Please fill our feedback form.

About the Workshop

In recent years, many of the technical and scientific advancements in machine learning and computer vision systems led to major innovations in the field of scene understanding. However, due to the limited generalization capabilities of these approaches and the lack of standards, only a small fraction of these promising ideas has been widely adopted by the robotic research community. Instead, the spatial representation research field continues to be largely influenced by algorithms and methods established prior to the deep learning revolution. In this workshop, our objective is twofold. Firstly, we seek to explore the opportunities presented to the field of spatial and semantic representations for robotics by recent innovations within the machine learning community. We will focus the discussion on learning-based models, including large-language and foundation models and their exceptional capabilities in comprehending and processing semantic knowledge, allowing open-vocabulary navigation and promising increased generalization. Simultaneously, we aim to identify the barriers hindering the widespread adoption of these technologies within our community. Our goal is to establish the groundwork for a machine learning toolkit for semantic spatial representation, specifically designed for the needs of the autonomous mobile robotics community.

Call for Papers

During this workshop, we will also hold a poster session to present recent developments. We invite you to submit your novel contribution aligned with the following indicative (and non-exhaustive) list of topics.

  • Implicit environment representations based on neural networks and other machine learning models.
  • Opportunities and limitations of foundation models for visual-language maps, visual-language navigation, and, in general, spatial and semantic representation.
  • Integration of new spatial and semantic reasoning methods into pre-existing robotic algorithms, such as probabilistic robots.
  • Technical integration of new methods into existing robotic frameworks (e.g. ROS).
  • Evaluation and benchmarking of newly proposed methods for autonomous mobile robots.
  • Long-term evolving representations of dynamic environments, to model changing aspects or moving agents (both robots and humans).
  • Zero-shot transfer, parameter-efficient fine-tuning, and re-use of pre-trained neural network components.
  • Deployment of computationally-intensive foundation models and transformer-based architecture on computationally- and communication-restrained platforms as mobile robots.

Guide for authors

Please submit an extended abstract of up to 4 pages, including references, to the workshop chair at robotmappingws@gmail.com. For the paper template, please use the standard IEEE conference template. Submissions that are re-elaborations of recently published papers are welcome. The workshop will not have archival proceedings. All the submitted papers will undergo review by the organising committee and will be accepted based on their quality, merit and timeliness.

Important dates – extended submission

  • Deadline for submission: 31 August 2024 22 September 2024.
  • Notification of acceptance: 15 September 2024 30 September 2024.
  • Deadline for final paper submission: 30 September 2024 10 October 2024.

Publication and dissemination

The accepted papers will be presented during a poster session accompanying the workshop during IEEE/RSJ IROS 2024 in Abu-Dhabi. After the workshop, the papers with accompanying posters will be available on the workshop's web page.

Participation

The key part of the conference will be held in person at the conference venue. However, for improved participation and dissemination the key talks will be streamed via zoom and they will be later available on the YouTube channel of the organisers.

Accepted papers

Invited speakers

To ensure diversity of points of view, backgrounds, and experience, we selected invited speakers representative of the breadth of research coming from different regions, giving particular attention to diversity. Moreover, we selected both academic speakers as well as speakers coming from different industries, from robotic hardware to AI. Our invited speakers, all confirmed, are:

Program

Time⨯
Speaker Topic
8:30 - 8:45 Organizers Welcome and Introduction
8:45 - 9:10 Javier Civera Visual Place Recognition: Foundational Models and Data Considerations
9:10 - 9:35 Ayoung Kim Radar in Robotics for Robust Localization and Mapping in Extreme Environments
9:35 - 10:00 Chris Paxton Towards Home Robots: Open Vocabulary Mobile Manipulation in Unstructured Environments
10:00 - 10:30 Coffee Break with Poster Session
10:30 - 10:55 Luca Carlone Representing Environments Through Scene-graphs and Their Application to Downstream Robotic Tasks
10:55 - 11:55 World Cafe Discussion Discussion with Roundtables
11:55 - 12:00 Organizers Closing Remarks
⨯Abu Dhabi Local Time