Adaptation and effective communication in collaborative physically Assistive Tasks

Physical robotic Assistance can often be modelled as a collaborative task in which the goal of both the user and the robot is to complete an assistive task together. However, assistive settings have a lot of particularities that differentiate them from traditional Human-Robot Collaboration tasks. For it to be effective, the assistance should be seamless, natural, and without a required effort on the user’s side. This means that these robots must be able to communicate with the user in a very natural and intuitive way, but also in an adaptive manner. In this project, we will investigate the development of techniques for the online adaptation of the robot to the human, as well as anticipation of user needs, and seamless communication in the context of assistive tasks such as robotic feeding and dressing. For this, the different input signals that may be used to drive the robot’s behaviour will be analysed (i.e., user expressions and movements, physiological responses, and behaviour), and will be integrated into a system that may assist the user in a proactive manner. The project will also consider the social aspects and impacts of the task, evaluating the feasibility of the proposed approaches and their potential societal benefits.

The developed methods will therefore intend to make the robotic system more trustworthy by being understandable and legible, as well as to increase the acceptance of the system through an improved interaction methodology that focuses on easy-to-understand signals and proactive robotic behaviours.

[1] Canal, G., Alenya, G., & Torras, C. (2019). Adapting robot task planning to user preferences: an assistive shoe dressing example. Autonomous Robots, 43(6), 1343-1356.
[2] Canal, G., Alenya, G., & Torras, C. (2016). Personalization framework for adaptive robotic feeding assistance. In Social Robotics: 8th International Conference, ICSR 2016, Kansas City, MO, USA, November 1-3, 2016 Proceedings 8 (pp. 22-31). Springer International Publishing.
[3] Bhattacharjee, T., Lee, G., Song, H., & Srinivasa, S. S. (2019). Towards robotic feeding: Role of haptics in fork-based food manipulation. IEEE Robotics and Automation Letters, 4(2), 1485-1492.
[4] Bhattacharjee, T., Gordon, E. K., Scalise, R., Cabrera, M. E., Caspi, A., Cakmak, M., & Srinivasa, S. S. (2020, March). Is more autonomy always better? exploring preferences of users with mobility impairments in robot-assisted feeding. In Proceedings of the 2020 ACM/IEEE international conference on human-robot interaction (pp. 181-190).
[5] Ondras, J., Anwar, A., Wu, T., Bu, F., Jung, M., Ortiz, J. J., & Bhattacharjee, T. (2022, August). Human-robot commensality: Bite timing prediction for robot-assisted feeding in groups. In 6th Annual Conference on Robot Learning.

Project ID