Abstract
Day by day realistic applications (e.g., disaster response, services and logistics applications, etc.) are bringing robots into unstructured environments (e.g., houses, hospitals, museums, etc.) where they are expected to perform complex manipulation tasks. This growth in robot applications and technologies is changing the classical view of robots as caged manipulators in industrial settings. Indeed, robots are now required to directly interact with unstructured environments (and possibly interact and collaborate with humans). This demands to use advanced interaction methodologies.
Analyzing the state-of-the-art, variable impedance robot skills are typically investigated in two different perspectives: namely, control theory and machine learning. Control approaches are model-based and provide analytical solutions, where the models are often simplified computational representations. Classical robotics, mostly characterized by high gain negative error feedback control, is not suitable for tasks that involve interaction with the environment (possibly humans), because of possible high impact forces. The use of impedance control provides a feasible solution to overcome position uncertainties and subsequently avoid large impact forces, since robots are controlled to modulate their motion or compliance according to force perceptions. However, we still need to avoid hard-coding such skills. In contrast, humans have much superior performance due to their ability to variate the impedance as much as it is necessary. In this context, robot learning provides suitable approaches to learn variable impedance skills from human demonstrations or by transferring human's impedance skills to robots. Therefore, robot learning and impedance control would give us the ability to enhance robot manipulation performance and safety in unstructured environments, and better handling of perturbations during the interaction.
The aim of this Research Topic is to examine current research on how to successfully transfer compliant motions from humans to robots, allowing for safe and energy-efficient interactions. In this manner, we enable robots to perform in many scenarios, not only the ones that need physical interaction with the human but also in industrial settings.
Analyzing the state-of-the-art, variable impedance robot skills are typically investigated in two different perspectives: namely, control theory and machine learning. Control approaches are model-based and provide analytical solutions, where the models are often simplified computational representations. Classical robotics, mostly characterized by high gain negative error feedback control, is not suitable for tasks that involve interaction with the environment (possibly humans), because of possible high impact forces. The use of impedance control provides a feasible solution to overcome position uncertainties and subsequently avoid large impact forces, since robots are controlled to modulate their motion or compliance according to force perceptions. However, we still need to avoid hard-coding such skills. In contrast, humans have much superior performance due to their ability to variate the impedance as much as it is necessary. In this context, robot learning provides suitable approaches to learn variable impedance skills from human demonstrations or by transferring human's impedance skills to robots. Therefore, robot learning and impedance control would give us the ability to enhance robot manipulation performance and safety in unstructured environments, and better handling of perturbations during the interaction.
The aim of this Research Topic is to examine current research on how to successfully transfer compliant motions from humans to robots, allowing for safe and energy-efficient interactions. In this manner, we enable robots to perform in many scenarios, not only the ones that need physical interaction with the human but also in industrial settings.
| Original language | English |
|---|---|
| Journal | Frontiers in Robotics and AI |
| Publication status | Published - 2020 |
| MoE publication type | C2 Edited book, conference proceedings or special issue of a journal |