RoboCup

(is paper presents an efficient technique for a self-learning dynamic walk for a quadrupedal robot. (e cost function for such a task is typically complicated, and the number of parameters to be optimized is high. (erefore, a simple technique for optimization is of importance. We apply a genetic algorithm (GA) which uses real experimental data rather than simulations to evaluate the fitness of a tested gait. (e algorithm actively optimizes 12 of the robot's dynamic walking parameters. (ese include the step length and duration and the bending of an active back. For this end, a simple quadrupedal robot was designed and fabricated in a structure inspired by small animals. (e fitness function was then computed based on experimental data collected from a camera located above the scene coupled with data collected from the actuators' sensors. (e experimental results demonstrate how walking abilities are improved in the course of learning, while including an active back should be considered to improve walking performances.

It is an increasingly common practice in schools to propose to children and young people educational activities based on the use of robots to introduce topics such as digital competences, computational thinking and artificial intelligence (AI) education. Although, the potentials of educational robotics are many, we must also ask ourselves what it means today, for a teacher to educate to AI. In this regard, this contribution reports the most significant aspects that emerged from a first exploratory survey aimed at acquiring specific information on the use of robots in relation to AI education. The survey was carried out on a small sample of privileged witnesses belonging to the school. In the face of a recognized impact of robotics experiences on learning, specific attention emerges to what can be done to educate the new generations to be future digital citizens, aware of possible implications of AI in our lives.