":"A Markovian Decision Process","volume":"6","author":"Bellman","year":"1957","journal-title":"Indiana Univ. Math. J."},{"key":"ref_19","unstructured":"Lippmann, R.P., Moody, J., and Touretzky, D. (1990). Integrated Modeling and Control Based on Reinforcement Learning and Dynamic Programming. Advances in Neural Information Processing Systems, Morgan-Kaufmann."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1023\/A:1022633531479","article-title":"Learning to Predict by the Methods of Temporal Differences","volume":"3","author":"Sutton","year":"1988","journal-title":"Mach. Learn."},{"key":"ref_21","unstructured":"Mnih, V., Kavukcuoglu, K., Silver, D., Graves, A., Antonoglou, I., Wierstra, D., and Riedmiller, M. (2013). Playing Atari with Deep Reinforcement Learning. arXiv."},{"key":"ref_22","unstructured":"Konda, V.R., and Tsitsiklis, J.N. (2000). Actor-Critic Algorithms. Advances in Neural Information Processing Systems, MIT Press."},{"key":"ref_23","unstructured":"Haarnoja, T., Zhou, A., Abbeel, P., and Levine, S. (2018, January 10\u201315). Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor. Proceedings of the 35th International Conference on Machine Learning, Stockholm, Sweden."},{"key":"ref_24","unstructured":"Rudin, N., Hoeller, D., Reist, P., and Hutter, M. (2021). Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learning. arXiv."},{"key":"ref_25","unstructured":"Iscen, A., Caluwaerts, K., Tan, J., Zhang, T., Coumans, E., Sindhwani, V., and Vanhoucke, V. (2019). Policies Modulating Trajectory Generators. arXiv."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"11945","DOI":"10.1038\/s41598-023-38259-7","article-title":"Controlling the Solo12 Quadruped Robot with Deep Reinforcement Learning","volume":"13","author":"Aractingi","year":"2023","journal-title":"Sci. Rep."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"572","DOI":"10.1177\/02783649231224053","article-title":"Rapid Locomotion via Reinforcement Learning","volume":"43","author":"Margolis","year":"2022","journal-title":"Int. J. Robot. Res."},{"key":"ref_28","unstructured":"Schulman, J., Wolski, F., Dhariwal, P., Radford, A., and Klimov, O. (2017). Proximal Policy Optimization Algorithms. arXiv."},{"key":"ref_29","doi-asserted-by":"crossref","unstructured":"Bengio, Y., Louradour, J., Collobert, R., and Weston, J. (2009, January 14). Curriculum Learning. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada.","DOI":"10.1145\/1553374.1553380"},{"key":"ref_30","doi-asserted-by":"crossref","unstructured":"Tobin, J., Fong, R., Ray, A., Schneider, J., Zaremba, W., and Abbeel, P. (2017, January 24\u201328). Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World. Proceedings of the 2017 IEEE\/RSJ International Conference on Intelligent Robots and Systems (IROS), Vancouver, BC, Canada.","DOI":"10.1109\/IROS.2017.8202133"},{"key":"ref_31","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Andrychowicz, M., Zaremba, W., and Abbeel, P. (2018, January 21\u201325). Sim-to-Real Transfer of Robotic Control with Dynamics Randomization. Proceedings of the 2018 IEEE International Conference on Robotics and Automation (ICRA), Brisbane, QLD, Australia.","DOI":"10.1109\/ICRA.2018.8460528"},{"key":"ref_32","doi-asserted-by":"crossref","unstructured":"Tan, J., Zhang, T., Coumans, E., Iscen, A., Bai, Y., Hafner, D., Bohez, S., and Vanhoucke, V. (2018). Sim-to-Real: Learning Agile Locomotion For Quadruped Robots. arXiv.","DOI":"10.15607\/RSS.2018.XIV.010"},{"key":"ref_33","unstructured":"Czarnecki, W.M., Pascanu, R., Osindero, S., Jayakumar, S.M., Swirszcz, G., and Jaderberg, M. (2019). Distilling Policy Distillation. arXiv."},{"key":"ref_34","unstructured":"Hinton, G.E., Vinyals, O., and Dean, J. (2015). Distilling the Knowledge in a Neural Network. arXiv."},{"key":"ref_35","unstructured":"Polino, A., Pascanu, R., and Alistarh, D. (2018). Model Compression via Distillation and Quantization. arXiv."},{"key":"ref_36","unstructured":"Parisotto, E., Ba, J., and Salakhutdinov, R. (2015). Actor-Mimic: Deep Multitask and Transfer Reinforcement Learning. arXiv."},{"key":"ref_37","unstructured":"Teh, Y.W., Bapst, V., Czarnecki, W.M., Quan, J., Kirkpatrick, J., Hadsell, R., Heess, N.M.O., and Pascanu, R. (2017). Distral: Robust Multitask Reinforcement Learning. Advances in Neural Information Processing Systems 30, Neural Information Processing Systems Foundation."},{"key":"ref_38","unstructured":"Berseth, G., Xie, C., Cernek, P., and Panne, M. (2018). van de Progressive Reinforcement Learning with Distillation for Multi-Skilled Motion Control. arXiv."},{"key":"ref_39","unstructured":"Traor\u00e9, K.R., Caselles-Dupr\u00e9, H., Lesort, T., Sun, T., Cai, G., Rodr\u00edguez, N.D., and Filliat, D. (2019). DisCoRL: Continual Reinforcement Learning via Policy Distillation. arXiv."},{"key":"ref_40","unstructured":"Rudin, N., He, J., Aurand, J., and Hutter, M. (2025). Parkour in the Wild: Learning a General and Extensible Agile Locomotion Policy Using Multi-Expert Distillation and RL Fine-Tuning. arXiv."},{"key":"ref_41","doi-asserted-by":"crossref","unstructured":"Kim, T., Oh, J., Kim, N., Cho, S., and Yun, S.-Y. (2021). Comparing Kullback-Leibler Divergence and Mean Squared Error Loss in Knowledge Distillation. arXiv.","DOI":"10.24963\/ijcai.2021\/362"},{"key":"ref_42","doi-asserted-by":"crossref","unstructured":"Kessler, S., Parker-Holder, J., Ball, P.J., Zohren, S., and Roberts, S.J. (2021). Same State, Different Task: Continual Reinforcement Learning without Interference. arXiv.","DOI":"10.1609\/aaai.v36i7.20674"},{"key":"ref_43","unstructured":"Arulkumaran, K., Dilokthanakul, N., Shanahan, M., and Bharath, A.A. (2016). Classifying Options for Deep Reinforcement Learning. arXiv."},{"key":"ref_44","unstructured":"(2024, March 24). Unitree_Ros. Available online: https:\/\/github.com\/unitreerobotics\/unitree_ros."},{"key":"ref_45","unstructured":"NVIDIA (2025, August 15). NVIDIA Isaac Lab. Available online: https:\/\/developer.nvidia.com\/isaac\/lab."},{"key":"ref_46","unstructured":"(2024, March 24). RS-Bpearl. Available online: https:\/\/www.robosense.ai\/en\/IncrementalComponents\/Bpearl."},{"key":"ref_47","doi-asserted-by":"crossref","unstructured":"Nobili, S., Camurri, M., Barasuol, V., Focchi, M., Caldwell, D., Semini, C., and Fallon, M. (2017, January 12\u201316). Heterogeneous Sensor Fusion for Accurate State Estimation of Dynamic Legged Robots. Proceedings of the Robotics: Science and Systems XIII, Massachusetts, MA, USA.","DOI":"10.15607\/RSS.2017.XIII.007"},{"key":"ref_48","doi-asserted-by":"crossref","unstructured":"Chen, J., Liang, Z., Zhu, Y., Liu, C., Zhang, L., Hao, L., and Zhao, J. (2019). Towards the Exploitation of Physical Compliance in Segmented and Electrically Actuated Robotic Legs: A Review Focused on Elastic Mechanisms. Sensors, 19.","DOI":"10.3390\/s19245351"},{"key":"ref_49","doi-asserted-by":"crossref","unstructured":"Ilyas, M., Cho, J.S., Park, S., and Baeg, S.-H. (2013, January 24\u201326). Attitude Stabilization of Quadruped Walking Robot. Proceedings of the IEEE ISR 2013, Seoul, Republic of Korea.","DOI":"10.1109\/ISR.2013.6695686"},{"key":"ref_50","unstructured":"Clevert, D.-A., Unterthiner, T., and Hochreiter, S. (2015). Fast and Accurate Deep Network Learning by Exponential Linear Units (ELUs). arXiv."},{"key":"ref_51","unstructured":"NVIDIA (2025, August 15). NVIDIA Isaac Sim. Available online: https:\/\/developer.nvidia.com\/isaac\/sim."},{"key":"ref_52","unstructured":"(2024, March 24). Tesla Bot FBX. Available online: https:\/\/sketchfab.com\/3d-models\/tesla-bot-fbx-627f9141da354a97acc7835c458df8f8."}],"container-title":["Sensors"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/566\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,14]],"date-time":"2026-01-14T15:13:51Z","timestamp":1768403631000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1424-8220\/26\/2\/566"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1,14]]},"references-count":52,"journal-issue":{"issue":"2","published-online":{"date-parts":[[2026,1]]}},"alternative-id":["s26020566"],"URL":"https:\/\/doi.org\/10.3390\/s26020566","relation":{},"ISSN":["1424-8220"],"issn-type":[{"value":"1424-8220","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1,14]]}}}