The $10 trillion global construction industry has traditionally been a labor-intensive industry, yet it stands to benefit from autonomous robots that promise to deliver construction work that is more accurate and efficient compared to manual or conventional methods. However, the integration of automation and robotic technology into the construction workplace is faced with significant barriers including high cost of entry, safety concerns, inadequate training and knowledge about robotics, and poor performance of robots in dynamic, cluttered and unpredictable environments such as construction sites.
To tackle these challenging issues, this workshop aims to facilitate discussion on technology that will enable advanced robotics for future construction workplaces with an emphasis on robust perception and navigation methods, learning-based task and motion planning, and safety-focused robot-worker interactions. In line with the ICRA's theme, this workshop will provide a venue for academics and industry practitioners to create a vision for robotics in construction work and ensure equitable participation in planning for the future of construction workplaces. The full-day workshop will feature presentations by distinguished speakers from both industry and academia as well as interactive activities in the form of a SLAM challenge, poster sessions, debate, and panel discussions
The workshop will be held as a hybrid event, and the session will be live-streamed to an online audience. All participants (in-person or online) must register for the workshop and tutorial through the ICRA registration page.
This workshop will solicit contributions in two tracks: (i) the Paper Track and (ii) the Poster-only Track.
Paper Track: This track consists of contributed papers that constitute novel, original research in construction robotics or closely related fields. Contributed papers cannot take the form of an existing paper that is published or under review. Contributed papers should be in the form of extended abstracts (about 3-4 pages in ICRA paper format, including references). Authors are encouraged to also submit an optional 2-3 minute video presentation of their paper if their work involves visualization, robot operation etc. The accepted contributed papers will be made publicly available on the workshop website. In addition, authors of accepted papers will be invited to publish their papers with The International Association for Automation and Robotics in Construction (IAARC), though this is optional for authors who wish to publish at other venues. In this case, these papers will receive DOI numbers and be made permanently available through the IAARC website.
Poster-only Track: This track consists of posters that can be either based on a prior publication or novel work. Authors with an original paper may submit it to both tracks (paper and poster). Accepted posters will be presented during the poster session on the day of the workshop in the hallway outside the conference room. Authors are expected to print out and bring their own posters to the workshop, though poster boards will be provided. Poster boards are A0 format (841 mm x 1189 mm) in portrait orientation. There is no specific template for the posters. You should choose the format that best represents your research work.
Submissions can be made through this Google Form, where the paper or poster can be uploaded in PDF format. Deadlines given below are in Anywhere on Earth Time. Questions regarding the paper submission should be directed to chenjingdao@cse.msstate.edu.
If you require an early decision notification due to having to apply for a visa, please contact chenjingdao@cse.msstate.edu
The topics of interest include, but are not limited to, the following:
Submitted papers (Paper Track only) will be considered for the best research awards based on technical merit, originality, and potential impact on the field. Winners will be announced along with the NSS Challenge winners during the day of the workshop. Best research award winners will also be invited to give a 10-minute presentation on their paper during the workshop.
Nothing Stands Still 2025 Challenge: HILTI and the Gradient Spaces group from Stanford University are announcing the new Nothing Stands Still 2025 Challenge to tackle the critical task of seamlessly integrating progress scans from various stages of construction. Specifically, the challenge targets the task of multiway spatiotemporal 3D point cloud registration of data collected over time at construction sites. The goal of the challenge is to achieve a global spatiotemporal map of 3D point clouds collected at any time and location at the same construction scenes, as the latter evolve. The challenge website may be accessed here.
Marvin Cheng is a research engineer in the Center for Occupational Robotics Research at NIOSH. He is currently the Assistant Coordinator of the Center for the Occupational Robotics Research (CORR), and the Team Lead of the Safety Control Team at the National Institute for Occupational Safety and Health. His research interests include operation safety of robots in workspaces, human-robot interaction, control system, and cyberphysical systems used for human-robot collaboration.
Ayoung Kim works as an associate professor in the department of mechanical engineering at Seoul National University since 2021 Sep. Before joining SNU, she was at the civil and environmental engineering, Korea Advanced Institute of Science and Technology (KAIST) from 2014 to 2021. She has B.S. and M.S. degrees in mechanical engineering from SNU in 2005 and 2007, and an M.S. degree in electrical engineering and a Ph.D. degree in mechanical engineering from the University of Michigan (UM), Ann Arbor, in 2011 and 2012. She also worked as a post-doctoral researcher in naval architecture and marine engineering, at U of M in 2013 before she worked at Electronics and Telecommunications Research Institute (ETRI) as a senior researcher.
Enhancing LiDAR SLAM for Construction Sites: Ensuring Robustness and Versatility LiDAR has been one of the most widely used sensors in construction sites. In this talk, I will explore three key aspects of LiDAR SLAM. First, with the increasing availability of LiDAR sensors from various manufacturers, we face the challenge of matching data across heterogeneous LiDAR systems deployed in the same environment. While most LiDAR-based place recognition methods focus on recognizing scenes captured by the same type of sensor, we introduce a dataset designed to address the SLAM problem using heterogeneous LiDAR sensors. Secondly, I will discuss how incorporating additional sensor modalities, such as radar, can significantly enhance LiDAR-inertial odometry performance. By leveraging the complementary nature of radar and LiDAR, radar can effectively remove dynamic objects and improve orientation estimation through gravity estimation. Lastly, once maps are constructed from LiDAR data, it's essential to identify meaningful changes over time. We present our new change detection algorithm, ELite, which handles changes as a continuous measure of ephemerality, rather than treating them as binary changes.
Dr. Siyu Tang leads the Computer Vision and Learning Group (VLG) at ETH Zurich and studies computational models that enable machines to perceive and analyze human motion and activities from visual input. Her work in scalable and reliable human digitalization is highly relevant for construction robots that work alongside humans.
Val Tzvetkov is the Director of VDC and Emerging Technology, overseeing the construction and emerging technology department for Skanska Metro New York's $800M -$1.2B yearly construction project portfolio.
Adrian Ferrier is the Engineering Director for Civil Construction Field Systems at Trimble, one of the largest software companies building navigation and positioning systems for building & construction, agriculture, geospatial, and transportation sectors. His current research focus is automation on earthworks construction sites. His talk would cover recent experiences within Trimble on Autonomous Compacting and Trenching (Excavation), comparing construction vehicle automation with autonomy in agriculture, including deterministic vs nondeterministic path planning, and how machine work groups are tightly or loosely coupled.
This workshop is made possible thanks to the generous sponsorship of the following organizations:
Links to previous iterations of this workshop at past conferences:
