Search for: All records

The construction industry has traditionally been a labor-intensive industry. Typically, labor cost takes a significant portion of the total project cost. In spite of the good pay, there was a big gap recently between demand and supply in construction trades position. A survey shows that more than 80% of construction companies in the Midwest of US are facing workforce shortage and suffering in finding enough skilled trades people to hire. This workforce shortage is also nationwide or even worldwide in many places. Construction automation provides a potential solution to mitigate this problem by seeking to replace some of the demanding, repetitive, and/or dangerous construction operations with robotic automation. Currently, robots have been used in bricklaying or heavy-lifting operations in the industry, and other uses remain to be explored. In this paper, the authors proposed a feasibility breakdown structure (FBS)-based robotic system method that can be used to test the feasibility of performing target construction operations with specific robotic systems, including a top-down work breakdown structure and a bottom-up set of feasibility analysis components based on literature search and/or simulation. The proposed method was demonstrated in testing the use of a KUKA robot and a Fetch robot to perform rebar mesh construction. Results showed that the overall workflow is feasible, whereas certain limitations presented in path planning. In addition, a smooth and timely information flow from the Fetch robot sensor and computer vision-based control to the two robots for a coordinated path planning and cooperation is critical for such constructability. 

Many Markov Chain Monte Carlo (MCMC) methods leverage gradient information of the potential function of target distribution to explore sample space efficiently. However, computing gradients can often be computationally expensive for large scale applications, such as those in contemporary machine learning. Stochastic Gradient (SG-)MCMC methods approximate gradients by stochastic ones, commonly via uniformly subsampled data points, and achieve improved computational efficiency, however at the price of introducing sampling error. We propose a non-uniform subsampling scheme to improve the sampling accuracy. The proposed exponentially weighted stochastic gradient (EWSG) is designed so that a non-uniform-SG-MCMC method mimics the statistical behavior of a batch-gradient-MCMC method, and hence the inaccuracy due to SG approximation is reduced. EWSG differs from classical variance reduction (VR) techniques as it focuses on the entire distribution instead of just the variance; nevertheless, its reduced local variance is also proved. EWSG can also be viewed as an extension of the importance sampling idea, successful for stochastic-gradient-based optimizations, to sampling tasks. In our practical implementation of EWSG, the non-uniform subsampling is performed efficiently via a Metropolis-Hastings chain on the data index, which is coupled to the MCMC algorithm. Numerical experiments are provided, not only to demonstrate EWSG's effectiveness, but also to guide hyperparameter choices, and validate our non-asymptotic global error bound despite of approximations in the implementation. Notably, while statistical accuracy is improved, convergence speed can be comparable to the uniform version, which renders EWSG a practical alternative to VR (but EWSG and VR can be combined too).

 

We propose a unified data-driven framework based on inverse optimal transport that can learn adaptive, nonlinear interaction cost function from noisy and incomplete empirical matching matrix and predict new matching in various matching contexts. We emphasize that the discrete optimal transport plays the role of a variational principle which gives rise to an optimization based framework for modeling the observed empirical matching data. Our formulation leads to a non-convex optimization problem which can be solved efficiently by an alternating optimization method. A key novel aspect of our formulation is the incorporation of marginal relaxation via regularized Wasserstein distance, significantly improving the robustness of the method in the face of noisy or missing empirical matching data. Our model falls into the category of prescriptive models, which not only predict potential future matching, but is also able to explain what leads to empirical matching and quantifies the impact of changes in matching factors. The proposed approach has wide applicability including predicting matching in online dating, labor market, college application and crowdsourcing. We back up our claims with numerical experiments on both synthetic data and real world data sets.