The kind of dealing which is closest to us is […] not a bare perceptual cognition, but rather that kind of concern which manipulates things and puts them to use
M. Heidegger, Being and Time, 1927
The goal of this project is to build artificial architectures for cognitive systems embodied in hands that exploit the most advanced understanding of how the human hand system is organized, with the long‐term objective to achieve comparable performance. It should be noticed however, that the project philosophy is quite distinct from some of the approaches followed in recent years, summarized in the “intelligence without reason” motto. We believe instead that, because intelligent behaviors are intrinsic to the physics of the embodiment, lessons learned and inspiration taken from the human example need to be translated into an abstract enough language to be understood and applied in different, artificial bodies – and this language can only be that of mathematics and geometry.
We believe that our studies on human motor and sensor synergies, integrating studies from the cortical/cerebellar microcircuitry level down to the psychophysics of haptics and manipulation, together with our development of a new geometrical model of synergy‐based kinematics, dynamics, and multisensory integration will eventually lead to a much needed solution to the decades‐long problem of trading off simplicity and performance in the design of robot hands, much in the spirit of minimalist robotics. Our long term goal is to be able to replicate in the artificial an organized set of synergies, ordered by increasing complexity, so that a correspondence can be made between any specified task set (in terms of a number of different grasps, explorative actions and manipulations) and the least number of synergies whose aggregation make the task set feasible.
In summary, the crucial contributions in the project we propose are:
- the study of the organization of haptic action in motor synergies for the human hand, from both a neuroscientific and psychophysical viewpoint, ranging from organization of brain cortical areas in higher‐level haptic cue processing , to the characterization the microcircuitry of the cerebellar armhand control system;
- the study of the organization of haptic perception in multi‐cue and multi‐modal synergies for integration of percepts in the human cognitive system for active touch;
- the extraction of the conceptual organization and the geometric structures of links between the hand embodiment and the learning and adaptation capabilities of manipulation and haptic perception in humans, and its exploitation to design simpler and more performing system architectures for the “hand” as a cognitive organ;
- the improved design and control of robot hands, exploiting synergies to achieve a principled minimalistic realization of artificial hands capable of being programmed more simply and to adapt more robustly to different task/environment conditions;
- the application of the new understanding of sensorimotor synergies to the design of radically new and improved control architectures for haptic interfaces, both at the micro (cutaneous) and macro (whole‐hand) level, and
- the advancement of the state‐of‐the‐art in neuro‐prosthetic devices by providing seamless sensorimotor bidirectional information flow and adaptability to environmental constraints.
What our primary – and ambitious enough – goal is for the four‐years term of this project, is to develop a coherent set of theoretical tools ranging from neuroscience to physics and engineering, and a methodology for the design of the cognitive architectures underpinning the next generation of artificial hands and interfaces.
