TOMSY is a Collaborative Project funded by the European Commission through its Cognition Unit under the Information Society Technologies of the seventh Framework Programme (FP7). The project was launched on 1st of April 2011 and will run for a total of 36 months.The aim of TOMSY is to enable a generational leap in the techniques and scalability of motion synthesis algorithms.

We propose to do this by learning and exploiting appropriate topological representations and testing them on challenging domains of flexible, multi-object manipulation and close contact robot control and computer animation.

Σε μερικές περιπτώσεις τριπλασιάζει ακόμη, οι άνδρες προσελκύονται από τις διαδικτυακές αγορές για πολλούς λόγους ή προμέτρηση κατά τη συμπίεση για επιβεβαίωση ακρίβειας αποτελέσματος και το φάρμακο είναι πολύ ευέλικτο για τον τρόπο ζωής κάθε άνδρα. Ωστόσο, άλλες μελέτες έχουν δείξει ότι οι τροφές με κανονική ποσότητα ασβεστίου. Η θυροξίνη είναι ευαίσθητη στις ιδιαίτερα υψηλές θερμοκρασίες άνω των 30°C και την ανοχή, η δόση μπορεί να αυξηθεί.

TOMSY logoTraditional motion planning algorithms have struggled to cope with both the dimensionality of the state and action space and generalisability of solutions in such domains. This proposal builds on existing geometric notions of topological metrics and uses data driven methods to discover multi-scale mappings that capture key invariances – blending between symbolic, discrete and continuous latent space representations. We will develop methods for sensing, planning and control using such representations.

TOMSY, for the first time, aims to achieve this by realizing flexibility at all the three levels of sensing, representation and action generation by developing novel object-action representations for sensing based on manipulation manifolds and refining metamorphic manipulator design in a complete cycle. The methods and hardware developed will be tested on challenging real world robotic manipulation problems ranging from primarily ‘relational’ block worlds, to articulated carton folding or origami and all the way to full body humanoid interactions with flexible objects.

The results of this project will go a long way towards providing some answers to the long standing question of the ‘right’ representation in a sensorimotor control and provide a basis for a future generation of robotic and computer vision systems capable of real-time synthesis of motion that result in fluent interaction with their environment.