Aerial robotics aims at the development of a new generation of flying service robots capable of supporting human beings in all those activities requiring the ability to interact, actively and safely, in the air. Challenging fields are the inspection of buildings and large infrastructures, sample picking, remote aerial manipulation, etc. Our research is focused on the development of advanced automatic control algorithms able to govern the aerial platform. These algorithms are remotely supervised by the operator with the use of haptic devices. Particular emphasis is given to developing advanced human-in-the-loop and autonomous navigation control strategies relying upon a cooperative and adaptive interaction between the automatic onboard control and the remote operator. Force and visual feedback strategies are also investigated to transform the aerial platform in a flying hand suitable for aerial manipulation.
In order for a robot to perform complex tasks in the real world, it is necessary to endow its control system with cognitive capabilities enabling deliberation, execution, learning, and perception in dynamic, interactive and unstructured environments. Cognitive robotics is concerned with these issues proposing architectures, AI-inspired methods for the integration of sensorimotor, cognitive, and interaction capabilities in autonomous robots. In this respect, we are developing an integrated cognitive control framework that combines supervisory attention, human-aware planning, collaborative plan execution, and incremental task teaching. We have demonstrated the effectiveness of the proposed methods in several applications of industrial, service and field robotics.
An assistive robot is a device that can process sensory information and perform actions to benefit people with disabilities and seniors. The goal of rehabilitation robotics is to investigate the application of robotics in motor therapy procedures for recovering motor capabilities and control in persons with impairment following such diseases as stroke, as well as to develop robotic and mechatronic technical aids for independent living of disabled. We are exploiting our expertise in robot design, mobile manipulation, human‒robot interaction, and multimodal control for assistive robots. We consider scenarios such as performing normal human activities of daily living (ADLs) or a physical rehabilitation setting for which we are designing and controlling robot prostheses.
Dexterous manipulation of objects with two robot hands requires a suitable cooperation between the robot arms. Also, the motion of the arms should be coordinated with that of the hands. In this framework, research is focused on design of control and planning algorithms. One objective is that of merging vision and touch data and integrating them with reasoning to execute complex manipulation tasks. Other objectives are to avoid self-collisions and collisions with the environment, redundancy resolution using a task-priority approach and human likeness during task execution. Furthermore, learning and control strategies based on neural networks, reinforcement learning and sensory-motor synergies are investigated and tested on anthropomorphic robots.
With the increase of persuasive technology in both sensing and actuation speed, it has become possible to manipulate an object speedily. However, it is not easy for a robot to replicate dexterous human capabilities. By exploiting the dynamic effects of both object and robot motion, a robotic system can effectively achieve object manipulation in the desired way. In dynamic manipulation, an important role is played by forces and accelerations, which are used together with kinematics, static, and quasi-static forces, to achieve a general description of a manipulation task. Moreover, the non-prehensile manipulation of an object extends its feasible movements allowing rolling, pushing, throwing, and tossing, and exhibits the intrinsic dynamics of both the task and the object. In this respect, we have developed a manipulation technique that actively uses task dynamics to control motion variables of a given object. Performing such dynamic non-prehensile manipulation tasks by using deformable objects and mobile platforms is a great challenge.
Robots are becoming ubiquitous and utilized in anthropic environments. When a robot cohabits the environment with a human being, human‒robot interaction issues are to be considered. It is customary to distinguish between cognitive and physical human‒robot interaction. Suitable modelling and control techniques for collision avoidance and, more generally, for fast reactive strategies, have been developed. Also, control strategies aimed at ensuring robot compliance at the end effector or along the robot’s body in the presence of physical interaction, have been introduced, allowing a safe and dependable interaction. For co-manipulation tasks, suitable approaches based on variable impedance control have been proposed to enhance task execution. An integration of control and cognitive processes is also needed. In this respect, we are investigating methods for human intention/activity recognition, multimodal interaction, human-aware planning, sliding autonomy, collaborative and mixed-initiative plan execution, learning by demonstration.
Legged robots are preferred to standard wheeled robots in the presence of rough and uneven terrains. The legs are indeed able to isolate the body from the ground irregularities and avoid undesirable footholds. However, robustness is one critical issue characterizing legged robots, especially the biped ones. Our research aims at developing model-based passive controllers to improve robustness of existing walking gaits. We are also seeking to find analogies between walking gaits and some other robotic tasks like non-prehensile dynamic manipulation.
Research is devoted to the development and employment of artificial hands in all those fields where the use of anthropomorphic prehensile devices makes the difference, such as humanoid robots, prosthetics, surgical tools. The innovation is found not only in the mechanical design and integrated sensory system but also in the novel planning and control algorithms generating intelligent and effective actions. For the hand design, we are investigating smart solutions for underactuated design aimed at simplification of the device itself in terms of weight and size, yet without reducing the functionalities. Dimensionality reduction is adopted to develop control and learning strategies for grasping and in-hand manipulation.
Industry 4.0 involves the large use of robots that must be mobile, collaborative, autonomous and connected to the cloud, both in manufacturing and in logistics. In manufacturing, we have developed algorithms where robot’s autonomy is enhanced by adopting suitable planning and control strategies based on the use of exteroceptive sensors, like force/torque sensors or cameras. These sensors can be also used to ensure a safe coexistence or collaboration with human workers, as well as for more intuitive programming. In logistics, we have recently developed a robotic depalletizing cell capable of picking and placing cases of different sizes in different ways from a non-homogeneous pallet, using the information provided by cameras and by the store management system.
Inspired by biological structures, soft robots exhibit novel capabilities with respect to their rigid-bodied counterpart, such as traversing confined spaces in unstructured environments, manipulating unknown objects, conforming their shape to complex paths and adapting their morphology by safely interacting with the environment. These desirable characteristics come at the cost of increased complexity for predicting, and thus controlling, the 3D shape that soft robots assume when subject to actuation and external loads. In this framework, our research is focused on the development of accurate models and efficient simulation algorithms for soft-bodied and soft articulated robots. The applications of the developed methods span from maintenance and inspection in industrial sites to minimally invasive robotic surgery in the medical field. Recent medical soft robot designs, including surgical, diagnostic soft tools, and rehabilitation devices, have been realized in our lab, such as a rigid-soft robot for prostate biopsy, a soft anthropomorphic surgical tool for organs/tissues manipulation and diagnostics, and a robot hand prosthesis with distributed compliance by means of elastic tendons.
Robot-assisted surgery allows doctors to perform many types of complex procedures with more precision, flexibility and control than it is possible with conventional techniques. Surgical robotics is a rapidly evolving field which helps minimizing pain and risk associated with surgery, while increasing the likelihood of a fast recovery and excellent clinical outcomes. Robotics is usually associated with minimally invasive surgery procedures performed through tiny incisions or natural orifice transluminal endoscopic surgery (NOTES), but it is also used in certain traditional open procedures. Our work is focused on the development of semi-autonomous control strategies for suturing, cutting and needle insertion, design of shared and supervised autonomy, modeling of deformable objects, simulation of soft and rigid contacts, design of new tools and surgical instruments, and force/tactile sensing devices. Our research interests focus also on the design of innovative robotic solutions for biopsy and microsurgery. We are also adopting deep learning techniques for surgical robot control and diagnostics.