NOTHING STANDS STILL CHALLENGE 2024

Challenge Details

The Next Frontier in Productivity and Transparency

Together with the Gradient Spaces group, Stanford University, we are tackling the critical challenge of seamlessly integrating progress scans from various stages of construction toward accurate progress monitoring and prediction. The Nothing Stands Still challenge was hosted at the 3rd Workshop on Future of Construction during this year's International Conference on Robotics and Automation (ICRA).
The Nothing Stands Still 2024 Challenge targets the task of multiway spatiotemporal 3D point cloud registration of data collected over time at construction sites. For more details on the challenge and data, we refer to the challenge details.

We congratulate the winners from SPARK Lab @ MIT, and the first runner-up from the University of Hong Kong.

The cash award winners are

  • Hyungtae Lim+, Jingnan Shi+, Yun Chang+, Lukas Schmid+, Prof. Luca Carlone (SPARK Lab @ MIT): 4000 USD
  • Yinqiang Zhang, Liang Lu, Prof. Jia Pan (University of Hong Kong): 1000 USD
("+" denotes equal contribution)

Leaderboard

Rank Name Global RMSE (m) Pairwise RMSE (m) Recall Avg. RE Avg. TE
1st (*) SPARK LAB, MIT 0.056 0.065 83.33 0.23 0.01
2nd THE UNIVERSITY OF HONG KONG 2.414 0.281 70.01 0.23 0.02
3rd - 7.085 2.006 - - -
4th - 14.734 4.329 58.93 0.19 0.02
5th - 14.753 1.471 50.71 0.01 0.02
(*) The 1st winners utilized training and validation set data points as anchors to register the test set data points, hence the very low errors. The 2nd winners utilized, as per the scope of the challenge, only the test data points without any prior knowledge of the space.

COMMITTED TO OUR CULTURE

At Hilti, the people within our organization make a difference.

Our co-founder, Martin Hilti, considered it his first job and priority "to create a company climate in which every single individual can develop the will to succeed and a sense of commitment while still having fun at work." To this day, that has been a constant within Hilti.

We are always seeking talented engineers to help build the future, check out our current career opportunities.

GRADIENT SPACES GROUP

We perform research and educational activities that focus on developing quantitative and data-driven methods that learn from real-world visual data to generate, predict, and simulate new or renewed built environments over all lifecycle stages that place the human in the center.
Our mission is to create sustainable, inclusive, and adaptive built environments that can support our current and future physical and digital needs.

We are always looking for collaborations in academia and industry, so feel free to reach out. For more information on the group, visit here.

General Conditions for Participation

Everybody is welcome to participate in the challenge, however only students (undergrad, postgrad) are eligible for receiving the cash prizes.

License

All datasets and benchmarks on this page are copyright by us and published under the Creative Commons Attribution NonCommercial ShareAlike 3.0 License. This means that you must attribute the work in the manner specified by the authors, you may not use this work for commercial purposes and if you alter, transform, or build upon this work, you may distribute the resulting work only under the same license.