Off-road autonomy entails R&D on a technology stack that enables autonomous and robotic systems to navigate through unstructured, off-road environments. Whereas on-road autonomy has to deal with the not-easy problems of figuring out how to share roads with road occupants such as cars, bicyclists, pedestrians, etc., while abiding by the traffic rules and following driving conventions.Â
Off-road autonomy, on the other hands, does not have to concern too much about interactions with road occupants, but no clear rules and boundaries of where and how to drive poses a different set of challenges under the paradox of choice. For example, off-road autonomy should enable its host system to know where it can drive on in a way not to damage the host system. No human driver would drive into a stream with unknown depth and current strength, even if it is a shortcut to the destination. To make things more complicated, the path it drove on yesterday might not be available today due to the changes of the environment or it may have to change the way it drove in the same area.Â
Â
Because of such intrinsic differences between these two domains, in contrast to what is often proposed and believed, it is not just a matter of transferring what we learned from on-road autonomy to the field of autonomous driving on off-road.Â
Thus the objective of this workshop aims at bringing together researchers and practitioners working on off-road autonomy, in order to discuss the challenges from automating off-road maneuvering, the issues of realizing off-road autonomy, share their latest results, discuss what matters most to accomplish the goals of off-road autonomy, and to network with people in the field.Â
This workshop solicits high-quality technical papers. The topics of interest include but not limited to the following:
Sensor fusion for estimating traversability
Data set on and for off-road driving
Exploratory maneuvers
Calibration methods for easier and quicker transfer of autonomy stack
Transfer learning for applying urban and/or on-road AD stack to off-road
Economic learning approach for off-road maneuvers, e.g., online learning, self-supervised learning, etc.
Knowledge representation: Terrain, moving and static objects, weather
Long-term localization and mapping in off-road environments
Addressing the characteristics of off-road terrains, e.g., estimating lateral slips and mitigating them
Autonomous navigation for GPS-denied and rough terrainsÂ
State estimation / SLAM for off-road environments
Paper submission due: Feb. 5, 2024 (no further extension)
Paper acceptance notification: Mar. 30, 2024
Camera ready due:Â Apr. 22, 2024
Workshop date: Jun. 2, 2024
Please refer to this page: submission guideline
Sebastian Scherer, Prof., Carnegie Mellon Univ., "A data-driven and self-supervised approach for offroad autonomy"
Dinesh Manocha, Prof., Univ. of Maryland at College Park, "Robot navigation in complex indoor and outdoor scenes"
Joel Pazhayapalli, CEO, Bluespace, "Field-testing Results on a Motion-based Odometry and Perception Stacks"
Fu Zhang, Prof., Univ. of Hong Kong, "A single-actuated UAV with efficient flight and autonomous navigation"
Michael Milford, Prof., Queensland Univ. Technology (QUT), "Introspection, Localization and Terrain Detection for Off-Road Autonomous Vehicles in Mine Sites and All Terrain Environments"
Youngwoo Seo, PhD
Executive Vice President
Hanwha Aerospace, Land Systems Business Group
6, Pangyo-ro 319beon-gil, Bundang-gu, Seongnam-si, Gyeonggi-dom 13488, Korea
Hyun Myung, PhD
Professor, School of Electrical Engineering
KAIST (Korea Advanced Institute of Science and Technology)
291 Daehak-ro Yuseong-gu Daejeon 34141, Republic of Korea
Sebastian Scherer, PhD
Associate Research Professor
Carnegie Mellon University
5000 Forbes Ave, Pittsburgh PA 15213
Chong Hui Kim, PhD
Chief, AI & Autonomy Technology Center
Advanced Defense Science & Technology Research Institute
Agency for Defense Development
Yuseong P.O.Box 35, Daejeon 34186, Republic of Korea