The use of machine learning techniques to enable modeling of complex problems is of significant interest to the Department of Defense (DoD). One goal that could benefit from machine learning is predicting the structural response of buildings, and a key input to this analysis is a good understanding of the building structure and the structural detailing. Often the Department of Defense does not have access to blue-prints or even information on internal layout of a building but must nonetheless estimate the internal structure before doing an analysis of the structural response of the building due to various loads. The current approach used in developing a target structure for a structural response analysis is for a skilled person sit down and use specialized software to make representative models of buildings and other structures based on standard construction templates and structural design rules of thumb. This is a time-consuming process that the Department of Defense would like to be largely automated. The goal of this challenge is to predict the internal configuration of structures such as buildings by only using external satellite photographs of the building taken from various angles.
The goal of this challenge is to predict the internal configuration of structures such as buildings by only using external satellite photographs of the building taken from various angles. Using the shape, size, and external characteristics of the building (such as the number and spacing of windows), the desired methodology should be able to produce a model of the building to include basic structure system (frame vs. load-bearing systems), the construction materials and likely material properties, structural detailing, and any other feature responsible for the overall structural strength of the building. A machine learning model trained with a sufficient database of known buildings, along with constraints to represent current construction processes, could potentially yield a machine learning model that can use a minimal of external visual clues and then automatically produce a digital file of the most likely structural design of the building. The prediction of the number of configurations of non-load bearing partition walls would also be a benefit and should be regarded as an additional secondary challenge.
The Problem:
Develop the methodology used to solve this challenge as well as deliver the final verified and validated machine learning algorithm, along with an analysis of the validity and appropriateness of using machine learning as an approach to solving this problem. A critique of the Solver’s approach is highly desired so AFRL can plan later efforts based on the lessons learned of this challenge. AFRL would like to have access to the training data set, the full methodology (codes, input decks, scripts, etc.) to modify and reproduce this work, as well as the data files of the estimated structural design of the buildings used to test the final machine learning algorithms.
To receive an award, the Solvers will not have to transfer their exclusive IP rights to the Seeker. Instead, they will grant to the Seeker Government Purpose Rights to build their solutions. However, the intent of this competition is to help the solution provider team with a company that can mature the results of this challenge into a packaged software solution for later use or modification by the department of Defense.
Phase I: White Paper & Pitch Competition
In the first phase of this contest, participants will submit white papers describing their approaches to identify the images and structural characteristics of buildings that they will use, their basic approach to the algorithm development, the technical risks and mitigation strategies, and the expertise and capabilities of their proposed team. Any proprietary information and technology should be clearly defined by the submitter. These white papers will be down selected from the viable entrees (potential awardees), and the chosen proposers will then be given a 1-hour time slot to pitch their concept to the evaluation team.
During the pitch, the proposed solution should be scoped for a 12-24 month technical effort clearly stating the expected deliverables (e.g. code, scripts, images, models, etc.), and identify/define solution constraints to the clearest extent possible. Examples here may be an AI/ML generated CAD drawing of the expected interior layout indicating major load bearing structures/walls. The winner of this Pitch Competition will be awarded 40% of the prize to build a machine learning approach to solve this challenge along with identifying and obtaining the image data set for training. It should be noted that while a CAD drawing is acceptable for the white paper and pitch competition, the competition winner will be expected to output building structural designs in a government supplied XML format. This XML specification will be provided to the competition winner.
Phase II: Solution Development & Demonstration
The solution of this challenge shall use publicly available machine learning tools, such as TensorFlow, and publicly available tools and languages, such as Anaconda and Python. These tools are only given as examples and are not requirements. However, the desire is to use software tools and languages available to a wide variety of organizations both inside and outside the Department of Defense. The intent of AFRL is to use the results of this challenge as a building block for later effort and using open-source tools will enable work to be transitioned to later efforts.
The inputs to this challenge will be a dataset of external satellite photos of common buildings and other structures, and this dataset will be compiled as part of the challenge. The DoD interest is in photos of buildings taken with very high-resolution satellites, although the team may examine using other aerial photos and modify them to make them the same size and resolution as one might expect from very high-resolution satellites. The training and validation sets will have to be of buildings for which the team can obtain details about the structural design.
The output of this challenge is the methodology used to solve this challenge as well as the final verified and validated machine learning algorithm, along with an analysis of the validity and appropriateness of using machine learning as an approach to solving this problem. A critique of the Solver’s approach is highly desired so AFRL can plan later efforts based on the lessons learned of this challenge. AFRL would like to have access to the training data set, the full methodology (codes, input decks, scripts, etc.) to modify and reproduce this work, as well as the data files of the estimated structural design of the buildings used to test the final machine learning algorithms. The competition winner will be expected to output machine learning predicted building structural designs in a government supplied XML format. This XML specification will be provided to the competition winner.
The deliverable for this phase 2 effort will be the dataset and a written description of the AI/ML approach that will be used on this dataset for accomplishing the goal
Phase III: Solution Development & Demonstration
If this approach and dataset are deemed sufficient by AFRL, another 40% of the prize money would be released to demonstrate the success of the proposed approach by using the compiled image dataset and training the network, which will then be tested with images not used for training. The solver will then prepare a report describing the results of this test and the final ML/AI algorithm that was used
Phase IV: Final test and report
The government will submit new pictures of buildings unknown to the Solvers to see how well the final machine learning model predicts the structure of a known building. The final 20% of the prize money will be released to the solver to run their AI/ML algorithm against this final dataset and provide the results to the AFRL team.
Submissions will be evaluated on the concepts ability to meet the requirement delineated under “The Solution and Demonstration.” Phase II. To receive an award, the Solvers will not have to transfer their exclusive IP rights to the Seeker. Instead, they will grant to the Seeker Government Purpose Rights to build their solutions. However, the intent of this competition is to help the solution provider team with a company that can mature the results of this challenge into a packaged software solution for later use or modification by the department of Defense.
No prize will be awarded if a viable path to building the algorithm is not identified in Phase 1(white paper solicitation).
Project Deliverables:
1. Test dataset of high-resolution photographs of the buildings for the baseline test.
2. Report describing the proposed approach for the AI/ML learning and rationale for this approach.
3. Report of the results of the Phase III testing.
4. Final report on the results of the Phase IV testing.
Awards:- Up to $1,000,000 (awarded in 3 phases)
Deadline:- 15-10-2021
