Approaches to directional drilling

1 . A method comprising:

receiving a well plan and determining a plurality of sections of the well plan;

receiving data from surface and downhole to determine a current location of a drill bit, the drill bit located on a bottom hole assembly of a drill string;

analyzing the well plan to automatically derive a plurality of trajectory constraints that are associated with each of the plurality of sections of the well plan;

identifying, based on a prior section of the plurality of sections and a future section of the plurality of sections, a current context at the current location of the drill bit, wherein the current context includes a current activity status of the bottom hole assembly;

determining a plurality of trajectory candidates that pertain to respective paths from the current location of the drill bit to respective targets included within each of the plurality of sections of the well plan based on a consideration of the plurality trajectory constraints;

identifying a plurality of trajectory contexts, each trajectory context of the plurality of trajectory contexts associated with at least one trajectory candidate of the plurality of trajectory candidates, wherein the plurality of trajectory contexts includes a plurality of trajectory activity statuses associated with drilling the associated trajectory candidate of the plurality of trajectory candidates;

generating a plurality of ranking properties for ranking of the plurality of trajectory candidates;

applying a machine learning model to historical data, the plurality of ranking properties and the plurality of trajectory candidates, the machine learning model outputting an additional ranking property;

adding the additional ranking property to the plurality of ranking properties;

assigning, for the plurality of trajectory candidates, a plurality of weights based on the plurality of trajectory contexts, wherein, based on the plurality of trajectory contexts associated with the plurality of trajectory candidates, a first weight of the plurality of weights for a first trajectory candidate of the plurality of trajectory candidates is different than a second weight of the plurality of weights for a second trajectory candidate of the plurality of trajectory candidates, wherein assigning the plurality of weights results in a plurality of weighted ranking properties;

generating a total cost for each trajectory candidate of the plurality of trajectory candidates, each trajectory candidate of the plurality of trajectory candidates associated with a cost function of a plurality of cost functions, each cost function of the plurality of cost functions including at least one weighted ranking property of the plurality of weighted ranking properties;

using the total cost, generating a plurality of rankings, each ranking of the plurality of rankings associated with one of the plurality of trajectory candidates, wherein the plurality of rankings rank the plurality of trajectory candidates with respect to at least one other trajectory candidate of the plurality of trajectory candidates;

using the plurality of rankings for each of the plurality of trajectory candidates, determining a working plan that includes an optimal path from the current location of the drill bit to reach a final target, wherein the working plan includes hardware specific drill command sequences to direct the drill bit along the optimal path;

communicating the hardware specific drill command sequences to control the bottom hole assembly of the drill string to access the final target from the current location; and

executing the hardware specific drill command sequences to steer the drill bit to the final target.

2 . The method of claim 1 , wherein the well plan includes information about at least one of a shape, an orientation, a depth, a completion, an evaluation, equipment to be used in a well construction process, or actions to be taken at different points in the well construction process.

3 . The method of claim 1 , wherein the plurality of sections of the well plan are determined by evaluating the plurality of trajectory candidates based on respective trajectory contexts that are associated with respective curves and orientations of a motor steering system or a rotary steerable system at different points in a well construction process.

4 . The method of claim 3 , further includes adjusting the plurality of weights based on the plurality of trajectory contexts that are associated with the plurality of cost functions, wherein the plurality of cost functions associated with the plurality of weights are utilized to produce the total cost for each of the plurality of trajectory candidates.

5 . The method of claim 1 , wherein the plurality of cost functions comprise at least one energy cost function for assessing energy utilization based at least in part on drill command schedules that are generated for the plurality of trajectory candidates and at least one emissions cost function for assessing emissions generation based at least in part on the drill command schedules.

6 . The method of claim 1 , further includes receiving data from the bottom hole assembly and estimating a downhole state using at least a portion of the data from the bottom hole assembly.

7 . The method of claim 1 , wherein the plurality of trajectory constraints include at least one of angular constraints, spatial constraints, a maximum dogleg constraint, an allowable tortuosity constraint, a risk measure constraint, a hole quality constraint, a confidence level constraint, or a sustainability impact constraint.

8 . The method of claim 1 , wherein the plurality of trajectory constraints include at least one of a vertical depth constraint, a distance constraint, a direction constraint, an inclination constraint, an azimuth angle constraint, a dogleg severity constraint, or a cylindrical constraint.

9 . The method of claim 1 , wherein the working plan is determined based on a ranking system that uses candidate properties that include at least one of a trajectory length, a total steering length, an average steering ratio, a maximum steering ratio, an average deviation from the well plan, a maximum deviation from the well plan, snaking, a risk level, target constraints, an angular deviation, a total time, a bit type, a tortuosity, tool wear, or geomechanics.

10 . The method of claim 1 , wherein the additional ranking property includes a drilling difficulty index based on surface automation constraints.

11 . The method of claim 10 , wherein applying the machine learning model includes applying the machine learning model to surface automation data at different levels of automation to output the drilling difficulty index.

12 . A system comprising:

a processor;

memory accessible by the processor;

processor-executable instructions stored in the memory and executable to instruct the system to:

receive a well plan and determining a plurality of sections of the well plan;

receive data from surface and downhole to determine a current location of a drill bit, the drill bit located on a bottom hole assembly of a drill string;

analyze the well plan to automatically derive a plurality of trajectory constraints that are associated with each of the plurality of sections of the well plan;

identify, based on a prior section of the plurality of sections and a future section of the plurality of sections, a current context at the current location of the drill bit, wherein the current context includes a current activity status of the bottom hole assembly;

determine a plurality of trajectory candidates that pertain to respective paths from the current location of the drill bit to respective targets included within each of the plurality of sections of the well plan based on a consideration of the plurality of trajectory constraints;

identify a plurality of trajectory contexts, each trajectory context of the plurality of trajectory contexts associated with at least one trajectory candidate of the plurality of trajectory candidates, wherein the plurality of trajectory contexts includes a plurality of candidate activity statuses associated with drilling the associated trajectory candidate of the plurality of trajectory candidates;

generate a plurality of ranking properties for ranking of the plurality of trajectory candidates;

apply a machine learning model to historical data, the plurality of ranking properties and the plurality of trajectory candidates, the machine learning model outputting an additional ranking property;

add the additional ranking property to the plurality of ranking properties;

assign, for the plurality of trajectory candidates, a plurality of weights based on the plurality of trajectory contexts, wherein, based on the plurality of trajectory contexts associated with the plurality of trajectory candidates, a first weight of the plurality of weights for a first trajectory candidate of the plurality of trajectory candidates is different than a second weight of the plurality of weights for a second trajectory candidate of the plurality of trajectory candidates, wherein assigning the plurality of weights results in a plurality of weighted ranking properties;

generate a total cost for each trajectory candidate of the plurality of trajectory candidates, each trajectory candidate of the plurality of trajectory candidates associated with a cost function of a plurality of cost functions, each cost function of the plurality of cost functions including at least one weighted ranking property of the plurality of weighted ranking properties;

using the total cost, generate a plurality of rankings, each ranking of the plurality of rankings associated with one of the plurality of trajectory candidates, wherein the plurality of rankings rank the plurality of trajectory candidates with respect to at least one other trajectory candidate of the plurality of trajectory candidates;

using the plurality of rankings for each of the plurality of trajectory candidates, determine a working plan that includes an optimal path from the current location of the drill bit to reach a final target, wherein the working plan includes hardware specific drill command sequences to direct the drill bit along the optimal path;

communicate the hardware specific drill command sequences to control the bottom hole assembly of the drill string to access the final target from the current location; and

execute the hardware specific drill command sequences to steer the drill bit to the final target.

13 . The system of claim 12 , wherein the well plan includes information about at least one of a shape, an orientation, a depth, a completion, an evaluation, equipment to be used in a well construction process, or actions to be taken at different points in the well construction process.

14 . The system of claim 12 , wherein the plurality of sections of the well plan are determined by evaluating the plurality of trajectory candidates based on respective trajectory contexts that are associated with respective curves and orientations of a motor steering system or a rotary steerable system at different points in a well construction process.

15 . The system of claim 14 , further includes adjusting the plurality of weights based on the plurality of trajectory contexts that are associated with the plurality of cost functions, wherein the plurality of cost functions associated with the plurality of weights are utilized to produce the total cost for each of the plurality of trajectory candidates.

16 . The system of claim 12 , wherein the plurality of cost functions comprise at least one energy cost function for assessing energy utilization based at least in part on drill command schedules that are generated for the plurality of trajectory candidates and at least one emissions cost function for assessing emissions generation based at least in part on the drill command schedules.

17 . The system of claim 12 , further includes receiving data from the bottom hole assembly and estimating a downhole state using at least a portion of the data from the bottom hole assembly.

18 . The system of claim 12 , wherein the plurality of trajectory constraints include at least one of angular constraints, spatial constraints, a maximum dogleg constraint, an allowable tortuosity constraint, a risk measure constraint, a hole quality constraint, a confidence level constraint, or a sustainability impact constraint.

19 . A non-transitory computer-readable storage medium storing instructions that when executed by a computer, which includes a processor performs a method, the method comprising:

receiving a well plan and determining a plurality of sections of the well plan;

receiving data from surface and downhole to determine a current location of a drill bit, the drill bit located on a bottom hole assembly of a drill string;

analyzing the well plan to automatically derive a plurality of trajectory constraints that are associated with each of the plurality of sections of the well plan;

identifying, based on a prior section of the plurality of sections and a future section of the plurality of sections, a current context at the current location of the drill bit, wherein the current context includes a current activity status of the bottom hole assembly;

determining a plurality of trajectory candidates that pertain to respective paths from the current location of the drill bit to respective targets included within each of the plurality of sections of the well plan based on a consideration of the plurality trajectory constraints;

identifying a plurality of trajectory contexts, each trajectory context of the plurality of trajectory contexts associated with at least one trajectory candidate of the plurality of trajectory candidates, wherein the plurality of trajectory contexts includes a plurality of candidate activity statuses associated with drilling the associated trajectory candidate of the plurality of trajectory candidates;

generating a plurality of ranking properties for ranking of the plurality of trajectory candidates;

applying a machine learning model to historical data, the plurality of ranking properties and the plurality of trajectory candidates, the machine learning model outputting an additional ranking property;

adding the additional ranking property to the plurality of ranking properties;

assigning, for the plurality of trajectory candidates, a plurality of weights based on the plurality of trajectory contexts, wherein, based on the plurality of trajectory contexts associated with the plurality of trajectory candidates, a first weight of the plurality of weights for a first trajectory candidate of the plurality of trajectory candidates is different than a second weight of the plurality of weights for a second trajectory candidate of the plurality of trajectory candidates, wherein assigning the plurality of weights results in a plurality of weighted ranking properties;

generating a total cost for each trajectory candidate of the plurality of trajectory candidates, each trajectory candidate of the plurality of trajectory candidates associated with a cost function of a plurality of cost functions, each cost function of the plurality of cost functions including at least one weighted ranking property of the plurality of weighted ranking properties;

using the total cost, generating a plurality of rankings, each ranking of the plurality of rankings associated with one of the plurality of trajectory candidates, wherein the plurality of rankings rank the plurality of trajectory candidates with respect to at least one other trajectory candidate of the plurality of trajectory candidates;

using the plurality of rankings for each of the plurality of trajectory candidates, determining a working plan that includes an optimal path from the current location of the drill bit to reach a final target, wherein the working plan includes hardware specific drill command sequences to direct the drill bit along the optimal path;

communicating the hardware specific drill command sequences to control the bottom hole assembly of the drill string to access the final target from the current location; and

executing the hardware specific drill command sequences to steer the drill bit to the final target.

20 . The non-transitory computer-readable storage medium of claim 19 , wherein the working plan is determined based on a ranking system that uses candidate properties that include at least one of a trajectory length, a total steering length, an average steering ratio, a maximum steering ratio, an average deviation from the well plan, a maximum deviation from the well plan, snaking, a risk level, target constraints, an angular deviation, a total time, a bit type, a tortuosity, tool wear, or geomechanics.