Sufficiently Accurate Model Learning for Planning
This work addresses the challenge of improving model accuracy for planners and controllers in robotics or control systems, but it appears incremental as it builds on existing constrained learning approaches with theoretical analysis.
The paper tackles the problem of learning dynamical system models for planning by incorporating task-specific constraints into the model learning process, resulting in models that focus expressive power on important aspects and are better suited for certain tasks, with solution quality depending on parameterization, smoothness, and sample count.
Data driven models of dynamical systems help planners and controllers to provide more precise and accurate motions. Most model learning algorithms will try to minimize a loss function between the observed data and the model's predictions. This can be improved using prior knowledge about the task at hand, which can be encoded in the form of constraints. This turns the unconstrained model learning problem into a constrained one. These constraints allow models with finite capacity to focus their expressive power on important aspects of the system. This can lead to models that are better suited for certain tasks. This paper introduces the constrained Sufficiently Accurate model learning approach, provides examples of such problems, and presents a theorem on how close some approximate solutions can be. The approximate solution quality will depend on the function parameterization, loss and constraint function smoothness, and the number of samples in model learning.