The drilling process is complex because unexpected situations may occur at any time. Furthermore, the drilling system is extremely long and slender, therefore prone to vibrations and often being dominated by long transient periods. Adding the fact that measurements are not well distributed along the drilling system, with the majority of real-time measurements only available at the top side and having only access to very sparse data from downhole, the drilling process is poorly observed therefore making it difficult to use standard control methods. Therefore, to achieve completely autonomous drilling operations, it is necessary to utilize a method that is capable of estimating the internal state of the drilling system from parsimonious information while being able to make decisions that will keep the operation safe but effective. A solution enabling autonomous decision-making while drilling has been developed. It relies on an optimization of the time to reach the section total depth (TD). The estimated time to reach the section TD is decomposed into the effective time spent in conducting the drilling operation and the likely time lost to solve unexpected drilling events. This optimization problem is solved by using a Markov decision process method. Several example scenarios have been run in a virtual rig environment to test the validity of the concept. It is found that the system is capable to adapt itself to various drilling conditions, as for example being aggressive when the operation runs smoothly and the estimated uncertainty of the internal states is low, but also more cautious when the downhole drilling conditions deteriorate or when observations tend to indicate more erratic behavior, which is often observed prior to a drilling event.

The ability to predict the response of a drill bit to the top-side axial and rotational velocities of the drill-string is a prerequisite for any system aimed at automatically controlling the drilling parameters to optimize the rate of penetration and the overall quality of the well construction process. When drilling with a Polycrystalline Diamond Compact (PDC) bit, even the

AI alignment is generally associated with ethics and social aspects. For high-risk AI systems, principles such as safety, stability and performance are crucial for their adoption in real-world application, to build trust and increase efficiency of a process. By safety it is meant both safety of the system itself but also safety of the process and environment. Any decision taken by a high-risk AI system should preserve safety, ensure continuous operation, real-time functioning, smooth control, and improve process efficiency. Human oversight needs to be continuously ensured, both to preserve safety of the process in case of transition from autonomous to manual mode in case of failures, but also to allow for contextual knowledge of the decisions. All these objectives are included in the AI operational alignment. High-risk AI systems designed to automatize complex processes in critical environments are continuously adapting to dynamic contexts, thus a static alignment might not be sufficient to properly assess their behaviour. The paper describes an approach to automated dynamic operational alignment in a complex high-risk process, exemplified by a case study on autonomous drilling. Possible sources of AI misalignments in this case are discussed and their potential implications.