Predicting the consequence of action in digital control state spaces
This work tackles the problem of enabling artificial devices to learn motor tasks more effectively, potentially benefiting robotics and AI control systems, but it appears incremental as it builds on existing neuroscience insights.
The dissertation addresses fundamental impediments in learning control laws in continuous state spaces by proposing an 'end effector control' principle inspired by neuroscience, as an alternative to classical 'displacement control'.
The objective of this dissertation is to shed light on some fundamental impediments in learning control laws in continuous state spaces. In particular, if one wants to build artificial devices capable to learn motor tasks the same way they learn to classify signals and images, one needs to establish control rules that do not necessitate comparisons between quantities of the surrounding space. We propose, in that context, to take inspiration from the "end effector control" principle, as suggested by neuroscience studies, as opposed to the "displacement control" principle used in the classical control theory.