Developing natural control strategies represents an intriguing challenge in the design of Human-Robot Interface (HRI) systems. The teleoperation of robotic grasping devices, especially in industrial, rescue and aerospace applications, is mostly based on non-intuitive approaches, such as remote controllers. On the other hand, recent research efforts target solutions that mimic the human ability to manage multi-finger grasps and finely modulate grasp impedance. Since electromyography (EMG) contains information about human motion control, it is possible to leverage such neuromuscular knowledge to teleoperate robotic hands for grasping tasks. In this article we present a HRI system based on 8 fully-differential EMG sensors connected to a wearable sensor node for acquisition and processing.By virtue of a novel bio-inspired approach, the embedded myocontroller merges pattern recognition and factorization techniques to combine a natural selection of the robotic hand configuration with the proportional control of the related grasps. The HRI system has been fully designed, implemented and tested on two robotic hands: a dexterous anthropomorphic hand and a three-fingered industrial gripper mounted on a robotic manipulator. Results of the test performed on 4 able-bodied subjects show success rates greater than 90% reached in grasping objects that require different hand shapes and impedance regulations for the task completion. The outcomes also show that the users modulate the bio-inspired degrees of control in a natural manner, proving the pertinence of the proposed system for an effective human-like control of robotic grasping devices in a wearable form-factor.

The scope of this work is to show the applicability of the Twisted String Actuators (TSAs) for lightweight, wearable and assistive robotic applications. To this aim, we have developed a novel surface electromyography (sEMG)-driven soft ExoSuit using the TSAs to perform both single and dual-arm elbow assistive applications. The proposed ExoSuit, with an overall weight of 1650 g, uses a pair of TSAs mounted in the back of the user, connected via tendons to the user's forearms to actuate each arm independently for supporting external loads. We confirm this new light-weight and customizable wearable solution via multiple user studies based on the biceps and tricep' sEMG measurements. We demonstrate that user's muscles can automatically activate and regulate the TSAs and compensate for the user's effort: by using our controller based on a Double Threshold Strategy (DTS) with a standard PID regulator, we report that the system was able to limit the biceps' sEMG activity under an arbitrary target threshold, compensating a muscular activity equal to 220% (related to a single arm 3 kg load) and 110% (related to a dual arm 4 kg load) of the threshold value itself. Moreover, the triceps' sEMG signal detects the external load and, depending on the threshold, returns the system to the initial state where it requires no assistance from the ExoSuit. The experimental results show the proposed ExoSuit's capabilities in both single and dualarm load compensation tasks. Therefore, the applicability of the TSAs is experimentally demonstrated for a real-case assistive device, fostering future studies and developments of this kind of actuation strategy for wearable robotic systems.

The preliminary experimental study toward the implementation of an arm rehabilitation device based on a twisted string actuation module is presented. The actuation module is characterized by an integrated force sensor based on optoelectronic components. The adopted actuation system can be used for a wide set of robotic applications and is particularly suited for very compact, light-weight, and wearable robotic devices, such as wearable rehabilitation systems and exoskeletons. Thorough presentation and description of the proposed actuation module as well as the basic force sensor working principle are illustrated and discussed. A conceptual design of a wearable arm assistive system based on the proposed actuation module is presented. Moreover, the actuation module has been used in a simple assistive application, in which surface-electromyography signals are used to detect muscle activity of the user wearing the system and to regulate the support action provided to the user to reduce his effort, showing in this way the effectiveness of the approach.

In this article we present a sEMG-driven humanin-the-loop (HITL) control designed to allow an assistive robot produce proper support forces for both muscular effort compensations, i.e. for assistance in physical tasks, and muscular effort generations, i.e. for the application in muscle strength training exercises related to the elbow joint. By employing our control strategy based on a Double Threshold Strategy (DTS) with a standard PID regulator, we report that our approach can be successfully used to achieve a target, quantifiable muscle activity assistance. In this relation, an experimental concept validation was carried out involving four healthy subjects in physical and muscle strength training tasks, reporting with single-subject and global results that the proposed sEMGdriven control strategy was able to successfully limit the elbow muscular activity to an arbitrary level for effort compensation objectives, and to impose a lower bound to the sEMG signals during effort generation goals. Also, a subjective qualitative evaluation of the robotic assistance was carried out by means of a questionnaire. The obtained results open future possibilities for a simplified usage of the sEMG measurements to obtain a target, quantitatively defined, robot assistance for human joints and muscles.

Human-Machine Interfaces based on gesture control are a very active field of research, aiming to enable natural interaction with objects. A successful State-of-the-Art (SoA) methodology for robotic hand control relies on the surface electromyographic (sEMG) signal, a non-invasive approach that can provide accurate and intuitive control when coupled with decoding algorithms based on Deep Learning (DL). However, the vast majority of the approaches so far have focused on sEMG classification, producing control systems that limit gestures to a predefined set of positions. In contrast, sEMG regression is still a new field, providing a more natural and complete control method that returns the complete hand kinematics. This work proposes a regression framework based on TEMPONet, a SoA Temporal Convolutional Network (TCN) for sEMG decoding, which we further optimize for deployment. We test our approach on the NinaPro DB8 dataset, targeting the estimation of 5 continuous degrees of freedom for 12 subjects (10 able-bodied and 2 trans-radial amputees) performing a set of 9 contralateral movements. Our model achieves a Mean Absolute Error of 6.89°, which is 0.15°better than the SoA. Our TCN reaches this accuracy with a memory footprint of only 70.9 kB, thanks to int8 quantization. This is remarkable since high-accuracy SoA neural networks for sEMG can reach sizes up to tens of MB, if deployment-oriented reductions like quantization or pruning are not applied. We deploy our model on the GAP8 edge microcontroller, obtaining 4.76 ms execution latency and an energy cost per inference of 0.243 mJ, showing that our solution is suitable for implementation on resourceconstrained devices for real-time control.Clinical relevance -The proposed setup enables the deployment of sEMG-based regression of hand kinematics for mechanical hand control via embedded devices, granting naturalness and accuracy with extremely low delay and energy consumption.