Search

The backlash is a lost motion in a mechanism created by gaps between its parts. It causes vibrations that increase over time and negatively affect accuracy and performance. The quickest and most precise way to measure the backlash is to use specific sensors, that have to be added to the standard equipment of the robot. However, this solution is little used in practice because raises the manufacturing costs. An alternative solution can be to exploit a virtual sensor, i.e., the information about phenomena that are not directly measured is reconstructed by signals from sensors used for other measurements.This work evaluates the use of bio-inspired swarm algorithms as the processing core of a virtual sensor for the backlash of a robotic joint. Swarm-based approaches, with their relatively modest occupation of memory and low computational load, could be ideal candidates to solve the problem. In this paper, we exploit four state-of-the-art swarm-based optimization algorithms: the Dragonfly Algorithm, the Ant Lion Optimizer, the Grasshopper Optimization Algorithm, and the Grey Wolf Optimizer. The four candidate algorithms are compared on 20 different datasets covering a range of backlash values that reflect an industrial case scenario. Numerical results indicate that, unfortunately, none of the algorithms considered provides satisfactory solutions for the problem analyzed. Therefore, even if promising, these algorithms cannot represent the final choice for the problem of interest.

International audience; The iterated prisoner's dilemma is a widely known model in game theory, fundamental to many theories of cooperation and trust among self-interested beings. There are many works in literature about developing efficient strategies for this problem, both inside and outside the machine learning community. This paper shift the focus from finding a “good strategy” in absolute terms, to dynamically adapting and optimizing the strategy against the current opponent. Turan evolves competitive non-deterministic models of the current opponent, and exploit them to predict its moves and maximize the payoff as the game develops. Experimental results show that the proposed approach is able to obtain good performances against different kind of opponent, whether their strategies can or cannot be implemented as finite state machines.

A huge number of optimization problems, in the CAD area as well as in many other fields, require a solution composed by a set of structurally homogeneous elements. Each element tackles a subset of the original task, and they cumulatively solve the whole problem. Sub-tasks, however, have exactly the same structure, and the splitting is completely arbitrary. Even the number of sub-tasks is not known and cannot be determined a-priori. Individual elements are structurally homogeneous, and their contribution to the main solution can be evaluated separately. We propose an evolutionary algorithm able to optimize groups of individuals for solving this class of problems. An individual of the best solution may be sub-optimal when considered alone, but the set of individuals cumulatively represent the optimal group able to completely solve the whole problem. Results of preliminary experiments show that our algorithm performs better than other techniques commonly applied in the CAD field.