Assistive Robotics @ RSS 2024

Overview

The societal challenges arising from a diminished workforce of caregivers and nurses due to declining birth rates and increased life expectancy are significant. A potential solution lies in the automation of assistive tasks through the use of robots. However, the caregiving environment presents a particularly intricate operational setting for robots. In such contexts, tasks may involve direct interaction with individuals who are frequently frail or disabled.

Unlike traditional manipulation scenarios where objects are assumed to be rigid, the caregiving environment introduces soft and deformable objects, including but not limited to bed sheets, clothes, and towels. Physical interaction is only half of the story, social interaction in elderly care is of equal importance. Socially assistive robotics involves designing robots that can interact with humans in a social context, understanding and responding to high-level social cues. With the emergence of LLMs and VLMs, their integration with socially assistive robots presents new challenges such as bias and fairness. We envision that a robot should have an intuitive and expressive general-purpose language/vision understanding model to assist human with daily tasks.

This workshop is taking a holistic approach to consider assistive robots that include both physical and socially assistive robots, as one may well inform the other. We aim to invite roboticists from diverse backgrounds to discuss, interact, and debate on pressing challenges of assistive robots for caregiving, to pave the way to advance the field of research.

Call for Contributions

Participants are encouraged to submit their research for presentation at the workshop. The submitted papers should be no more than 2 pages (excluding references and appendix) and should follow the RSS paper format. Submitted papers will be reviewed by the organizing committee. Accepted papers will be hosted on the workshop website and presented in poster and spotlight sessions. Topics of interest include but are not limited to:

Social Interaction
LLM/LVM in assistive robotics
Multimodal sensing (visual, force, capacitance, tactile, etc) for assistive manipulation
Personalization and safety in HRI context
Long-horizon assistive manipulation tasks
Simulation environment for caregiving and sim-to-real transfer learning
Data-efficient perception and assistive manipulation
Fail-safe strategies for assistive manipulation
Virtual/Augmented Reality User Interfaces for assistive manipulation

Papers submission: Researchers interested in presenting their work during the workshop can submit 2 pages of abstract in the RSS format. Please note that it is possible to use material that has already been presented in a previous conference. Abstracts will be reviewed by the organizers. Papers could be submitted via e-mail to: fan.zhang@honda-ri.de or jihong.zhu@york.ac.uk. Please include "Call for Papers: RSS WS on Learning for Assistive Robots" in the email subject line.

“Blue Sky” papers:

We seek “Blue Sky” submissions (two pages in RSS format) that present a novel high-level perspective of the challenges associated with learning for assistive robotics. Preference will be given to early career academics—senior graduate students, postdocs, and young researchers in academia and industry. Please include “[Blue Sky]” in the paper title.

Important dates

Abstract submission deadline: May 15, 2024 (AoE)
Notification of acceptance: Jun 15, 2024 (AoE) / ASAP
Workshop: July 15, 2024

Presentation instructions

Poster presenters will have to prepare a 1-slide presentation to briefly present their contribution during the "Poster Teasers" and an A0 poster in portrait orientation to be presented during the "Poster Session".