In this paper, we present the modeling and validation of a new family of climbing robots that are capable of adhering to vertical surfaces through permanent magnetic elements. The robotic system is composed of two modules, the master and the follower carts, which are arranged in a sandwich configuration, with the surface to climb interposed between them. Thanks to this configuration, the mobile robot can climb even nonferromagnetic and curved surfaces; moreover, the master cart is capable of freely moving on the floor by detaching from the follower. In this paper, we propose the mathematical modeling, simulation, and experimental validation of this kind of robots, with particular focus on the transitions between floor and climbing motion.

Controlling a chain of tethered mobile robots (TMRs) can be a challenging task. This kind of system can be considered kinematically as an open-chain robotic arm where the mobile robots are considered as a revolute joint and the tether is considered as a variable length link, using a prismatic joint. Thus, the TMRs problem is decoupled into two parallel problems: the equivalent robotic manipulator control and the tether shape computation. Kinematic redundancy is exploited in order to coordinate the motion of all mobile robots forming the chain, expressing the constraints acting on the mobile robots as secondary tasks for the equivalent robotic arm. Implementation in the Gazebo simulation environment shows that the methodology is capable of controlling the chain of TMRs in cluttered environments.

Crowd navigation with autonomous systems is a topic which has seen a rapid increase in interest recently. While it appears natural to humans, being able to reach a target can prove difficult or impossible to a mobile robot because of the safety issues related to collisions with people. In this work we propose an approach to control a robot in a crowded environment; the method employs an Artificial Neural Network (ANN) that is trained with the NeuroEvolution of Augmented Topologies (NEAT) method. Models for the kinematics, perception, and cognition of the robot are presented. In particular, perception is based on a raycasting model which is tailored on the ANN. An in-depth analysis of a number of parameters of the environment and the robot is performed and a comparative analysis is presented; finally, results of the performance of the controller trained with NEAT are compared to those of a human driver who takes over the controller itself. Results show that the intelligent controller is able to perform on par with the human, within the simulated environment.

For a mobile robot, navigation in a densely crowded space can be a challenging and sometimes impossible task, especially with traditional techniques. In this paper, we present a framework to train neural controllers for differential drive mobile robots that must safely navigate a crowded environment while trying to reach a target location. To learn the robot’s policy, we train a convolutional neural network using two Reinforcement Learning algorithms, Deep Q-Networks (DQN) and Asynchronous Advantage Actor Critic (A3C) and develop a training pipeline that allows to scale the process to several compute nodes. We show that the asynchronous training procedure in A3C can be leveraged to quickly train neural controllers and test them on a real robot in a crowded environment.

In this paper, we propose an in-depth evaluation of the performance of the Archimede rover while traversing rough terrain with loose soil. In order to better analyze this, the reality gap is evaluated when simulating the behavior with an open-source simulator. To this extent, we implement a full model of the rover in the open-source dynamics simulator Gazebo, along with several types of terrains that replicate the experimental conditions. The rover control system is equipped with a kinematics model that allows for driving in different modes. We implement an odometric system aboard the rover, as well as an external optical absolute tracking system as reference. We estimate the drift occurring during driving in different configurations, two types of soil with corresponding wheel geometries. The results show good adherence of the odometry when the rover drives on planar ground; conversely, as expected, a marked influence of slope is seen on wheel drift. The reality gap between simulations and experimental results is kept comparatively small provided that slopes are not present.