Marek Sierotowicz

Modern assistive technologies, including prosthetic limbs, orthotic devices, and rehabilitation robots, are increasingly being driven by biosignal-based control systems. However, developing and validating such systems remains challenging owing to the complex signal-processing pipelines, heterogeneous hardware requirements, and limited support for real-time prototyping. We present MOSAIC, an open-source, modular software suite written in C# for real-time biosignal processing and intelligent device control. Configured via human-readable files, MOSAIC enables rapid prototyping through functional units called blocks, which support asynchronous data flow and precise execution timing. The system is hardware-independent and supports a wide range of sensors and output interfaces, including electromyography, inertial sensors, ultrasound, functional electrical stimulation, Internet Protocol over User Datagram Protocol, serial communication, and Bluetooth streaming. A live graphical interface enables interactive experimentation and immediate inspection of system behavior. We demonstrate MOSAIC across real-world applications, including prosthetic limb control, gesture-guided medical systems, and muscle-controlled orthotic devices. Its extensible design supports reproducible experimentation in assistive technologies.

Recently, the deflection-domain passivity approach (DDPA) was introduced which does not control a system's energetic behavior over time but over the deflection of the coupling controller's virtual spring. So far, it has been applied to guarantee passivity in variable stiffness systems and for chattering-free force attenuation. When compared to time-domain based approaches as the Time Domain Passivity Approach or energy-tanks, the DDPA yields a more continuous and proactive variation of the controller force since the required dissipative action is distributed over the deflection of the spring applied in the coupling controller. In contrast, time-based approaches behave non-proactively and often attenuate control signals such as commanded forces completely. This attenuation happens suddenly when no energy is left available with regards to passivity. The DDPA was the first method to ensure passivity and non-zero stiffnesses for arbitrary unknown stiffness profiles.Here, we extend the DDPA to the control of three energetically coupled rotations in SO(3). Experiments in a teleoperation setup confirm the functionality of the approach.

Objective. In recent years, Functional Electrical Stimulation has found many applications both within and outside the medical field. However, most available wearable FES devices are not easily adaptable to different users, and most setups rely on task-specific control schemes. Approach. In this article, we present a peripheral stimulation prototype featuring a compressive jacket which allows to easily modify the electrode arrangement to better fit any body frame. Coupled with a suitable control system, this device can induce the output of arbitrary forces at the end-effector, which is the basis to facilitate universal, task-independent impedance control of the human limbs. Here, the device is validated by having it provide stimulation currents that should induce a desired force output. The forces exerted by the user as a result of stimulation are measured through a 6-axis force-torque sensor, and compared to the desired forces. Furthermore, here we present the offline analysis of a regression algorithm, trained on the data acquired during the aforementioned validation, which is able to reliably predict the force output based on the stimulation currents. Main results. Open-loop control of the output force is possible with correlation coefficients between commanded and measured force output direction up to 0.88. A twitch-based calibration procedure shows significant reduction of the RMS error in the online control. The regression algorithm trained offline is able to predict the force output given the injected stimulation with correlations up to 0.94, and average normalized errors of 0.12 RMS. Significance. A reliable force output control through FES is the first basis towards higher-level FES force controls. This could eventually provide full, general-purpose control of the human neuromuscular system, which would allow to induce any desired movement in the peri-personal space in individuals affected by e.g. spinal cord injury.

Repetitive or tiring tasks and movements during manual work can lead to serious musculoskeletal disorders and, consequently, to monetary damage for both the worker and the employer. Among the most common of these tasks is overhead working while operating a heavy tool, such as drilling, painting, and decorating. In such scenarios, it is desirable to provide adaptive support in order to take some of the load off the shoulder joint as needed. However, even to this day, hardly any viable approaches have been tested, which could enable the user to control such assistive devices naturally and in real time. Here, we present and assess the adaptive Paexo Shoulder exoskeleton, an unobtrusive device explicitly designed for this kind of industrial scenario, which can provide a variable amount of support to the shoulders and arms of a user engaged in overhead work. The adaptive Paexo Shoulder exoskeleton is controlled through machine learning applied to force myography. The controller is able to determine the lifted mass and provide the required support in real time. Twelve subjects joined a user study comparing the Paexo driven through this adaptive control to the Paexo locked in a fixed level of support. The results showed that the machine learning algorithm can successfully adapt the level of assistance to the lifted mass. Specifically, adaptive assistance can sensibly reduce the muscle activity’s sensitivity to the lifted mass, with an observed relative reduction of up to 31% of the muscular activity observed when lifting 2 kg normalized by the baseline when lifting no mass.

The paralysis of the muscles controlling the hand dramatically limits the quality of life of individuals living with spinal cord injury (SCI). Here, we present a non-invasive neural interface technology that will change the lives of individuals living with cervical SCI (C4-C6). We demonstrate that eight motor- and sensory-complete SCI individuals (C5-C6, n = 7; C4, n = 1) are still able to task-modulate in real-time the activity of populations of spinal motor neurons with spared corticospinal pathways. In all tested patients, we identified groups of motor units under voluntary control that encoded a variety of hand movements. The motor unit discharges were mapped into more than 10 degrees of freedom, ranging from grasping to individual hand digit flexions and extensions. We then mapped the neural dynamics into a real-time controlled virtual hand. The patients were able to match the cue hand posture by proportionally controlling four degrees of freedom (opening and closing the hand and index flexion/extension). These results demonstrate that wearable muscle sensors provide access to voluntarily controlled neural activity in complete cervical SCI individuals.

With emerging capabilities, robots will advance gradually into human environments in the near future. Thereby, safety and robustness is currently tackled through intrinsically soft robotics or variable impedances, mainly stiffnesses. In tele-operation, for instance, the control stiffness can be adapted to a measured arm impedance of the operator to stiffen the robot only when required for a manipulation task. Thus, humans or moving objects in the robot’s environment are protected from hard collisions. Independent from its realization through hardware or software, the stability of the variation needs to be ensured through control strategies since energy is potentially introduced into the robotic system. This work presents a novel gradient-based passivity control concept for variable stiffnesses. In contrast to state-of-the-art methods, the approach is based on a potential energy storage reference and prevents phases of zero stiffness through deflection-domain control. I.e., according to the energy storage, the stiffness variation over the spring deflection is controlled to ensure passivity. Experiments confirm the functionality of the approach and its robustness against delayed communication and active environments.

In the field of rehabilitation robotics, transparent, precise and intuitive control of hand exoskeletons still represents a substantial challenge. In particular, the use of compliant systems often leads to a trade-off between lightness and material flexibility, and control precision. In this letter, we present a compliant, actuated glove with a control scheme to detectthe user’s motion intent, which is estimated by a machine learning algorithm based on muscle activity. Six healthy study participants used the glove in three assistance conditions during a force reaching task. The results suggest that active assistance from the glove can aid the user, reducing the muscular activity needed to attain a medium-high grasp force, and that closed-loop control of a compliant assistive glove can successfully be implemented by means of a machine learning algorithm.

Objective. Bimanual humanoid platforms for home assistance are nowadays available, both as academic prototypes and commercially. Although they are usually thought of as daily helpers for non-disabled users, their ability to move around, together with their dexterity, makes them ideal assistive devices for upper-limb disabled persons, too. Indeed, teleoperating a bimanual robotic platform via muscle activation could revolutionize the way stroke survivors, amputees and patients with spinal injuries solve their daily home chores. Moreover, with respect to direct prosthetic control, teleoperation has the advantage of freeing the user from the burden of the prosthesis itself, overpassing several limitations regarding size, weight, or integration, and thus enables a much higher level of functionality. Approach. In this study, nine participants, two of whom suffer from severe upper-limb disabilities, teleoperated a humanoid assistive platform, performing complex bimanual tasks requiring high precision and bilateral arm/hand coordination, simulating home/office chores. A wearable body posture tracker was used for position control of the robotic torso and arms, while interactive machine learning applied to electromyography of the forearms helped the robot to build an increasingly accurate model of the participant’s intent over time. Main results. All participants, irrespective of their disability, were uniformly able to perform the demanded tasks. Completion times, subjective evaluation scores, as well as energy- and time- efficiency show improvement over time on short and long term. Significance. This is the first time a hybrid setup, involving myoeletric and inertial measurements, is used by disabled people to teleoperate a bimanual humanoid robot. The proposed setup, taking advantage of interactive machine learning, is simple, non-invasive, and offers a new assistive solution for disabled people in their home environment. Additionnally, it has the potential of being used in several other applications in which fine humanoid robot control is required.