Robot Manipulator with emergent Behaviour supported by a Smart Sensorial Material and Agent Systems
Stefan Bosse, Florian Pantke, Stefan Edelkamp
In Proceedings of the Smart Systems Integration Conference SSI 2013, Topic 5, Sensor Networks, (SSI-2013), 13.3.-14.3.2013, Amsterdam, o.A., Mar/2013.
Intelligent behaviour of robot manipulators become important in unknown and changing environments. Emergent behaviour of a machine arises intelligence from the interactions of robots with its environment. Sensorial materials equipped with networks of embedded miniaturized smart sensors can support this behaviour. In this work an integrated autonomous decentralized sensor networks is shown providing perception in a robot arm manipulator. Each sensor network is connected to strain gauge sensors mounted on a flexible polymer surface, delivering spatial resolved information of external forces applied to the robot arm, required for example for obstacle avoidance or for manipulation of objects.
Each autonomous sensor node provides communication, data processing, and energy management implemented on microchip level. Commonly a high number of strain gauge sensors are used to satisfy a high spatial
resolution. Our approach uses advanced Artificial Intelligence and Machine Learning methods for the mapping of only a few non-calibrated and non-long-term stable noisy strain sensor signals to spatially resolved load information and a decentralized data processing approach to improve robustness. Robustness in the sensor network is provided by 1. autonomy of sensor nodes, 2. by smart adaptive communication to overcome link failures and to reflect changes in network topology, and 3. by using intelligent adaptive algorithms. Robust cooperation and distributed data processing is achieved by using Mobile Agent systems . Agent behaviour and cooperation is implemented on microchip level .
The central aim is to derive useful information constrained by limited computational power and noisy sensor signals not able to be captured by a complete system model. Machine Learning (ML) methods are capable to map an initially unknown n-dimensional set of input signals to a m-dimensional output set of information like the position and strength of applied forces . Without any interaction and material model Machine Learning requires a training
phase. Additional material models and FEM simulation can reduce or avoid the training phase . The training set contains recorded load positions, masses and classification results for different load cases determined via sensor measurement. The hyper-elastic behaviour of polymers reduces the long-term prediction accuracy of learned models as well as the consistency with FEM output, requiring Machine Learning models that automatically adjust their output to the structure’s ageing process.