Frontiers in Robotics and AI

RSS Feed for Frontiers in Robotics and AI | New and Recent Articles
Subscribe to Frontiers in Robotics and AI feed

Stroke is a major global issue, affecting millions every year. When a stroke occurs, survivors are often left with physical disabilities or difficulties, frequently marked by abnormal gait. Post-stroke gait normally presents as one of or a combination of unilaterally shortened step length, decreased dorsiflexion during swing phase, and decreased walking speed. These factors lead to an increased chance of falling and an overall decrease in quality of life due to a reduced ability to locomote quickly and safely under one’s own power. Many current rehabilitation techniques fail to show lasting results that suggest the potential for producing permanent changes. As technology has advanced, robot-assisted rehabilitation appears to have a distinct advantage, as the precision and repeatability of such an intervention are not matched by conventional human-administered therapy. The possible role in gait rehabilitation of the Variable Stiffness Treadmill (VST), a unique, robotic treadmill, is further investigated in this paper. The VST is a split-belt treadmill that can reduce the vertical stiffness of one of the belts, while the other belt remains rigid. In this work, we show that the repeated unilateral stiffness perturbations created by this device elicit an aftereffect of increased step length that is seen for over 575 gait cycles with healthy subjects after a single 10-min intervention. These long aftereffects are currently unmatched in the literature according to our knowledge. This step length increase is accompanied by kinematics and muscle activity aftereffects that help explain functional changes and have their own independent value when considering the characteristics of post-stroke gait. These results suggest that repeated unilateral stiffness perturbations could possibly be a useful form of post-stroke gait rehabilitation.

In the current industrial context, the importance of assessing and improving workers' health conditions is widely recognised. Both physical and psycho-social factors contribute to jeopardising the underlying comfort and well-being, boosting the occurrence of diseases and injuries, and affecting their quality of life. Human-robot interaction and collaboration frameworks stand out among the possible solutions to prevent and mitigate workplace risk factors. The increasingly advanced control strategies and planning schemes featured by collaborative robots have the potential to foster fruitful and efficient coordination during the execution of hybrid tasks, by meeting their human counterparts' needs and limits. To this end, a thorough and comprehensive evaluation of an individual's ergonomics, i.e. direct effect of workload on the human psycho-physical status, must be taken into account. In this review article, we provide an overview of the existing ergonomics assessment tools as well as the available monitoring technologies to drive and adapt a collaborative robot's behaviour. Preliminary attempts of ergonomic human-robot collaboration frameworks are presented next, discussing state-of-the-art limitations and challenges. Future trends and promising themes are finally highlighted, aiming to promote safety, health, and equality in worldwide workplaces.

Speech-to-text engines are extremely needed nowadays for different applications, representing an essential enabler in human–robot interaction. Still, some languages suffer from the lack of labeled speech data, especially in the Arabic dialects or any low-resource languages. The need for a self-supervised training process and self-training using noisy training is proven to be one of the up-and-coming feasible solutions. This article proposes an end-to-end, transformers-based model with a framework for low-resource languages. In addition, the framework incorporates customized audio-to-text processing algorithms to achieve a highly efficient Jordanian Arabic dialect speech-to-text system. The proposed framework enables ingesting data from many sources, making the ground truth from external sources possible by speeding up the manual annotation process. The framework allows the training process using noisy student training and self-supervised learning to utilize the unlabeled data in both pre- and post-training stages and incorporate multiple types of data augmentation. The proposed self-training approach outperforms the fine-tuned Wav2Vec model by 5% in terms of word error rate reduction. The outcome of this work provides the research community with a Jordanian-spoken data set along with an end-to-end approach to deal with low-resource languages. This is done by utilizing the power of the pretraining, post-training, and injecting noisy labeled and augmented data with minimal human intervention. It enables the development of new applications in the field of Arabic language speech-to-text area like the question-answering systems and intelligent control systems, and it will add human-like perception and hearing sensors to intelligent robots.

The fifth industrial revolution and the accompanying influences of digitalization are presenting enterprises with significant challenges. Regardless of the trend, however, humans will remain a central resource in future factories and will continue to be required to perform manual tasks. Against the backdrop of, e.g., societal and demographic changes and skills shortage, future-oriented support technologies such as exoskeletons represent a promising opportunity to support workers. Accordingly, the increasing interconnection of human operators, devices, and the environment, especially in human-centered work processes, requires improved human-machine interaction and further qualification of support systems to smart devices. In order to meet these requirements and enable exoskeletons as a future-proof technology, this article presents a framework for the future-oriented qualification of exoskeletons, which reveals potential in terms of user-individual and context-dependent adaptivity of support systems. In this context, a framework has been developed, allowing different support situations to be classified based on elementary functions. Using these support function dependencies and characteristics, it becomes possible to describe adaptive system behavior for human-centered support systems such as exoskeletons as a central aspect. For practical illustration, it is shown for an exemplary active exoskeleton using the example of user-individuality and context-specificity how the support characteristics of exoskeletons in the form of different support characteristics can bring about a purposeful and needs-based application for users and can contribute valuably to design future workplaces.

Dielectric elastomer actuator (DEA) is a smart material that holds promise for soft robotics due to the material’s intrinsic softness, high energy density, fast response, and reversible electromechanical characteristics. Like for most soft robotics materials, additive manufacturing (AM) can significantly benefit DEAs and is mainly applied to the unimorph DEA (UDEA) configuration. While major aspects of UDEA modeling are known, 3D printed UDEAs are subject to specific material and geometrical limitations due to the AM process and require a more thorough analysis of their design and performance. Furthermore, a figure of merit (FOM) is an analytical tool that is frequently used for planar DEA design optimization and material selection but is not yet derived for UDEA. Thus, the objective of the paper is modeling of 3D printed UDEAs, analyzing the effects of their design features on the actuation performance, and deriving FOMs for UDEAs. As a result, the derived analytical model demonstrates dependence of actuation performance on various design parameters typical for 3D printed DEAs, provides a new optimum thickness to Young’s modulus ratio of UDEA layers when designing a 3D printed DEA with fixed dielectric elastomer layer thickness, and serves as a base for UDEAs’ FOMs. The FOMs have various degrees of complexity depending on considered UDEA design features. The model was numerically verified and experimentally validated through the actuation of a 3D printed UDEA. The fabricated and tested UDEA design was optimized geometrically by controlling the thickness of each layer and from the material perspective by mixing commercially available silicones in non-standard ratios for the passive and dielectric layers. Finally, the prepared non-standard mix ratios of the silicones were characterized for their viscosity dynamics during curing at various conditions to investigate the silicones’ manufacturability through AM.

Socio-conversational systems are dialogue systems, including what are sometimes referred to as chatbots, vocal assistants, social robots, and embodied conversational agents, that are capable of interacting with humans in a way that treats both the specifically social nature of the interaction and the content of a task. The aim of this paper is twofold: 1) to uncover some places where the compartmentalized nature of research conducted around socio-conversational systems creates problems for the field as a whole, and 2) to propose a way to overcome this compartmentalization and thus strengthen the capabilities of socio-conversational systems by defining common challenges. Specifically, we examine research carried out by the signal processing, natural language processing and dialogue, machine/deep learning, social/affective computing and social sciences communities. We focus on three major challenges for the development of effective socio-conversational systems, and describe ways to tackle them.

The production of large components currently requires cost-intensive special machine tools with large workspaces. The corresponding process chains are usually sequential and hard to scale. Furthermore, large components are usually manufactured in small batches; consequently, the planning effort has a significant share in the manufacturing costs. This paper presents a novel approach for manufacturing large components by industrial robots and machine tools through segmented manufacturing. This leads to a decoupling of component size and necessary workspace and enables a new type of flexible and scalable manufacturing system. The presented solution is based on the automatic segmentation of the CAD model of the component into segments, which are provided with predefined connection elements. The proposed segmentation strategy divides the part into segments whose structural design is adapted to the capabilities (workspace, axis configuration, etc.) of the field components available on the shopfloor. The capabilities are provided by specific information models containing a self-description. The process planning step of each segment is automated by utilizing the similarity of the segments and the self-description of the corresponding field component. The result is a transformation of a batch size one production into an automated quasi-serial production of the segments. To generate the final component geometry, the individual segments are mounted and joined by robot-guided Direct Energy Deposition. The final surface finish is achieved by post-processing using a mobile machine tool coupled to the component. The entire approach is demonstrated along the process chain for manufacturing a forming tool.

Flapping wing micro aerial vehicles (FWMAVs) are known for their flight agility and maneuverability. These bio-inspired and lightweight flying robots still present limitations in their ability to fly in direct wind and gusts, as their stability is severely compromised in contrast with their biological counterparts. To this end, this work aims at making in-gust flight of flapping wing drones possible using an embodied airflow sensing approach combined with an adaptive control framework at the velocity and position control loops. At first, an extensive experimental campaign is conducted on a real FWMAV to generate a reliable and accurate model of the in-gust flight dynamics, which informs the design of the adaptive position and velocity controllers. With an extended experimental validation, this embodied airflow-sensing approach integrated with the adaptive controller reduces the root-mean-square errors along the wind direction by 25.15% when the drone is subject to frontal wind gusts of alternating speeds up to 2.4 m/s, compared to the case with a standard cascaded PID controller. The proposed sensing and control framework improve flight performance reliably and serve as the basis of future progress in the field of in-gust flight of lightweight FWMAVs.

The use of manipulators in space missions has become popular, as their applications can be extended to various space missions such as on-orbit servicing, assembly, and debris removal. Due to space reachability limitations, such robots must accomplish their tasks in space autonomously and under severe operating conditions such as the occurrence of faults or uncertainties. For robots and manipulators used in space missions, this paper provides a unique, robust control technique based on Model Predictive Path Integral Control (MPPI). The proposed algorithm, named Planner-Estimator MPPI (PE-MPPI), comprises a planner and an estimator. The planner controls a system, while the estimator modifies the system parameters in the case of parameter uncertainties. The performance of the proposed controller is investigated under parameter uncertainties and system component failure in the pre-capture phase of the debris removal mission. Simulation results confirm the superior performance of PE-MPPI against vanilla MPPI.