Robotic Perception and Mapping: Emerging Techniques

This workshop aims to present the latest results on the theory and practice of learning and algorithmic techniques for robotic perception and mapping.  A series of contributed and invited talks by academic leaders and renowned researchers will discuss ground-breaking perception and mapping methods based on optimization and filtering, learning and data-driven models, uncertainty-aware and certifiable perception, multi-agent and distributed mapping, semantic representation, and mesh-based compression. The workshop will also discuss the current challenges and research directions in the next 5-10 years, and will include posters and spotlight talks to facilitate interaction between the speakers and the audience. The workshop plans to have a hybrid format with in-person speakers/attendees and a live broadcast to convey the message to a broader audience. Talk recordings and accepted contributions will be published on the workshop's webpage to broaden the research impact.

Expected outcome:

By facilitating discussion among participants, authors of contributed papers, and invited speakers, the workshop aims to study and answer the following fundamental questions:

1) What are the latest results and emerging research directions for algorithmic perception and mapping (such as optimization and graph-theoretic techniques)? 

2) What are the latest results and emerging research directions for end-to-end and data-driven robotic perception and mapping?

3) How can existing solutions be used in multi-robot and distributed settings with asynchronous and/or incremental data?

4) How to utilize these methods in real-time systems with limited computational resources or in distributed systems with limited communication capacity and what are the trade-offs? 

5) What are the correct notions, quantifications, and measures of accuracy for perception and mapping?

6) How is "failure" defined in perception and mapping and what is the consequence of failure in downstream applications?

Date: Monday, May 23, 2022

Time: 8:30-15:50 US Eastern Daylight Time

Schedule:

8:30 - 10:00 Session 1: 

• 8:30-8:40 Welcome message by organizers 

• 8:40-9:00 Daniel Cremers 

• 9:00-9:20 Luca Carlone

• 9:20-9:40 Kostas Daniilidis

• 9:40-9:50 Spotlight talk 1: "Differentiable Nonparametric Belief Propagation," Anthony Opipari et al.

9:50 - 10:20 Coffee break & posters

10:20 - 12:00 Session 2: 

• 10:20-10:40 Frank Dellaert  

• 10:40-11:00 Nikolay Atansov

• 11:00-11:20 Jonathan How

• 11:20-12:00 Panel discussion: Atanasov, Davison, Dellaert, Leonard

12:00 - 13:00 Lunch break & posters

13:00 - 14:00 Session 3: 

• 13:00-13:20 Andrew Davison

• 13:20-13:40 Jongwoo Lim 

• 13:40-14:00 Sebastian Scherer 

• 14:00-14:10 Spotlight talk 2: "Discrete-Continuous Smoothing and Mapping," Kevin Doherty et al.

14:10 -14:40 Coffee break & posters

14:40 - 16:00 Session 4: 

• 14:40-15:00 Guoquan (Paul) Huang

• 15:00-15:20 Maani Ghaffari

• 15:20-15:40 Camillo J. Taylor

• 15:40-15:50 Closing remarks

We cordially invite researchers to submit short papers, extended abstracts, posters, and/or videos. We accept original papers, as well as in-review or accepted manuscripts. Submitted contributions can describe work in progress, preliminary results, novel concepts, or industrial applications. 

All manuscripts are limited to 4+n pages (i.e., additional pages over 4 are ONLY allowed for references), should use the IEEE standard two-column conference format (paper template available on the IEEE ICRA 2022 website), and must be in the PDF format with size less than 20 MB. We encourage authors to submit a video for their manuscript as supplementary material. All video submissions must have the mp4 format with a size less than 100 MB. 

All original submissions will be peer-reviewed. Authors who submit a paper are expected to provide (up to) 3 single-blind reviews for the papers submitted to this workshop. Submissions will be selected by workshop organizers based on the reviews, their originality, relevance to the workshop topics, contributions, technical clarity, and presentation. All accepted manuscripts will be presented as posters during the workshop, which will be displayed throughout the day. Two top contributions will be selected for 10-minute oral presentations at spotlight sessions. Accepted posters and videos will be posted on the workshop website. You can contact the corresponding organizer with any questions: Mr. Kaveh Fathian, kavehf@mit.edu.

Topics of interest:

• Machine learning methods, algorithmic techniques, and their synergy for robotic perception and mapping

• Multi-agent, distributed, and/or asynchronous methods for mapping and structure from motion

• Perception-based robotic navigation and planning 

• Methods based on synergetic mathematical and learned models

• Certifiable and risk-aware perception, localization, and mapping

• Filter-based estimation, statistical techniques, and uncertainty-aware methods

• Factor graphs, pose graphs, rotation/translation averaging, and graph-based optimization techniques

• Point cloud, mesh-based, and occupancy maps

• Semantic segmentation, object detection, and pose estimation

• Perception algorithms for autonomous ground, air, and underwater vehicles, bipedal robots, and industrial applications

Submission platform:

To submit your contributions please follow:
​https://cmt3.research.microsoft.com/ROPM2022

You will need to create a new account if you have not used Microsoft CMT before. 

Important dates:

Submission Deadline: Sunday, April 24, 2022, 8:00 PM EDT

Reviews due:  Tuesday, May 03, 2022, 7:00 PM EDT

Acceptance Notification: Monday, May 9, 2022

Camera-ready submission: Sunday, May 15, 2022,  7:00 PM EDT

Workshop: Monday, May 23, 2022

Location: Room 119 AB, Pennsylvania Convention Center