Search

Due to the increasing average age of skilled professionals in the field of construction and municipal facilities as well as increasing the number of migrants who often do not possess the necessary skills to carry out construction work and research, there is an urgent need to an influx of skilled workers with different levels of education and training. In this regard, it is necessary to improve the skills of teachers and trainers, to help them in their acquisition of professional experience in work with the modern technological equipment, contribute to the development of innovative technologies applied to the leading construction companies in the region; and train the concept of “double teacher”, who can solve several problems. Solving this problem allows Technical College will contribute effective organization of production practices, will increase interest in the building trade, the formation of the graduates of the college corporate spirit and the emergence of confidence in their own employability. [ABSTRACT FROM AUTHOR]

Programming a robot to deal with open-ended tasks remains a challenge, in particular if the robot has to manipulate objects. Launching, grasping, pushing or any other object interaction can be simulated but the corresponding models are not reversible and the robot behavior thus cannot be directly deduced. These behaviors are hard to learn without a demonstration as the search space is large and the reward sparse. We propose a method to autonomously generate a diverse repertoire of simple object interaction behaviors in simulation. Our goal is to bootstrap a robot learning and development process with limited information about what the robot has to achieve and how. This repertoire can be exploited to solve different tasks in reality thanks to a proposed adaptation method or could be used as a training set for data-hungry algorithms. The proposed approach relies on the definition of a goal space and generates a repertoire of trajectories to reach attainable goals, thus allowing the robot to control this goal space. The repertoire is built with an off-the-shelf simulation thanks to a quality–diversity algorithm. The result is a set of solutions tested in simulation only. It may result in two different problems: (1) as the repertoire is discrete and finite, it may not contain the trajectory to deal with a given situation or (2) some trajectories may lead to a behavior in reality that differs from simulation because of a reality gap. We propose an approach to deal with both issues by using a local linearization of the mapping between the motion parameters and the observed effects. Furthermore, we present an approach to update the existing solutions repertoire with the tests done on the real robot. The approach has been validated on two different experiments on the Baxter robot: a ball launching and a joystick manipulation tasks. • Divergent evolutionary algorithms can be used to learn object manipulation skills. • Rich, diverse actions repertoires can simply be learnt in simulation. • Learnt repertoires can be used to accurately estimate the local Jacobian matrix. • This can be used to generalize to new actions or cross the reality gap. • Most learning is done in simulation, with few real robot experiments. [ABSTRACT FROM AUTHOR]