FIG. 4 depicts an illustrative example of an overview of an adaptive learning system 400 that may be used in accordance with at least some embodiments. In particular, FIG. 4 depicts an adaptive learning system 400 type machine learning model. The adaptive learning system 400 may be an example of the adaptive rule-based system 312 of FIG. 3 described above.

As illustrated, the adaptive learning system 400 includes a series of layers, each representing a set of nodes. On one side of the series of layers exists an input layer 402. The input layer 402 includes a set of nodes that are referred to herein as input nodes. Each of these input nodes may be mapped to a particular feature of an object model or an object model itself. In some embodiments, each “feature” may actually comprise a combination of other features. For example, a feature may comprise a number of data points, a label associated with those data points (e.g., a region label), a position of the data points with respect to the rest of the object model, or any other suitable feature. For example, the input layer 402 may include input nodes associated with the inputs described above. There may be separate input nodes for driver state 304, trip status 306, traffic information 308, and user device information 310 described in FIG. 3. There may be further input nodes not listed above, including driver identity, vehicle status, and other information gathered by sensors of the vehicle or stored on a database of the vehicle computing system.