27 September 2023 in Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies
Passive Haptic Learning (PHL) is a method by which users are able to learn motor skills without paying active attention. In past research, vibration is widely applied in PHL as the signal delivered on the participant's skin. The human somatosensory system provides not only discriminative input (the perception of pressure, vibration, slip, and texture, etc.) to the brain but also an affective input (sliding, tapping and stroking, etc.). The former is often described as being mediated by low-threshold mechanosensitive (LTM) units with rapidly conducting large myelinated (Aᵬ) afferents, while the latter is mediated by a class of LTM afferents called C-tactile afferents (CTs). We investigated whether different tactile sensations (tapping, light stroking, and vibration) influence the learning effect of PHL in this work. We built three wearable systems corresponding to the three sensations respectively. 17 participants were invited to learn to play three different note sequences passively via three different systems. The subjects were then tested on their remembered note sequences after each learning session. Our results indicate that the sensations of tapping or stroking are as effective as the vibration system in passive haptic learning of piano songs, providing viable alternatives to the vibration sensations that have been used so far. We also found that participants on average made up to 1.06 errors less when using affective inputs, namely tapping or stroking. As the first work exploring the differences in multiple types of tactile sensations in PHL, we offer our design to the readers and hope they may employ our works for further research of PHL.
1 March 2023 in IEEE Sensors Letters
Minimally invasive surgical procedures can strongly benefit from nonvisual magnetic instrument tracking. Most state-of-the-art sensor systems for magnetic tracking, however, are rigid and bulky or depend on multimodal sensor technologies. In this work, we investigate a compliant, wearable 2-D Hall-effect sensor array with self-sensing ability and a minimal spatial footprint. Our tracking algorithm is based on a permanent magnet model and a least squares optimization. For evaluation of self-sensing, we tested the sensor array attached to 3D-printed circular frames with known geometries. Tracking was experimentally evaluated moving the target magnet on a preset path utilizing a robotic actuator. Results show that stronger bending radii lead to larger errors of the shape estimation with an overall absolute error of $8.33^{\circ }$ . However, larger radii eventually lead to a decreased Euclidean distance error in the actual tracking procedure between 1.31 mm and 3.38 mm. Thus, the additional efforts due to shape estimation appear fair, since the overall performance of the tracking improves and the spatial footprint can be minimized with our approach. Future work will address performance improvement and implementation of a machine learning approach, aiming for real-time capability.
1 July 2023 in at - Automatisierungstechnik
Shape memory alloy-based flexible instruments have potential for enhancing the safety in minimally invasive surgery compared to passive rigid devices. We developed a data-driven polynomial model to estimate deflection of a 2D bending actuator using electrical resistance. The model accurately predicts deflections (mean error <3.6 mm), but force sensing augmentation is required for unknown load cases. The model is specific to the tested actuator geometry, and future research should investigate multiple actuators and explore nonlinear modeling approaches.
18 October 2023 in IEEE Robotics and Automation Letters
Tendon-driven continuum robots offer enhanced dexterity for intricate tasks within confined spaces. Nevertheless, when exclusively relying on remote access points, the entire fixed-length robotic system must be precisely repositioned to insert the robotic structure. Conversely, existing methods incorporating extendability tend to introduce complex design requirements, often resulting in a larger spatial footprint. Here, we present a novel design featuring a self-assembling continuum robotic structure during extension process with variable section- and segment lengths. We investigate a compact actuator unit ( $\text{240} \,\text{mm}\times \text{140} \, \text{mm} \times \text{145} \,\text{mm}$ , $\text{1.5} \,\text{kg}$ ) assembling a robotic structure smaller than $15.4 \,\text{mm}$ in diameter, with a three-tendon configuration and two omnidirectional bendable segments, able to extend up to $240 \,\text{mm}$ . A reliable assembly performance was found with repeatability errors below $2 \,\text{mm}$ during extension, while workspace and dexterity of the continuum robot achieved a median error of $2.39 \,\text{mm}$ for bending. Our scalable approach reaches state-of-the-art dexterity and workspace range, showing great potential to be used for existing and future tendon-driven robotic systems.
13 February 2026 in IEEE Robotics and Automation Letters
Mechanical thrombectomy (MT) is typically the optimal treatment for acute ischemic stroke involving large vessel occlusions, but access is limited due to geographic and logistical barriers. Reinforcement learning (RL) shows promise in autonomous endovascular navigation, but generalization across ‘long’ navigation tasks remains challenging. We propose a Hierarchical Modular Multi-Agent Reinforcement Learning (HM-MARL) framework for autonomous two-device navigation in vitro, enabling efficient and generalizable navigation. HM-MARL was developed to autonomously navigate a guide catheter and guidewire from the femoral artery to the internal carotid artery (ICA). A modular multi-agent approach was used to decompose the complex navigation task into specialized subtasks, each trained using Soft Actor-Critic RL. The framework was validated in both in silico and in vitro testbeds to assess generalization and real-world feasibility. In silico, a single-vasculature model achieved 92–100% success rates on individual anatomies, while a multi-vasculature model achieved 56–80% across multiple patient anatomies. In vitro, both HM-MARL models successfully navigated 100% of trials from the femoral artery to the right common carotid artery and 80% to the right ICA but failed on the left-side vessel superhuman challenge due to the anatomy and catheter type used in navigation. This study presents the first demonstration of in vitro autonomous navigation in MT vasculature. While HM-MARL enables generalization across anatomies, the simulation-to-real transition introduces challenges. Future work will refine RL strategies using world models and validate performance on unseen in vitro data, advancing autonomous MT towards clinical translation.
1 August 2021 in Current Directions in Biomedical Engineering
Smart medical phantoms for training and evaluation of endovascular procedures ought to measure impact forces on the vessel walls worth protecting to provide feedback to clinicians and articulated soft robots. Recent commercial smart phantoms are expensive, usually not customizable to different applications and lack accessibility for integrated development. This work investigates piezoresistive films as highly integratable flexible sensors to be used in arbitrary soft vessel phantom anatomies over large surfaces and curved shapes providing quantitative measurement in the force range up to 1 N with 0.1 N resolution. First results show promising performance at the point of calibration and in a 5 mm range around it, with absolute measuring error of 28 mN and a standard deviation of ±10 mN and response times <500 ms. Future work shall address the optimization of response time and sensor shapes as well as the evaluation with experienced clinicians.