A systematic evaluation of the evidence for perceptual control theory in tracking studies

Perceptual control theory (PCT) proposes that perceptual inputs are controlled to intentional 'reference' states by hierarchical negative feedback control, evidence for which comes from manual tracking experiments in humans. We reviewed these experiments to determine whether tracking is a process of perceptual control, and to assess the state-of-the-evidence for PCT. A systematic literature search was conducted of peer-review journal and book chapters in which tracking data were simulated with a PCT model (13 studies, 53 participants). We report a narrative review of these studies and a qualitative assessment of their methodological quality. We found evidence that individuals track to individual-specific endogenously-specified reference states and act against disturbances, and evidence that hierarchical PCT can simulate complex tracking. PCT's learning algorithm, reorganization, was not modelled. Limitations exist in the range of tracking conditions under which the PCT model has been tested. Future PCT research should apply the PCT methodology to identify control variables in real-world tasks and develop hierarchical PCT architectures for goal-oriented robotics to test the plausibility of PCT model-based action control.

Compositional Learning of Human Activities With a Self-Organizing Neural Architecture

An important step for assistive systems and robot companions operating in human environments is to learn the compositionality of human activities, i.e., recognize both activities and their comprising actions. Most existing approaches address action and activity recognition as separate tasks, i.e., actions need to be inferred before the activity labels, and are thus highly sensitive to the correct temporal segmentation of the activity sequences. In this paper, we present a novel learning approach that jointly learns human activities on two levels of semantic and temporal complexity: (1) transitive actions such as reaching and opening, e.g., a cereal box, and (2) high-level activities such as having breakfast. Our model consists of a hierarchy of GWR networks which process and learn inherent spatiotemporal dependencies of multiple visual cues extracted from the human body skeletal representation and the interaction with objects. The neural architecture learns and semantically segments input RGB-D sequences of high-level activities into their composing actions, without supervision. We investigate the performance of our architecture with a set of experiments on a publicly available benchmark dataset. The experimental results show that our approach outperforms the state of the art with respect to the classification of the high-level activities. Additionally, we introduce a novel top-down modulation mechanism to the architecture which uses the actions and activity labels as constraints during the learning phase. In our experiments, we show how this mechanism can be used to control the network's neural growth without decreasing the overall performance.