Feed aggregator

Robotics has gained, in recent years, a significant role in educational processes that take place in formal, non-formal, and informal contexts, mainly in the subjects related to STEM (science, technology, engineering, and mathematics). Indeed, educational robotics (ER) can be fruitfully applied also to soft skills, as it allows promoting social links between students, if it is proposed as a group activity. Working in a group to solve a problem or to accomplish a task in the robotics field allows fostering new relations and overcoming the constraints of the established links associated to the school context. Together with this aspect, ER offers an environment where it is possible to assess group dynamics by means of sociometric tools. In this paper, we will describe an example of how ER can be used to foster and assess social relations in students' group. In particular, we report a study that compares: (1) a laboratory with robots, (2) a laboratory with Scratch for coding, and (3) a control group. This study involved Italian students attending middle school. As the focus of this experiment was to study relations in students' group, we used the sociometric tools proposed by Moreno. Results show that involving students in a robotics lab can effectively foster relations between students and, jointly with sociometric tools, can be employed to portrait group dynamics in a synthetic and manageable way.

Autonomous agents perceive the world through streams of continuous sensori-motor data. Yet, in order to reason and communicate about their environment, agents need to be able to distill meaningful concepts from their raw observations. Most current approaches that bridge between the continuous and symbolic domain are using deep learning techniques. While these approaches often achieve high levels of accuracy, they rely on large amounts of training data, and the resulting models lack transparency, generality, and adaptivity. In this paper, we introduce a novel methodology for grounded concept learning. In a tutor-learner scenario, the method allows an agent to construct a conceptual system in which meaningful concepts are formed by discriminative combinations of prototypical values on human-interpretable feature channels. We evaluate our approach on the CLEVR dataset, using features that are either simulated or extracted using computer vision techniques. Through a range of experiments, we show that our method allows for incremental learning, needs few data points, and that the resulting concepts are general enough to be applied to previously unseen objects and can be combined compositionally. These properties make the approach well-suited to be used in robotic agents as the module that maps from continuous sensory input to grounded, symbolic concepts that can then be used for higher-level reasoning tasks.

It is hypothesized that the nonlinear muscle characteristic of biomechanical systems simplify control in the sense that the information the nervous system has to process is reduced through off-loading computation to the morphological structure. It has been proposed to quantify the required information with an information-entropy based approach, which evaluates the minimally required information to control a desired movement, i.e., control effort. The key idea is to compare the same movement but generated by different actuators, e.g., muscles and torque actuators, and determine which of the two morphologies requires less information to generate the same movement. In this work, for the first time, we apply this measure to numerical simulations of more complex human movements: point-to-point arm movements and walking. These models consider up to 24 control signals rendering the brute force approach of the previous implementation to search for the minimally required information futile. We therefore propose a novel algorithm based on the pattern search approach specifically designed to solve this constraint optimization problem. We apply this algorithm to numerical models, which include Hill-type muscle-tendon actuation as well as ideal torque sources acting directly on the joints. The controller for the point-to-point movements was obtained by deep reinforcement learning for muscle and torque actuators. Walking was controlled by proprioceptive neural feedback in the muscular system and a PD controller in the torque model. Results show that the neuromuscular models consistently require less information to successfully generate the movement than the torque-driven counterparts. These findings were consistent for all investigated controllers in our experiments, implying that this is a system property, not a controller property. The proposed algorithm to determine the control effort is more efficient than other standard optimization techniques and provided as open source.

Falling is among the most damaging event elderly people may experience. With the ever-growing aging population, there is an urgent need for the development of fall detection systems. Thanks to the rapid development of sensor networks and the Internet of Things (IoT), human-computer interaction using sensor fusion has been regarded as an effective method to address the problem of fall detection. In this paper, we provide a literature survey of work conducted on elderly fall detection using sensor networks and IoT. Although there are various existing studies which focus on the fall detection with individual sensors, such as wearable ones and depth cameras, the performance of these systems are still not satisfying as they suffer mostly from high false alarms. Literature shows that fusing the signals of different sensors could result in higher accuracy and lower false alarms, while improving the robustness of such systems. We approach this survey from different perspectives, including data collection, data transmission, sensor fusion, data analysis, security, and privacy. We also review the benchmark data sets available that have been used to quantify the performance of the proposed methods. The survey is meant to provide researchers in the field of elderly fall detection using sensor networks with a summary of progress achieved up to date and to identify areas where further effort would be beneficial.

At present we are witnessing a tremendous interest in Artificial Intelligence (AI), particularly in Deep Learning (DL)/Deep Neural Networks (DNNs). One of the reasons appears to be the unmatched performance achieved by such systems. This has resulted in an enormous hope on such techniques and often these are viewed as all—cure solutions. But most of these systems cannot explain why a particular decision is made (black box) and sometimes miserably fail in cases where other systems would not. Consequently, in critical applications such as healthcare and defense practitioners do not like to trust such systems. Although an AI system is often designed taking inspiration from the brain, there is not much attempt to exploit cues from the brain in true sense. In our opinion, to realize intelligent systems with human like reasoning ability, we need to exploit knowledge from the brain science. Here we discuss a few findings in brain science that may help designing intelligent systems. We explain the relevance of transparency, explainability, learning from a few examples, and the trustworthiness of an AI system. We also discuss a few ways that may help to achieve these attributes in a learning system.

Percutaneous biopsies are popular for extracting suspicious tissue formations (primarily for cancer diagnosis purposes) due to the: relatively low cost, minimal invasiveness, quick procedure times, and low risk for the patient. Despite the advantages provided by percutaneous biopsies, poor needle and tumor visualization is a problem that can result in the clinicians classifying the tumor as benign when it was malignant (false negative). The system developed by the authors aims to address the concern of poor needle and tumor visualization through two virtualization setups. This system is designed to track and visualize the needle and tumor in three-dimensional space using an electromagnetic tracking system. User trials were conducted in which the 10 participants, who were not medically trained, performed a total of 6 tests, each guiding the biopsy needle to the desired location. The users guided the biopsy needle to the desired point on an artificial spherical tumor (diameters of 30, 20, and 10 mm) using the 3D augmented reality (AR) overlay for three trials and a projection on a second monitor (TV) for the other three trials. From the randomized trials, it was found that the participants were able to guide the needle tip 6.5 ± 3.3 mm away from the desired position with an angle deviation of 1.96 ± 1.10° in the AR trials, compared to values of 4.5 ± 2.3 mm and 2.70 ± 1.67° in the TV trials. The results indicate that for simple stationary surgical procedures, an AR display is non-inferior a TV display.

It has been proposed that machine learning techniques can benefit from symbolic representations and reasoning systems. We describe a method in which the two can be combined in a natural and direct way by use of hyperdimensional vectors and hyperdimensional computing. By using hashing neural networks to produce binary vector representations of images, we show how hyperdimensional vectors can be constructed such that vector-symbolic inference arises naturally out of their output. We design the Hyperdimensional Inference Layer (HIL) to facilitate this process and evaluate its performance compared to baseline hashing networks. In addition to this, we show that separate network outputs can directly be fused at the vector symbolic level within HILs to improve performance and robustness of the overall model. Furthermore, to the best of our knowledge, this is the first instance in which meaningful hyperdimensional representations of images are created on real data, while still maintaining hyperdimensionality.

Climbing plants are being increasingly viewed as models for bioinspired growing robots capable of spanning voids and attaching to diverse substrates. We explore the functional traits of the climbing cactus Selenicereus setaceus (Cactaceae) from the Atlantic forest of Brazil and discuss the potential of these traits for robotics applications. The plant is capable of growing through highly unstructured habitats and attaching to variable substrates including soil, leaf litter, tree surfaces, rocks, and fine branches of tree canopies in wind-blown conditions. Stems develop highly variable cross-sectional geometries at different stages of growth. They include cylindrical basal stems, triangular climbing stems and apical star-shaped stems searching for supports. Searcher stems develop relatively rigid properties for a given cross-sectional area and are capable of spanning voids of up to 1 m. Optimization of rigidity in searcher stems provide some potential design ideas for additive engineering technologies where climbing robotic artifacts must limit materials and mass for curbing bending moments and buckling while climbing and searching. A two-step attachment mechanism involves deployment of recurved, multi-angled spines that grapple on to wide ranging surfaces holding the stem in place for more solid attachment via root growth from the stem. The cactus is an instructive example of how light mass searchers with a winged profile and two step attachment strategies can facilitate traversing voids and making reliable attachment to a wide range of supports and surfaces.

In this paper, we present a novel pipeline to simultaneously estimate and manipulate the deformation of an object using only force sensing and an FEM model. The pipeline is composed of a sensor model, a deformation model and a pose controller. The sensor model computes the contact forces that are used as input to the deformation model which updates the volumetric mesh of a manipulated object. The controller then deforms the object such that a given pose on the mesh reaches a desired pose. The proposed approach is thoroughly evaluated in real experiments using a robot manipulator and a force-torque sensor to show its accuracy in estimating and manipulating deformations without the use of vision sensors.

In this paper, we present a modular and flexible state estimation framework for legged robots operating in real-world scenarios, where environmental conditions, such as occlusions, low light, rough terrain, and dynamic obstacles can severely impair estimation performance. At the core of the proposed estimation system, called Pronto, is an Extended Kalman Filter (EKF) that fuses IMU and Leg Odometry sensing for pose and velocity estimation. We also show how Pronto can integrate pose corrections from visual and LIDAR and odometry to correct pose drift in a loosely coupled manner. This allows it to have a real-time proprioceptive estimation thread running at high frequency (250–1,000 Hz) for use in the control loop while taking advantage of occasional (and often delayed) low frequency (1–15 Hz) updates from exteroceptive sources, such as cameras and LIDARs. To demonstrate the robustness and versatility of the approach, we have tested it on a variety of legged platforms, including two humanoid robots (the Boston Dynamics Atlas and NASA Valkyrie) and two dynamic quadruped robots (IIT HyQ and ANYbotics ANYmal) for more than 2 h of total runtime and 1.37 km of distance traveled. The tests were conducted in a number of different field scenarios under the conditions described above. The algorithms presented in this paper are made available to the research community as open-source ROS packages.

Producing feasible motions for highly redundant robots, such as humanoids, is a complicated and high-dimensional problem. Model-based whole-body control of such robots can generate complex dynamic behaviors through the simultaneous execution of multiple tasks. Unfortunately, tasks are generally planned without close consideration for the underlying controller being used, or the other tasks being executed, and are often infeasible when executed on the robot. Consequently, there is no guarantee that the motion will be accomplished. In this work, we develop a proof-of-concept optimization loop which automatically improves task feasibility using model-free policy search in conjunction with model-based whole-body control. This combination allows problems to be solved, which would be otherwise intractable using simply one or the other. Through experiments on both the simulated and real iCub humanoid robot, we show that by optimizing task feasibility, initially infeasible complex dynamic motions can be realized—specifically, a sit-to-stand transition. These experiments can be viewed in the accompanying Video S1.

Robots that are designed to work in close proximity to humans are required to move and act in a way that ensures social acceptance by their users. Hence, a robot's proximal behavior toward a human is a main concern, especially in human-robot interaction that relies on relatively close proximity. This study investigated how the distance and lateral offset of “Follow Me” robots influences how they are perceived by humans. To this end, a Follow Me robot was built and tested in a user study for a number of subjective variables. A total of 18 participants interacted with the robot, with the robot's lateral offset and distance varied in a within-subject design. After each interaction, participants were asked to rate the movement of the robot on the dimensions of comfort, expectancy conformity, human likeness, safety, trust, and unobtrusiveness. Results show that users generally prefer robot following distances in the social space, without a lateral offset. However, we found a main influence of affinity for technology, as those participants with a high affinity for technology preferred closer following distances than participants with low affinity for technology. The results of this study show the importance of user-adaptiveness in human-robot-interaction.

Point cloud data provides three-dimensional (3D) measurement of the geometric details in the physical world, which relies heavily on the quality of the machine vision system. In this paper, we explore the potentials of a 3D scanner of high quality (15 million points per second), accuracy (up to 0.150 mm), and frame rate (up to 20 FPS) during static and dynamic measurements of the robot flange for direct hand-eye calibration and trajectory error tracking. With the availability of high-quality point cloud data, we can exploit the standardized geometric features on the robot flange for 3D measurement, which are directly accessible for hand-eye calibration problems. In the meanwhile, we tested the proposed flange-based calibration methods in a dynamic setting to capture point cloud data in a high frame rate. We found that our proposed method works robustly even in dynamic environments, enabling a versatile hand-eye calibration during motion. Furthermore, capturing high-quality point cloud data in real-time opens new doors for the use of 3D scanners, capable of detecting sensitive anomalies of refined details even in motion trajectories. Codes and sample data of this calibration method is provided at Github (https://github.com/ancorasir/flange_handeye_calibration).

Programming by demonstration has received much attention as it offers a general framework which allows robots to efficiently acquire novel motor skills from a human teacher. While traditional imitation learning that only focuses on either Cartesian or joint space might become inappropriate in situations where both spaces are equally important (e.g., writing or striking task), hybrid imitation learning of skills in both Cartesian and joint spaces simultaneously has been studied recently. However, an important issue which often arises in dynamical or unstructured environments is overlooked, namely how can a robot avoid obstacles? In this paper, we aim to address the problem of avoiding obstacles in the context of hybrid imitation learning. Specifically, we propose to tackle three subproblems: (i) designing a proper potential field so as to bypass obstacles, (ii) guaranteeing joint limits are respected when adjusting trajectories in the process of avoiding obstacles, and (iii) determining proper control commands for robots such that potential human-robot interaction is safe. By solving the aforementioned subproblems, the robot is capable of generalizing observed skills to new situations featuring obstacles in a feasible and safe manner. The effectiveness of the proposed method is validated through a toy example as well as a real transportation experiment on the iCub humanoid robot.

The article describes a highly trustable environmental monitoring system employing a small scalable swarm of small-sized marine vessels equipped with compact sensors and intended for the monitoring of water resources and infrastructures. The technological foundation of the process which guarantees that any third party can not alter the samples taken by the robot swarm is based on the Robonomics platform. This platform provides encrypted decentralized technologies based on distributed ledger tools, and market mechanisms for organizing the work of heterogeneous multi-vendor cyber-physical systems when automated economical transactions are needed. A small swarm of robots follows the autonomous ship, which is in charge of maintaining the secure transactions. The swarm implements a version of Reynolds' Boids model based on the Belief Space Planning approach. The main contributions of our work consist of: (1) the deployment of a secure sample certification and logging platform based on the blockchain with a small-sized swarm of autonomous vessels performing maneuvers to measure chemical parameters of water in automatic mode; (2) the coordination of a leader-follower framework for the small platoon of robots by means of a Reynolds' Boids model based on a Belief Space Planning approach. In addition, the article describes the process of measuring the chemical parameters of water by using sensors located on the vessels. Both technology testing on experimental vessel and environmental measurements are detailed. The results have been obtained through real world experiments of an autonomous vessel, which was integrated as the “leader” into a mixed reality simulation of a swarm of simulated smaller vessels.The design of the experimental vessel physically deployed in the Volga river to demonstrate the practical viability of the proposed methods is shortly described.

We consider the detection of change in spatial distribution of fluorescent markers inside cells imaged by single cell microscopy. Such problems are important in bioimaging since the density of these markers can reflect the healthy or pathological state of cells, the spatial organization of DNA, or cell cycle stage. With the new super-resolved microscopes and associated microfluidic devices, bio-markers can be detected in single cells individually or collectively as a texture depending on the quality of the microscope impulse response. In this work, we propose, via numerical simulations, to address detection of changes in spatial density or in spatial clustering with an individual (pointillist) or collective (textural) approach by comparing their performances according to the size of the impulse response of the microscope. Pointillist approaches show good performances for small impulse response sizes only, while all textural approaches are found to overcome pointillist approaches with small as well as with large impulse response sizes. These results are validated with real fluorescence microscopy images with conventional resolution. This, a priori non-intuitive result in the perspective of the quest of super-resolution, demonstrates that, for difference detection tasks in single cell microscopy, super-resolved microscopes may not be mandatory and that lower cost, sub-resolved, microscopes can be sufficient.

Recognizing material categories is one of the core challenges in robotic nuclear waste decommissioning. All nuclear waste should be sorted and segregated according to its materials, and then different disposal post-process can be applied. In this paper, we propose a novel transfer learning approach to learn boundary-aware material segmentation from a meta-dataset and weakly annotated data. The proposed method is data-efficient, leveraging a publically available dataset for general computer vision tasks and coarsely labeled material recognition data, with only a limited number of fine pixel-wise annotations required. Importantly, our approach is integrated with a Simultaneous Localization and Mapping (SLAM) system to fuse the per-frame understanding delicately into a 3D global semantic map to facilitate robot manipulation in self-occluded object heaps or robot navigation in disaster zones. We evaluate the proposed method on the Materials in Context dataset over 23 categories and that our integrated system delivers quasi-real-time 3D semantic mapping with high-resolution images. The trained model is also verified in an industrial environment as part of the EU RoMaNs project, and promising qualitative results are presented. A video demo and the newly generated data can be found at the project website1 (Supplementary Material).

Consensus achievement is a crucial capability for robot swarms, for example, for path selection, spatial aggregation, or collective sensing. However, the presence of malfunctioning and malicious robots (Byzantine robots) can make it impossible to achieve consensus using classical consensus protocols. In this work, we show how a swarm of robots can achieve consensus even in the presence of Byzantine robots by exploiting blockchain technology. Bitcoin and later blockchain frameworks, such as Ethereum, have revolutionized financial transactions. These frameworks are based on decentralized databases (blockchains) that can achieve secure consensus in peer-to-peer networks. We illustrate our approach in a collective sensing scenario where robots in a swarm are controlled via blockchain-based smart contracts (decentralized protocols executed via blockchain technology) that serve as “meta-controllers” and we compare it to state-of-the-art consensus protocols using a robot swarm simulator. Additionally, we show that our blockchain-based approach can prevent attacks where robots forge a large number of identities (Sybil attacks). The developed robot-blockchain interface is released as open-source software in order to facilitate future research in blockchain-controlled robot swarms. Besides increasing security, we expect the presented approach to be important for data analysis, digital forensics, and robot-to-robot financial transactions in robot swarms.