Control of two-wheeled humanoid robots poses several challenges due to the unstable dynamics of their mobile base and the coupling between the upper and lower body dynamics. The problem is often faced in the literature with methods based on the linearized or simplified models that fail in exploiting the whole body dynamic capabilities of the platform in use. In this letter, we tackle the problem of whole-body dynamic control for a mobile wheeled unstable humanoid robot. Compared to the existing approaches based on online optimization to guarantee respect of the constraints, we propose a control method that takes into account the nominal constrained dynamics of the robot in the quasi-velocities through an internal model, thus reducing the computational burden. A computed-torque control law in the quasi-velocities is used to stabilize the robot around the upper position. We report on preliminary experimental results and on the method effectiveness in rejecting unknown external disturbances.

This contribution describes a case study of a “do-it-yourself” (DIY) opensource service and related product to help combating the COVID-19 emergency. It illustrates the birth of LHF Connect, a project designed to facilitate communication between patients isolated in COVID-19 hospitals’ ward and their relatives. LHF Connect is a teleoperated robot that can move in autonomy around the hospital. A User Centered Design approach, methods and specific tools helped in managing crucial steps of the design process such as i) the collection of needs coming from the context, stakeholders and end-users; ii) defining the service blueprint; iii) imagining finishing concepts; and iv) managing the communication activities. The initiative has been promoted by a multidisciplinary team of researchers (mainly roboticists with the help of specific competences coming from Design discipline).

The objective of this paper is to propose a framework for a robot to learn multiple Sensory-Motor Contingencies from human demonstrations and reproduce them. Sensory-Motor Contingencies are a concept that describes intelligent behavior of animals and humans in relation to their environment. They have been used to design control and planning algorithms for robots capable of interacting and adapting autonomously. However, enabling a robot to autonomously develop Sensory-Motor Contingencies is challenging due to the complexity of action and perception signals. This framework leverages tools from Learning from Demonstrations to have the robot memorize various sensory phases and corresponding motor actions through an attention mechanism. This generates a metric in the perception space, used by the robot to determine which sensory-motor memory is contingent to the current context. The robot generalizes the memorized actions to adapt them to the present perception. This process creates a discrete lattice of continuous Sensory-Motor Contingencies that can control a robot in loco-manipulation tasks. Experiments on a 7-dof collaborative robotic arm with a gripper, and on a mobile manipulator demonstrate the functionality and versatility of the framework.