Adapting robot task planning to user preferences: an assistive shoe dressing example
- 74 Downloads
Healthcare robots will be the next big advance in humans’ domestic welfare, with robots able to assist elderly people and users with disabilities. However, each user has his/her own preferences, needs and abilities. Therefore, robotic assistants will need to adapt to them, behaving accordingly. Towards this goal, we propose a method to perform behavior adaptation to the user preferences, using symbolic task planning. A user model is built from the user’s answers to simple questions with a fuzzy inference system, and it is then integrated into the planning domain. We describe an adaptation method based on both the user satisfaction and the execution outcome, depending on which penalizations are applied to the planner’s rules. We demonstrate the application of the adaptation method in a simple shoe-fitting scenario, with experiments performed in a simulated user environment. The results show quick behavior adaptation, even when the user behavior changes, as well as robustness to wrong inference of the initial user model. Finally, some insights in a non-simulated world shoe-fitting setup are also provided.
KeywordsPlanning with preferences Behavior adaptation Task personalization Shoe fitting
The authors thank Clea Parcerisas, Sergi Foix and Adrià Colomé for their help in the realization of the experiments, pictures and video.
Supplementary material 1 (mp4 104868 KB)
- Alili, S., Warnier, M., Ali, M., & Alami, R. (2009). Planning and plan-execution for human–robot cooperative task achievement. In 19th international conference on automated planning and scheduling (pp. 19–23).Google Scholar
- Canal, G., Alenyà, G., & Torras, C. (2016). Personalization framework for adaptive robotic feeding assistance. In 8th international conference on social robotics (ICSR) (pp. 22–31).Google Scholar
- Canal, G., Alenyà, G., & Torras, C. (2017). A taxonomy of preferences for physically assistive robots. In IEEE international symposium on robot and human interactive communication (RO-MAN) (pp. 292–297).Google Scholar
- Chance, G., Camilleri, A., Winstone, B., Caleb-Solly, P., & Dogramadzi, S. (2016). An assistive robot to support dressing-strategies for planning and error handling. In Proceedings of the 6th IEEE RAS/EMBS international conference on biomedical robotics and biomechatronics. IEEE.Google Scholar
- de Silva, L., Lallement, R., & Alami, R. (2015). The HATP hierarchical planner: Formalisation and an initial study of its usability and practicality. In 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 6465–6472).Google Scholar
- Gao, Y., Chang, H. J., & Demiris, Y. (2015). User modelling for personalised dressing assistance by humanoid robots. In 2015 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 1840–1845). IEEE.Google Scholar
- Gao, Y., Chang, H. J., & Demiris, Y. (2016). Iterative path optimisation for personalised dressing assistance using vision and force information. In 2016 IEEE/RSJ international conference on intelligent robots and systems (IROS) (pp. 4398–4403).Google Scholar
- Griffith, S., Subramanian, K., Scholz, J., Isbell, C., & Thomaz, A. L. (2013). Policy shaping: Integrating human feedback with reinforcement learning. In C. J. C. Burges, L. Bottou, M. Welling, Z. Ghahramani, & K. Q. Weinberger (Eds.), Advances in neural information processing systems (Vol. 26, pp. 2625–2633). La Jolla: Curran Associates, Inc.Google Scholar
- Heerink, M., Krose, B., Evers, V., & Wielinga, B. (2009). Measuring acceptance of an assistive social robot: A suggested toolkit. In RO-MAN 2009—The 18th IEEE international symposium on robot and human interactive communication (pp. 528–533).Google Scholar
- Klee, S. D., Ferreira, B. Q., Silva, R., Costeira, J. P., Melo, F. S., & Veloso, M. (2015). Personalized assistance for dressing users. In Social robotics: 7th international conference, ICSR 2015 (pp. 359–369). Springer.Google Scholar
- Knox, W. B., & Stone, P. (2009). Interactively shaping agents via human reinforcement: The tamer framework. In The fifth international conference on knowledge capture.Google Scholar
- Lallement, R., De Silva, L., & Alami, R. (2014). HATP: An HTN planner for robotics. In 2nd ICAPS workshop on planning and robotics.Google Scholar
- Quigley, M., Conley, K., Gerkey, B., Faust, J., Foote, T., Leibs, J., Wheeler, R., & Ng, A. Y. (2009). ROS: An open-source robot operating system. In ICRA workshop on open source software (Vol. 3, p. 5).Google Scholar
- Rada-Vilela, J. (2014). fuzzylite: A fuzzy logic control library. http://www.fuzzylite.com. Accessed 26 Oct 2016.
- Tamei, T., Matsubara, T., Rai, A., & Shibata, T. (2011). Reinforcement learning of clothing assistance with a dual-arm robot. In 2011 11th IEEE-RAS international conference on humanoid robots (humanoids) (pp. 733–738). IEEE.Google Scholar
- Thomaz, A. L., & Breazeal, C. (2006). Reinforcement learning with human teachers: Evidence of feedback and guidance with implications for learning performance. In Proceedings of the 21st national conference on artificial intelligence (Vol. 1, pp. 1000–1005). AAAI Press, AAAI’06.Google Scholar
- Vahrenkamp, N., Wächter, M., Kröhnert, M., Welke, K., & Asfour, T. (2015). The robot software framework armarx. Information Technology, 57(2), 99–111.Google Scholar
- Yamazaki, K., Oya, R., Nagahama, K., Okada, K., & Inaba, M. (2014). Bottom dressing by a life-sized humanoid robot provided failure detection and recovery functions. In 2014 IEEE/SICE international symposium on system integration (pp. 564–570).Google Scholar