L3H2: Life-Long Learning with Human Help (ICRA 2023) ICRA 2023 London, UK, May 29, 2023 |
| Conference website | https://life-long-learning-with-human-help-l3h2.github.io |
| Submission link | https://easychair.org/conferences/?conf=l3h2 |
Dear Colleagues,
We invite interested researchers to submit their preliminary or ongoing work to our the ICRA'23 Workshop on “Life-Long Learning with Human Help” (L3H2), which will be held as a one-day workshop on May 29, 2023.
==============================
- IMPORTANT DETAILS -
When: May 29, 2023.
Where: Full-day workshop co-located with ICRA 2023 in Londo, United Kingdom.
Website: https://life-long-learning-with-human-help-l3h2.github.io
Paper Submission Deadline: April 28, 2023 (AoE)
Notification of Acceptance: May 12, 2023
Camera Ready: May 24, 2023
Submission website: https://easychair.org/conferences/?conf=l3h2
Submission format: 2-6 page extended abstracts of
original, possibly ongoing research. Papers should be formatted in the ICRA 2023 style guidelines https://www.icra2023.org
==============================
AIM AND SCOPE
We expect autonomous robots to operate with and around humans, to provide added value to the collaborative team, to earn-and-prove trustworthiness, as well as to utilize the support from their human team-mates. The presence of humans brings additional challenges for robot decision-making, but also offers opportunities to improve the decision-making capabilities with human help. Many recent decision-making approaches utilize the synergy of planning and learning (e.g. neuro-symbolic AI). But still, we are missing principled integration of human input into these combined approaches. Human input can play an important role in bridging planning and learning and enable reliable and trustworthy life-long learning with human help. It can be used for grounding learned models, providing “common sense” knowledge, teaching skills, setting goals, etc. In this workshop, we aim to bring together researchers from the field of robot learning, symbolic AI (planning), and human-robot interaction to discuss emerging trends and define common challenges and new opportunities for cross-fertilization in these fields.
TOPICS OF INTEREST
The workshop will tackle topics and invite contributions within, and especially at the intersections of the following areas:
Lifelong learning and curriculum learning
- Learning general robotic task specifications
- Interactive imitation learning
- Learning from demonstration
- Modeling, symbolic model acquisition, representation learning
- Task and motion planning
- Skill learning, cross-domain skill transfer and generalization
- Hierarchical reinforcement learning
- Safe reinforcement learning
- Inverse reinforcement learning
- Neuro-symbolic AI for robotics
- Learning computational models of human behavior for human-robot interaction
- Shared autonomy in human-robot interaction
CALL FOR CONTRIBUTIONS
We invite extended abstract submissions of preliminary or ongoing work related to the topics of interest. These submissions can be:
- Traditional submissions presenting preliminary results of ongoing research (including negative results and open problems)
- Submissions linked to already published papers coming from A) Journal papers which have not had the chance to be discussed in a conference and B) Conference papers from other Robotics and Machine Learning conferences that are of high interest for our workshop.
All accepted abstracts will have the opportunity to be presented at the workshop during a spotlight talk and poster session. We also plan to invite some of the authors of accepted submissions to the junior panel, where current challenges, emerging topics and bluesky ideas will be discussed. This is a non-archival venue: there will be no formal proceedings, but we strongly encourage the authors to publish their extended abstracts on arXiv; links to the papers will be placed on the workshop’s website and will remain available after the workshop.
Submission format: We encourage participants to submit their research in the form of either a paper (6 pages maximum without references), or an extended abstract (2 pages maximum), both using the IEEE conference template. The submitted contributions will go through a single-blind review process.
==============================
Invited Speakers and Panelists:
George Konidaris, Brown University, USA. Karinne Ramirez-Amaro, Chalmers University of Technology, Sweden.
Meng Guo, Peking University, China.
Peter Stone, University of Texas at Austin, USA .
Andy Zeng, Google AI, USA.
Dorsa Sadigh, Stanford University, USA.
Nick Hawes, University of Oxford, United Kingdom.
====================
Organizing Committee:
Zlatan Ajanović, TU Delft, The Netherlands.
Jens Kober, TU Delft, The Netherlands.
Christian Pek, KTH Royal Institute of Technology, Sweden.
Jana Tumova, KTH Royal Institute of Technology, Sweden.
Selma Musić, Stanford University, USA.