RESUMEN
The simulation-to-reality (sim2real) problem is a common issue when deploying simulation-trained models to real-world scenarios, especially given the extremely high imbalance between simulation and real-world data (scarce real-world data). Although the cycle-consistent generative adversarial network (CycleGAN) has demonstrated promise in addressing some sim2real issues, it encounters limitations in situations of data imbalance due to the lower capacity of the discriminator and the indeterminacy of learned sim2real mapping. To overcome such problems, we proposed the imbalanced Sim2Real scheme (ImbalSim2Real). Differing from CycleGAN, the ImbalSim2Real scheme segments the dataset into paired and unpaired data for two-fold training. The unpaired data incorporated discriminator-enhanced samples to further squash the solution space of the discriminator, for enhancing the discriminator's ability. For paired data, a term targeted regression loss was integrated to ensure specific and quantitative mapping and further minimize the solution space of the generator. The ImbalSim2Real scheme was validated through numerical experiments, demonstrating its superiority over conventional sim2real methods. In addition, as an application of the proposed ImbalSim2Real scheme, we designed a finger joint stiffness self-sensing framework, where the validation loss for estimating real-world finger joint stiffness was reduced by roughly 41% compared to the supervised learning method that was trained with scarce real-world data and by 56% relative to the CycleGAN trained with the imbalanced dataset. Our proposed scheme and framework have potential applicability to bio-signal estimation when facing an imbalanced sim2real problem.
RESUMEN
To provide a stable surgical view in Minimally Invasive Surgery (MIS), it is necessary for a flexible endoscope applied in MIS to have adjustable stiffness to resist different external loads from surrounding organs and tissues. Pneumatic soft actuators are expected to fulfill this role, since they could feed the endoscope with an internal access channel and adjust their stiffness via an antagonistic mechanism. For that purpose, it is essential to estimate the external load. In this study, we proposed a neural network (NN)-based active load-sensing scheme and stiffness adjustment for a soft actuator for MIS support with antagonistic chambers for three degrees of freedom (DoFs) of control. To deal with the influence of the nonlinearity of the soft actuating system and uncertainty of the interaction between the soft actuator and its environment, an environment exploration strategy was studied for improving the robustness of sensing. Moreover, a NN-based inverse dynamics model for controlling the stiffness of the soft actuator with different flexible endoscopes was proposed too. The results showed that the exploration strategy with different sequence lengths improved the estimation accuracy of external loads in different conditions. The proposed method for external load exploration and inverse dynamics model could be used for in-depth studies of stiffness control of soft actuators for MIS support.
Asunto(s)
Robótica , Robótica/métodos , Diseño de Equipo , Procedimientos Quirúrgicos Mínimamente Invasivos , Endoscopios , Redes Neurales de la ComputaciónRESUMEN
Introduction: Minimally Invasive Surgery (MIS) offers targeted surgical access with reduced invasiveness; however, the maneuverability challenges of traditional instruments in this domain underscore the need for innovative solutions. Soft actuators activated by fluids or gases present a promising strategy for augmenting endoscopic capabilities, thereby enhancing the surgical precision in MIS. This study aimed to explore the intricate dynamics of the interactions between soft actuators and endoscopes, with an emphasis on the pivotal role of cross-sectional chamber shapes. While previous studies have touched on the influence of chamber shapes on bending properties, we provide a comprehensive exploration. We explore how these shapes modulate friction forces, which in turn influence the interactions governing bending, response, and stiffness adjustability, all of which are essential for enhancing endoscope maneuverability in MIS contexts. Methods: A novel bilateral symmetrical air chamber design was adopted to investigate various chamber shapes. We employed finite element analysis (FEA) simulations followed by prototype testing to evaluate the interactions driven by these chamber shapes and to discern their impact on actuator properties. Recognizing the pivotal role of friction in these interactions, we conducted dedicated friction experiments. These experiments further deepened our understanding of the relationship between chamber shape and friction, and how this synergy influences the properties of the actuator. Results: Our findings showed that actuators with wider chambers generate larger friction forces, thereby enhancing the interaction and improving the bending, response, and stiffness adjustability. Additionally, the soft actuator significantly improved the maneuverability and bending radius of the endoscope, demonstrating enhanced navigation capabilities in complex environments. Discussion: The shape of a cross-sectional chamber plays a pivotal role in designing soft actuators for MIS applications. Our research emphasizes the importance of this design component, offering key insights for the development of endoscope-supporting soft actuators that can effectively handle intricate actuator-endoscope interactions, thereby enhancing surgical outcomes.
RESUMEN
Various robotic devices have been developed for home rehabilitation and support of therapists. Special attention has been focused on soft actuators due to their high viscoelasticity and flexibility, which can contribute to the safety and affinity with the users. However, most of them aimed at the assist of finger flexion, and few have been designed to support extension actively. Moreover, for most soft actuator based mechanisms, the individual-adaptability have not been considered nor appropriately evaluated. Consequently, the effect of individual difference on the assistance using soft robotic devices is unclear, and for the purpose of dealing with the individual difference, the whole mechanism should be designed and fabricated for each individual user, which is ineffective for the rehabilitation support. In this study, we proposed a hybrid soft mechanism with modularized fiber-reinforced elastomer actuators for joint-dependent flexion support and McKibben actuators for finger extension support. Without further changing the design of the elastomer actuator, the hybrid mechanism could be adapted to individual hand difference: proportions of hand segments, range of motion (ROM) and torque characteristics of the joints. A prototype of the mechanism was fabricated and evaluated. The results showed that the mechanism could meet the requirement of finger function assist. Moreover, the mechanism could be fine-tuned towards the individual hand by changing the fiber-reinforcement and adjusting the fittings of the actuators.