AI4Space 2024

ACCEPTED PAPERS

See you in Seattle!

Introduction

The space sector is experiencing significant growth. Currently planned activities and utilisation models also greatly exceed the scope, ambition and/or commercial value of space missions in the previous century, e.g., autonomous satellites for earth observation, on-orbit servicing, intelligent rovers for planetary exploration, and space traffic management and debris mitigation. Achieving these ambitious goals requires surmounting non-trivial technical obstacles. AI4Space focuses on the role of AI, particularly computer vision and machine learning, in helping to solve those technical hurdles. The workshop will highlight the space capabilities that draw from and/or overlap significantly with vision and learning research, outline the unique difficulties presented by space applications to vision and learning, and discuss recent advances towards overcoming those obstacles.

Call for Papers

We solicit papers for AI4Space. The general emphasis of AI4Space is vision and learning algorithms for autonomous space systems, which operate in the Earth’s orbital regions, cislunar orbit, planetary bodies (e.g., the moon, Mars and asteroids), and interplanetary space. Emphasis is also placed on novel sensors and processors for vision and learning in space, mitigating the challenges of the space environment towards vision and learning (e.g., radiation, extreme temperatures), and fundamental difficulties in vision and learning for space (e.g., lack of training data, unknown operating environments).

A specific list of topics is as follows:

• Vision and learning for spacecraft navigation and operations (e.g., rendezvous, proximity operations, docking, space maneuvers, entry descent landing).
• Vision and learning for space robots (e.g., rovers, UAVs, UGVs, UUWs) and multi-agent systems.
• Mapping and global positioning on planetary bodies (moon, Mars, asteroids), including celestial positioning.
• Onboard AI for Earth observation applications (e.g. near-real-time disaster monitoring, distributed learning on satellites, tip and cue satellite-based systems).
• Onboard AI for satellite operations (e.g. AI-based star trackers, fault detection isolation and recovery).
• Space debris monitoring and mitigation.
• Sensors for space applications (e.g., optical, multispectral, lidar, radar, neuromorphic).
• Onboard compute hardware for vision and learning (e.g., neural network accelerators, neuromorphic processors).
• Mitigating challenges of the space environment (e.g., radiation, thermal) to vision and learning systems.
• Datasets, transfer learning and domain gap.

Things to note:

• Papers will be fully peer reviewed and accepted papers will be published in the proceedings of CVPR 2024 Workshops.
• AI4Space follows the submission policies of CVPR 2024. An implication is that submissions to AI4Space should be sufficiently original works not under consideration/reviewing in other venues.
• Consistent with the submission policy, we highly encourage submission of papers relevant to AI4Space but are rejected from the main CVPR conference (decisions on Feb 27---before the AI4Space submission deadline on March 1).
• Accepted AI4Space papers are also expected to be presented in person at the workshop, which will be co-located with CVPR 2024.
• If you require a formal invitation letter to facilitate your travel to CVPR 2024 in Seattle, please visit the main conference page.
• All papers published via this workshop must be aimed towards the peaceful usage of AI for space.

Submission

Submissions must be in the CVPR format and are limited to 8 pages excluding references. Please refer to the main conference's submission guildelines for more details, and do not hesitate to contact the lead organiser Tat-Jun Chin if you have any questions.

Paper submission will be conducted through CMT3. See key dates for submission deadline and reviewing timeline.

Reviewing is double blind - remember to remove your names and affiliations in the submitted version (selecting the reviewing option in the LaTeX template will take care of that). Accepted works will be published in the CVPR 2024 workshop proceedings.

To the submission site.

SPARK2024

Important Dates

Workshop Program

Invited Speakers

Accepted Papers

Each paper will be presented as

• A spotlight presentation (strictly 4 minutes presentation, plus 1 minute buffer for changover; see schedule below); and
• A poster (poster session at 10:35 am).

Organisers

Sponsors