To meet these needs, this research line is focused on the analysis, design, and implementation of methods and tools that offer non-expert users an intuitive way to program and interact with robots. Furthermore, thanks to the Joiint Lab established in 2021 within the technology park Kilometro Rosso, our laboratory collaborates side by side with several companies which propose new challenges and provide valuable feedback on the developed technologies, establishing a synergy between research and industrial needs.

Human-Robot Interfaces (HRI)

In history, several tools and devices have been developed by humans to interact and interface with different systems, facilitating the work and increasing ergonomics, safety, and precision.

In general, the interfaces enable communication between systems that do not share the same language. Today, user interfaces are playing a relevant role in the industrial field, bridging the gap between humans and machines. The research activities in this area present interfaces for remote and  proximity interaction:

Interface for remote interaction: the main field of application concerns teleoperation. The approaches developed in our Lab are designed to interface with a generic robot composed of both manipulators and mobile systems. The strengths of the developed interfaces lie in their intuitiveness, functionality, and affordability.

The proposed teleoperation framework [1] leverages a motion capture suite composed of wearable and lightweight devices placed on the user’s arms, forearms, and hands. Each device integrates inertial and electromyography sensors thanks to which it is possible to remap the user's movements and intentions on the controlled robot. In addition, stereoscopic cameras integrated with virtual reality headsets provide appropriate and immersive visual feedback.

This framework has been tested on different robots and in several real scenarios: Search & Rescue applications [2] (video), service robotics [1] (video), and in response to the pandemic [3] (video).

Interface for proximity interaction: although kinesthetic teaching represents one of the most effective methods to program industrial robots, it is useful only for manipulators and often requires expensive extra hardware (e.g. force/torque sensors) to achieve a powerful gravity compensation.

The method developed in our Lab [1] provides a tool to jog and program mobile manipulators by using a single and user-friendly interface. Inspired by hand-guide approaches to jog robotic arms, the proposed method enables users to move both manipulators and mobile bases in an intuitive and contactless way through a common smartphone (video).

Robot Programming without Coding

Robot programming remains a crucial point in the robot’s spread. Despite the great strides made in the “Intuitive Robot Programming” field, the significant part of the lifetime cost of a robotic cell still lies in the application software.

Learning from demonstration (LfD) established, over the years, as a promising method to transfer skills from humans to robots. In general, three phases in LfD have been identified: teaching, learning, and autonomous execution. The scientific community provided several tools to demonstrate a task to a robot as well as methods to encode and generalize the learned actions in a new situation. Although the relation between perception and action has been demonstrated through several psychological and neurobiological studies, it is important to establish and select what is relevant during the execution of a given task.

This line of research presents a framework [1] that encapsulates the three phases involved during robot programming, grouping perceptions according to their nature and establishing rules for the selection of salient perceptions. In addition, the proposed framework is compatible with the different sub-methods offered by the literature in the field of “tasks segmentation” and “actions generalization”. Finally, all the learned tasks are represented as a network, which is able to evolve and reorganize automatically in case new tasks are learned (video).