Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI)

About
Today’s high-capacity generalist robot policies provide a strong foundation for broad task-level competence, yet achieving effective and equitable support for people in everyday settings remains a significant challenge. Real-world environments are dynamic and unstructured, and human needs evolve over time, requiring robots that can adapt accordingly. The ultimate evaluator of any robotic system is the person it assists, and personalization is essential to ensuring equitable and meaningful support across diverse users and contexts. Developing robots that can continually learn from interaction, adapt their behaviors over time, and flexibly assume roles as learners and collaborators is a critical step toward realizing effective integration of robots into daily life.

With this year's theme of "Evolving Assistance for Everyday Life", and in alignment with the conference theme "HRI Empowering Society", the sixth edition of the "Lifelong Learning and Personalization in Long-Term Human-Robot Interaction (LEAP-HRI)" workshop aims to bring together insights across diverse disciplines, focusing on how robots can progressively adapt their support to suit diverse individuals, each with unique and changing needs, across real-world contexts. Through this lens, the workshop aims to discuss current and future directions in how assistive systems can flexibly respond, continually improve over time, and deliver more inclusive and empowering support in everyday life.

Schedule

Time (GMT)
14:30 - 14:40		Opening Remarks
14:40 - 15:40		Fireside Chat
15:40 - 16:20		Discussion Session #1
16:20 - 16:30		Break
16:30 - 17:15		Contributed Talks
	16:30 - 16:44	From Long-Term HRI to Dementia Care: Scoping Personalization Approaches [PDF] William Valentine, Selma Šabanović, David Crandall and Weslie Khoo Abstract Lifelong personalization faces a significantly challenging test case in older adults with progressive cognitive decline. We present a scoping review that maps existing personalization mechanisms and identifies gaps relevant to progressive cognitive decline. Dementia renders successful modeling of any aspect of a person’s mind a moving target. A person’s communication abilities, memory, preferences, and interaction patterns change continuously over months and years at variable rates. In this scoping review, we examine the literature on long-term studies of older adults and on robot-assisted interventions for cognitive impairment, as well as the progress made toward personalization in these contexts. We found no evidence of a published system that implements closed-loop adaptation for progressive cognitive decline. We identify and discuss several open challenges in implementing lifelong personalization for older adults with cognitive decline.
	16:45 - 16:59	Structuring User Preferences for Task Delegation and Proactivity in Assistive Meal Preparation: Insights from a User Study [PDF] Han Pan, Ti-Chung Cheng, Yu-Chun Yen and Yi-Ting Chen Abstract Assistive robots could alleviate the physical demands of home meal preparation, yet a central challenge lies in capturing individuals’ nuanced preferences for robotic assistance across tasks and contexts. We introduce a novel framework that models how user characteristics relate to desired types of support and levels of robot proactivity. Twenty participants with diverse cooking experience completed a Quadratic Survey to indicate which physical actions they prioritize for robotic assistance and what levels of proactivity they expect.We found that user profiles and task characteristics jointly shape action prioritization, whereas expectations for proactivity are driven primarily by task and situational factors. We argue that robotic meal preparation should prioritize empowerment over replacement, and offer a design space for personalized assistive technologies.
	17:00 - 17:14	Bimanual Wearable EMG Control for Multi-Day In-Home Mobile Manipulation by a User with Quadriplegia [PDF] Jehan Yang, Eleanor Hodgson, Cindy Sun, Zackory Erickson and Douglas J. Weber Abstract Mobile manipulators in the home can enable people with cSCI to perform daily household tasks that they could not otherwise do themselves, yet paralysis often limits access to traditional control interfaces such as joysticks or keyboards. We introduce and deploy the first system that enables a user with quadriplegia to control a mobile manipulator in their own home using bimanual high-density electromyography (HDEMG).We develop custom fabric-integrated forearm sleeves worn on both arms that capture residual neuromotor activity and support real-time gesture-based robot control. We further integrate vision, language, and motion planning into a shared autonomy framework that assists with alignment and navigation while preserving user control. Finally, we present a twelveday in-home user study demonstrating wearable EMG-based control of diverse activities of daily living (ADLs) and household tasks in a real home environment.
17:15 - 17:55		Discussion Session #2
17:55 - 18:00		Concluding Remarks

Call for Papers

Areas of interest

We encourage researchers and students from HRI, robotics, cognitive science, rehabilitation, social sciences, and educational backgrounds to contribute. The workshop welcomes contributions across a wide range of topics including, but not limited to:

Lifelong personalization and/or adaptation
Continual/lifelong machine learning
Adaptive assistance for evolving daily routines and real-world tasks
Evaluation methods and metrics for long-term adaptive assistance
Balancing autonomy and user control in adaptive assistance
Incremental and/or online learning in HRI
Modeling user(s) and/or user behavior(s) in multi-session/long-term HRI
Modeling robot behavior in multi-session/long-term HRI
Modeling context in multi-session/long-term HRI
Agent/robot architectures for personalization/adaptation
Lifelong (long-term) human-agent or multi-user/multi-agent interactions
Lifelong (long-term) multimodal interactions
Long-term memory (episodic, semantic, associative)
Transfer and generalization of learned behaviors across tasks, users, and contexts
Privacy and ethical considerations in lifelong learning/ personalization in HRI
Cross-cultural adaption in HRI

Submission Guidelines

We invite submissions of scientific papers of 3–4 pages in length, with additional pages permitted for references and appendices. Contributions may include a wide range of work, such as ongoing projects with preliminary results, technical reports, case studies, surveys, or novel research advancing the state of the art in lifelong learning and personalization. Relevant topics span real-world applications including (but not limited to) rehabilitation, elder care, companion robots, collaborative work, education, customer-facing services, and long-term interaction studies.

This year, we particularly encourage submissions that reflect the workshop's theme: "Evolving Assistance for Everyday Life". All papers will undergo peer review to evaluate their relevance, originality, and scientific/technical quality. Authors are expected to follow the HRI 2026 submission guidelines. We welcome contributions from both academia and industry, especially those working in human–robot interaction, robotics, machine learning, cognitive science, and psychology.

Submissions do not need to be anonymized for review. All manuscripts must be written in English and submitted electronically in PDF format via EasyChair. The accepted papers will be published on the workshop website. Depending on the number and quality of submissions, we may also propose extending the workshop outcomes into a Research Topic in Frontiers in Robotics and AI to provide authors with an opportunity to further develop and disseminate their work.

Note that at least one author needs to register to HRI with (or only) workshop option, and attend in person or online for the accepted paper to be presented at the workshop.

Authors should use ACM SIG format (use “sigconf” as document class, instead of “manuscript,screen,review”) template files (US letter). Overleaf template (use “sigconf” as document class, instead of “manuscript,screen,review”).

Important Dates

Early-bird submission deadline: January 25
Early-bird notification of acceptance: January 30
General submission deadline: February 16
General notification of acceptance: March 2
Camera-ready deadline: March 9

All deadlines are at 23:59 Anywhere on Earth time. Deadlines will not be extended.