When? 23rd of October, 9am to 5pm Japan Time
Where? KICC Room RM-2 (Room B-1) and Zoom (https://utexas.zoom.us/j/92382743703)
Objectives
Research in Artificial Intelligence (AI) and robotics has achieved significant mobile robot navigation and fixed base manipulation, but is still limited to specific installations and specialized to single tasks. We believe it is time to build on this significant progress to finally achieve the vision of embodied AI systems that support humans in everyday tasks. Mobile manipulator robots are the most promising candidates for this role, as they combine the advantages of mobile platforms and manipulator arms. The combined mobility and dexterity extend the workspace of statically installed robotic arms, introducing many benefits and challenges to be addressed.
Our IROS2022 MOMA workshop will address the ongoing challenges and opportunities of researching embodied AI mobile manipulator robots in real-world unstructured environments, bringing together a broader community of researchers, from robotics, AI planning, computer vision, and machine learning, who shall come together to discuss and contribute to the challenging topic of embodied AI mobile manipulation.
The workshop’s objectives are to discuss fundamental research questions on mobile manipulation, such as:
- How can we effectively coordinate the properties (embodiments) of mobile manipulators?
- How can we encode (represent) the multimodal information of dynamically changing environments for planning mobile manipulation tasks?
- How can we effectively integrate learning for mobile manipulation? What are the challenges and benefits?
- How can high-level decision-making affect the low-level mobile manipulation execution?
Some applications related to mobile manipulation robots are personal assistants, nursing assistants, office cleaners, disinfection, agriculture, shopping assistants, logistics, warehouse assistants, space missions, etc.
While the topic of mobile manipulation has been in the research spotlight the previous decade, it has been long hibernated, as researchers focused on challenging aspects of mobile robot navigation, static manipulation, and the coupling of perception and learning mechanisms.
This workshop will serve as the awakening point for the new era of research in mobile manipulation and embodied intelligence, bringing together a cohort of top researchers in perception, learning, robotics, and control.
Topics of Interest
- (Bimanual) mobile manipulation, mobile legged manipulation, aerial mobile manipulation, underwater mobile manipulation
- Dynamic mobile manipulation
- Active robot perception, partial observability, sensing uncertainty
- Representation learning for mobile manipulation
- Sensorial integration for mobile manipulation
- Interactive navigation, whole-body motion planning
- Whole-body control, whole-body coordination, impedance control
- (Hierarchical) Reinforcement learning of mobile manipulation
- Embodied perception
- Embodied Intelligence
- Cognitive Learning
- High-level decision-making and reasoning
- Task and Motion planning
- Long-horizon planning
- System Integration
Speakers
Program
| Time | Event | Speaker |
|---|---|---|
| 9:00 – 9:05 | Introduction | by the Organizing Committee |
| 9:05 – 9:30 | Talk: Neural Radiance fields as a Unified Representation for Navigation and Manipulation | Jeannette Bohg |
| 9:30 – 09:55 | Talk: Object-centric Adaptation for Robust Manipulation Skills | Oliver Kroemer |
| 09:55 – 10:20 | Talk: Learning with Tactile Fingers | Matei Ciocarlei |
| 10:20 – 10:50 | Posters + Coffee Break | |
| 10:50 – 11:15 | Talk: TBD | Jitendra Malik |
| 11:15 – 11:45 | Panel Discussion: Effective representations and abstractions in mobile manipulation | Moderator: Roberto Martin-Martin |
| 11:45 – 12:00 | 1. Semantic Frame Mapping for Building-wide Perception and Affordance Execution, by Cameron E Kisailus 2. End-Effector Contact Force Estimation for Aerial Manipulators, by Anton Bredenbeck 3. Towards generic object property estimation using Unsupervised Reinforcement Learning, Maxime Chareyre | Spotlight talks |
| 12:00 – 13:00 | Lunch break | |
| 13:00 – 13:25 | Talk: Mobile Manipulation for in-space assembly and servicing operations | Maximo Roa |
| 13:25 – 13:40 | Mobile Manipulation: Challenges and Opportunities | Roberto Martin-Martin & Georgia Chalvatzaki |
| 13:40 – 14:05 | Talk: Robots that learn from experience to improve low-level manipulation tasks | Karinne Ramirez-Amaro |
| 14:05 – 14:30 | Talk: Teleoperating a legged manipulator: challenges and prospects | Firas Abi Farraj |
| 14:30 – 15:00 | Posters + Coffee Break | |
| 15:00 – 15:15 | 4. N2M2: Learning Navigation for Arbitrary Mobile Manipulation Motions in Unseen and Dynamic Environments, by Daniel Honerkamp 5. A Hybrid Learning and Optimization Framework to Achieve Physically Interactive Tasks with Mobile Manipulators, by Jianzhuang Zhao 6. Robot Learning of Mobile Manipulation with Reachability Behavior Priors, by Snehal Jauhri | Spotlight talks |
| 15:15 – 15:40 | Talk: Astronaut-in-the-loop mobile manipulation for planetary surface infrastructure maintenance | Daniel Leidner |
| 15:40 – 16:05 | Talk: Learning when to Trust Unreliable Models for Manipulation in Unstructured Environments (pre-recorded) | Dmitry Berenson |
| 16:05 – 16:35 | Panel discussion: The challenges of controlling and orchestrating behaviors for mobile manipulation systems | Moderator: Georgia Chalvatzaki |
| 16:35 – 16:45 | 7. A Causal-based Method to Find Explanations for Robot Failures, by Maximilian Diehl 8. The TIAGo Family of Robots: Past, Present, and Future, by Narcis Miguel | Spotlight talk |
| 16:45 – 17:00 | Networking and Sponsors | |
| 17:00 – 17:05 | Closing Remarks and Award Ceremony |
Accepted Papers
Call for Papers
We encourage participants to submit their research related to the topics of interest in this workshop in a single PDF. Submissions may be up to 4 pages long, including figures but excluding references and supplementary material. Please use the IEEE conference template.
Any type of contribution, either already published or work in progress, is welcome to our workshop.
Accepted papers will be presented in a poster session and selected papers as spotlight talks. All submitted contributions will go through a single-blind review process. The contributed papers will be made available on the workshop’s website. However, this does not constitute an archival publication and no formal workshop proceedings will be made available, meaning contributors are free to publish their work in archival journals or conferences.
PAL Robotics offers a Best Paper Award of $500!!!
Submission Deadline: 27 September 2022, 23:59pm PT
Notification of Acceptance: 30 September 2022 05 October 2022
Submission Website: https://cmt3.research.microsoft.com/MOMA2022
LaTeX Template: http://ras.papercept.net/conferences/support/tex.php
Student travel grant sponsored by the TC on Mobile Manipulation
We offer one travel grant for IROS 2022 in conjunction with this workshop to cover expenses of up to $2,500. The award refers to students who want to show their active interest in the mobile manipulation field, particularly those from underrepresented groups.
Submit together with your short paper a motivation letter of up to two pages and attach your CV as a single PDF as supplementary material, with a filename TCMM_StudentAward_Surname.pdf
Organizers
Sponsors
Supported by the IEEE RAS TC on Mobile Manipulation and the IEEE RAS TC on Robotic Hands, Grasping, and Manipulation