The increasing adoption of technologies, such as building information modeling underscores the significance of leveraging data and digital technologies on construction sites. Research and development of data-driven automated excavators are underway. Cooperative construction using multiple automated excavators is required to improve productivity. For realizing the construction method, utilizing operation and construction data collected in the construction sites is effective. This study presents cooperative motion planning based on a data-driven numerical optimization method. By leveraging a database of historical construction data, the search range for optimization calculations is limited, enabling the efficient calculation of motion plans for automated excavators that avoid collision with nearby machinery. The effectiveness of the proposed method was validated through simulations and experiments conducted with radio-controlled (RC) excavators.

This paper addresses a regulation problem of non-linear systems via database-driven nonlinear generalized predictive controller without model information. In industrial processes, lots of controlled systems with unknown time-delay and strong nonlinearity, are difficult to be handled in terms of control performance. Advanced controllers are considered to be established to deal with those nonlinear systems. In several design methods, advanced controllers are designed based on model information. However, it is time- and cost-consuming to identify the model of controlled systems, and requires regular maintenance to maintain acceptable performance. The database-driven approach has been attracted attentions to tackle those issues without model information. The controller can be designed and tuned only based on data, which is the main feature of this approach. Besides, the database-driven approach can deal with strong nonlinear systems. Additionally, the Generalized Predictive Control (GPC) is one of predictive controllers and widely applied in industrial processes. The GPC controller is developed based on multi-step prediction, therefore, it is effective to those systems subject to unknown or time-delay. As a result, a nonlinear GPC controller in the proposed scheme inherits the advantage of GPC, and is also tuned by the database-driven approach. The effectiveness and benefits of the proposed scheme are demonstrated through a numerical simulation and a comparative study.

The work object characteristics of a hydraulic excavator differ depending on the construction site, furthermore, they change during the work. Therefore, it is difficult to derive the desired control performance in the control system of a hydraulic excavator without considering the characteristics of the work object. This paper presents a database-driven model predictive control system that considers the characteristics of the work object. The characteristics of the excavator-environment interaction are modeled as a spring-mass-damper system with two degrees of freedom, and used in the proposed control system. The effectiveness of the proposed method is verified by a simulation using the model. The control performance is improved by applying the proposed method to the controlled object whose characteristics are subject to change.