Search

Visual navigation is a key capability for robots and animals. Inspired by the navigational prowess of social insects, a family of insect-inspired route navigation algorithms—familiarity-based algorithms—have been developed that use stored panoramic images collected during a training route to subsequently derive directional information during route recapitulation. However, unlike the ants that inspire them, these algorithms ignore the sequence in which the training images are acquired so that all temporal information/correlation is lost. In this paper, the benefits of incorporating sequence information in familiarity-based algorithms are tested. To do this, instead of comparing a test view to all the training route images, a window of memories is used to restrict the number of comparisons that need to be made. As ants are able to visually navigate when odometric information is removed, the window position is updated via visual matching information only and not odometry. The performance of an algorithm without sequence information is compared to the performance of window methods with different fixed lengths as well as a method that adapts the window size dynamically. All algorithms were benchmarked on a simulation of an environment used for ant navigation experiments and showed that sequence information can boost performance and reduce computation. A detailed analysis of successes and failures highlights the interaction between the length of the route memory sequence and environment type and shows the benefits of an adaptive method. [ABSTRACT FROM AUTHOR]

Abstract Autonomous robotics working in the uncertain environment have drawn increasing interests from researchers. Here, an issue of online motion optimization under unknown environment is considered while preserving the safety and improving the flexible manoeuvrability of robot–environment interaction. This problem is addressed by improving the conventional dynamic movement primitives (DMPs) framework with force tracking constraints. First, an initial motion is learned through the DMPs. At the stage of skill generalization, a temporal coupling term combining with force constraints scheme which is inspired by the barrier Lyapunov function and finite‐time prescribed performance is deduced and adds to the original DMPs, so as to remain the contacting force staying within a predefined limit while aligning the motion along with surface of unknown environment adaptively. In this way, not only the contacting force can be guaranteed within a safe margin, but the shape of generalizing motion is preserved. Then the convergence and stability of the proposed DMPs are proved which is grounded on Laplace transformation‐based stability analysis to ensure the performance and safety. Finally, the proposed method is instantiated combined with conventional PID controller through the compared simulations to verify its effectiveness.

Robotic systems are increasingly present in dynamic environments. This paper proposes a hierarchical control structure wherein a behavior tree (BT) is used to improve the flexibility and adaptability of an omni-directional mobile robot for point stabilization. Flexibility and adaptability are crucial at each level of the sense–plan–act loop to implement robust and effective robotic solutions in dynamic environments. The proposed BT combines high-level decision making and continuous execution monitoring while applying non-linear model predictive control (NMPC) for the point stabilization of an omni-directional mobile robot. The proposed control architecture can guide the mobile robot to any configuration within the workspace while satisfying state constraints (e.g., obstacle avoidance) and input constraints (e.g., motor limits). The effectiveness of the controller was validated through a set of realistic simulation scenarios and experiments in a real environment, where an industrial omni-directional mobile robot performed a point stabilization task with obstacle avoidance in a workspace. [ABSTRACT FROM AUTHOR]

AbstractThere is significant interest in emerging technologies. Universities, companies and other adopters are researching how and when these technologies should be implemented. However, this research area still lacks ways to evaluate the maturity level of the technologies and rapid experimentation concepts for testing the new technologies. This paper addresses the research gap by providing a new evaluation method and a rapid experimentation concept. This method and concept were successfully used in twenty-five Flash-projects, where five emerging digital Industry 4.0 themes evaluated.

Autonomous robotics working in the uncertain environment have drawn increasing interests from researchers. Here, an issue of online motion optimization under unknown environment is considered while preserving the safety and improving the flexible manoeuvrability of robot–environment interaction. This problem is addressed by improving the conventional dynamic movement primitives (DMPs) framework with force tracking constraints. First, an initial motion is learned through the DMPs. At the stage of skill generalization, a temporal coupling term combining with force constraints scheme which is inspired by the barrier Lyapunov function and finite‐time prescribed performance is deduced and adds to the original DMPs, so as to remain the contacting force staying within a predefined limit while aligning the motion along with surface of unknown environment adaptively. In this way, not only the contacting force can be guaranteed within a safe margin, but the shape of generalizing motion is preserved. Then the convergence and stability of the proposed DMPs are proved which is grounded on Laplace transformation‐based stability analysis to ensure the performance and safety. Finally, the proposed method is instantiated combined with conventional PID controller through the compared simulations to verify its effectiveness. [ABSTRACT FROM AUTHOR]

Mapping the environment is a powerful technique for enabling autonomy through localization and planning in robotics. This article seeks to provide a global overview of actionable map construction in robotics, outlining the basic problems, introducing techniques for overcoming them, and directing the reader toward established research covering these problem and solution domains in more detail. Multiple levels of abstraction are covered in a non-exhaustive vertical slice, starting with the fundamental problem of constructing metric occupancy grids with Simultaneous Mapping and Localization techniques. On top of these, topological meshes and semantic maps are reviewed, and a comparison is drawn between multiple representation formats. Furthermore, the datasets and metrics used in performance benchmarks are discussed, as are the challenges faced in some domains that deviate from typical laboratory conditions. Finally, recent advances in robot control without explicit map construction are touched upon. [ABSTRACT FROM AUTHOR]

Recent research and developments in cloud robotics (CR) require appropriate knowledge representation to ensure interoperable data, information, and knowledge sharing within cloud infrastructures. As an important branch of the Internet of Things (IoT), these demands to advance it forward motivates academic and industrial sectors to invest on it. The IEEE 'Ontologies for Robotics and Automation' Working Group (ORA WG) has been developing standard ontologies for different robotic domains, including industrial and autonomous robots. The use of such robotic standards has the potential to benefit the Cloud Robotic Community (CRC) as well, supporting the provision of ubiquitous intelligent services by the CR-based systems. This paper explores this potential by developing an ontological approach for effective information sharing in cloud robotics scenarios. It presents an extension to the existing ontological standards to cater for the CR domain. The use of the new ontological elements is illustrated through its use in a couple of CR case studies. To the best of our knowledge, this is the first work ever that implements an ontology comprising concepts and axioms applicable to the CR domain. [ABSTRACT FROM AUTHOR]

Robotic systems are increasingly present in dynamic environments. This paper proposes a hierarchical control structure wherein a behavior tree (BT) is used to improve the flexibility and adaptability of an omni-directional mobile robot for point stabilization. Flexibility and adaptability are crucial at each level of the sense–plan–act loop to implement robust and effective robotic solutions in dynamic environments. The proposed BT combines high-level decision making and continuous execution monitoring while applying non-linear model predictive control (NMPC) for the point stabilization of an omni-directional mobile robot. The proposed control architecture can guide the mobile robot to any configuration within the workspace while satisfying state constraints (e.g., obstacle avoidance) and input constraints (e.g., motor limits). The effectiveness of the controller was validated through a set of realistic simulation scenarios and experiments in a real environment, where an industrial omni-directional mobile robot performed a point stabilization task with obstacle avoidance in a workspace.

There is significant interest in emerging technologies. Universities, companies and other adopters are researching how and when these technologies should be implemented. However, this research area still lacks ways to evaluate the maturity level of the technologies and rapid experimentation concepts for testing the new technologies. This paper addresses the research gap by providing a new evaluation method and a rapid experimentation concept. This method and concept were successfully used in twenty-five Flash-projects, where five emerging digital Industry 4.0 themes evaluated. [ABSTRACT FROM AUTHOR]

Recent advances in deep learning, including the development of AlexNet, Residual Network (ResNet), and transfer learning, offer unprecedented classification accuracy in the field of machine vision. A developing application of deep learning is the automated identification and management of aquatic invasive plants. Classification of submersed aquatic vegetation (SAV) presents a unique challenge, namely, the lack of a single source of sensor data that can produce robust, interpretable images across a variable range of depth, turbidity, and lighting conditions. This paper focuses on the development of a multi-sensor (RGB and hydroacoustic) classification system for SAV that is robust to environmental conditions and combines the strengths of each sensing modality. The detection of invasive Hydrilla verticillata (hydrilla) is the primary goal. Over 5000 aerial RGB and hydroacoustic images were generated from two Florida lakes via an unmanned aerial vehicle and boat-mounted sonar unit, and tagged for neural network training and evaluation. Classes included "HYDR", containing hydrilla; "NONE", lacking SAV, and "OTHER", containing SAV other than hydrilla. Using a transfer learning approach, deep neural networks with the ResNet architecture were individually trained on the RGB and hydroacoustic datasets. Multiple data fusion methodologies were evaluated to ensemble the outputs of these neural networks for optimal classification accuracy. A method incorporating logic and a Monte Carlo dropout approach yielded the best overall classification accuracy (84%), with recall and precision of 84.5% and 77.5%, respectively, for the hydrilla class. The training and ensembling approaches were repeated for a DenseNet model with identical training and testing datasets. The overall classification accuracy was similar between the ResNet and DenseNet models when averaged across all approaches (1.9% higher accuracy for the ResNet vs. the DenseNet). [ABSTRACT FROM AUTHOR]

A robust and accurate real-time navigation system is crucial for autonomous robotics. In particular, GNSS denied and poor visual conditions are still very challenging as vision based approaches tend to fail in darkness, direct sunlight, fog, or smoke. Therefore, we are taking advantage of inertial data and FMCW radar sensors as both are not affected by such conditions. In this work, we propose a framework, which uses several 4D mmWave radar sensors simultaneously. The extrinsic calibration of each radar sensor is estimated online. Based on a single radar scan, the 3D ego velocity and optionally yaw measurements based on Manhattan world assumptions are fused. An extensive evaluation with real world datasets is presented. We achieve even better accuracies than state of the art stereo Visual Inertial Odometry (VIO) while being able to cope with degraded visual conditions and requiring only very little computational resources. [ABSTRACT FROM AUTHOR]

Goal-directed manipulation of internal representations is a key element of human flexible behaviour, while consciousness is commonly associated with higher-order cognition and human flexibility. Current perspectives have only partially linked these processes, thus preventing a clear understanding of how they jointly generate flexible cognition and behaviour. Moreover, these limitations prevent an effective exploitation of this knowledge for technological scopes. We propose a new theoretical perspective that extends our 'three-component theory of flexible cognition' toward higher-order cognition and consciousness, based on the systematic integration of key concepts from Cognitive Neuroscience and AI/Robotics. The theory proposes that the function of conscious processes is to support the alignment of representations with multi-level goals. This higher alignment leads to more flexible and effective behaviours. We analyse here our previous model of goal-directed flexible cognition (validated with more than 20 human populations) as a starting GARIM-inspired model. By bridging the main theories of consciousness and goal-directed behaviour, the theory has relevant implications for scientific and technological fields. In particular, it contributes to developing new experimental tasks and interpreting clinical evidence. Finally, it indicates directions for improving machine learning and robotics systems and for informing real-world applications (e.g., in digital-twin healthcare and roboethics). • Current frameworks do not integrate goal-directed cognition and consciousness • We introduce a theory that bridges conscious and flexible goal-directed cognition • Consciousness supports representation alignment with goals, thus boosting flexibility • The theory provides data interpretations, neuropsychological tasks, computational models • The theory fosters machine learning, robotics, and real-world applications [ABSTRACT FROM AUTHOR]

Cognition and the cognitive processing of sensory information in biological entities is known to occur over multiple layers of processing. In the example of human vision there are a vast number of photo-receptors feeding into various layers of cells which pre-process the original information before it arrives to the brain (as biased data).We propose to use a mechanism known to theoretical biologists as a means to bring about adaptive selforganization in colonies of social insects, and to apply it to such early stage signal processing. The underlying mathematical model is simple, and in the coming years, robotics will move into an era when aggregating simple computation devices into massively large collectives becomes feasible, making it possible to actually build such distributed cognitive sensing systems.

Visual place recognition (VPR) is the process of recognising a previously visited place using visual information, often under varying appearance conditions and viewpoint changes and with computational constraints. VPR is related to the concepts of localisation, loop closure, image retrieval and is a critical component of many autonomous navigation systems ranging from autonomous vehicles to drones and computer vision systems. While the concept of place recognition has been around for many years, VPR research has grown rapidly as a field over the past decade due to improving camera hardware and its potential for deep learning-based techniques, and has become a widely studied topic in both the computer vision and robotics communities. This growth however has led to fragmentation and a lack of standardisation in the field, especially concerning performance evaluation. Moreover, the notion of viewpoint and illumination invariance of VPR techniques has largely been assessed qualitatively and hence ambiguously in the past. In this paper, we address these gaps through a new comprehensive open-source framework for assessing the performance of VPR techniques, dubbed "VPR-Bench". VPR-Bench (Open-sourced at: https://github.com/MubarizZaffar/VPR-Bench) introduces two much-needed capabilities for VPR researchers: firstly, it contains a benchmark of 12 fully-integrated datasets and 10 VPR techniques, and secondly, it integrates a comprehensive variation-quantified dataset for quantifying viewpoint and illumination invariance. We apply and analyse popular evaluation metrics for VPR from both the computer vision and robotics communities, and discuss how these different metrics complement and/or replace each other, depending upon the underlying applications and system requirements. Our analysis reveals that no universal SOTA VPR technique exists, since: (a) state-of-the-art (SOTA) performance is achieved by 8 out of the 10 techniques on at least one dataset, (b) SOTA technique in one community does not necessarily yield SOTA performance in the other given the differences in datasets and metrics. Furthermore, we identify key open challenges since: (c) all 10 techniques suffer greatly in perceptually-aliased and less-structured environments, (d) all techniques suffer from viewpoint variance where lateral change has less effect than 3D change, and (e) directional illumination change has more adverse effects on matching confidence than uniform illumination change. We also present detailed meta-analyses regarding the roles of varying ground-truths, platforms, application requirements and technique parameters. Finally, VPR-Bench provides a unified implementation to deploy these VPR techniques, metrics and datasets, and is extensible through templates. [ABSTRACT FROM AUTHOR]

The COVID-19 pandemic has emerged as a serious global health crisis, with the predominant morbidity and mortality linked to pulmonary involvement. Point-of-Care ultrasound (POCUS) scanning, becoming one of the primary determinative methods for its diagnosis and staging, requires, however, close contact of healthcare workers with patients, therefore increasing the risk of infection. This work thus proposes an autonomous robotic solution that enables POCUS scanning of COVID-19 patients’ lungs for diagnosis and staging. An algorithm was developed for approximating the optimal position of an ultrasound probe on a patient from prior CT scans to reach predefined lung infiltrates. In the absence of prior CT scans, a deep learning method was developed for predicting 3D landmark positions of a human ribcage given a torso surface model. The landmarks, combined with the surface model, are subsequently used for estimating optimal ultrasound probe position on the patient for imaging infiltrates. These algorithms, combined with a force–displacement profile collection methodology, enabled the system to successfully image all points of interest in a simulated experimental setup with an average accuracy of 20.6 ± 14.7 mm using prior CT scans, and 19.8 ± 16.9 mm using only ribcage landmark estimation. A study on a full torso ultrasound phantom showed that autonomously acquired ultrasound images were 100% interpretable when using force feedback with prior CT and 88% with landmark estimation, compared to 75 and 58% without force feedback, respectively. This demonstrates the preliminary feasibility of the system, and its potential for offering a solution to help mitigate the spread of COVID-19 in vulnerable environments.

Recent advances in deep learning, including the development of AlexNet, Residual Network (ResNet), and transfer learning, offer unprecedented classification accuracy in the field of machine vision. A developing application of deep learning is the automated identification and management of aquatic invasive plants. Classification of submersed aquatic vegetation (SAV) presents a unique challenge, namely, the lack of a single source of sensor data that can produce robust, interpretable images across a variable range of depth, turbidity, and lighting conditions. This paper focuses on the development of a multi-sensor (RGB and hydroacoustic) classification system for SAV that is robust to environmental conditions and combines the strengths of each sensing modality. The detection of invasive Hydrilla verticillata (hydrilla) is the primary goal. Over 5000 aerial RGB and hydroacoustic images were generated from two Florida lakes via an unmanned aerial vehicle and boat-mounted sonar unit, and tagged for neural network training and evaluation. Classes included “HYDR”, containing hydrilla; “NONE”, lacking SAV, and “OTHER”, containing SAV other than hydrilla. Using a transfer learning approach, deep neural networks with the ResNet architecture were individually trained on the RGB and hydroacoustic datasets. Multiple data fusion methodologies were evaluated to ensemble the outputs of these neural networks for optimal classification accuracy. A method incorporating logic and a Monte Carlo dropout approach yielded the best overall classification accuracy (84%), with recall and precision of 84.5% and 77.5%, respectively, for the hydrilla class. The training and ensembling approaches were repeated for a DenseNet model with identical training and testing datasets. The overall classification accuracy was similar between the ResNet and DenseNet models when averaged across all approaches (1.9% higher accuracy for the ResNet vs. the DenseNet).

We consider the problem of autonomous acquisition of manipulation skills where problem-solving strategies are initially available only for a narrow range of situations. We propose to extend the range of solvable situations by autonomous play with the object. By applying previously-trained skills and behaviors, the robot learns how to prepare situations for which a successful strategy is already known. The information gathered during autonomous play is additionally used to train an environment model. This model is exploited for active learning and the generation of novel preparatory behaviors compositions. We apply our approach to a wide range of different manipulation tasks, e.g., book grasping, grasping of objects of different sizes by selecting different grasping strategies, placement on shelves, and tower disassembly. We show that the composite behavior generation mechanism enables the robot to solve previously-unsolvable tasks, e.g., tower disassembly. We use success statistics gained during real-world experiments to simulate the convergence behavior of our system. Simulation experiments show that the learning speed can be improved by around 30% by using active learning.

Using assistive robots for educational applications requires robots to be able to adapt their behavior specifically for each child with whom they interact.Among relevant signals, non-verbal cues such as the child’s gaze can provide the robot with important information about the child’s current engagement in the task, and whether the robot should continue its current behavior or not. Here we propose a reinforcement learning algorithm extended with active state-specific exploration and show its applicability to child engagement maximization as well as more classical tasks such as maze navigation. We first demonstrate its adaptive nature on a continuous maze problem as an enhancement of the classic grid world. There, parameterized actions enable the agent to learn single moves until the end of a corridor, similarly to “options” but without explicit hierarchical representations.We then apply the algorithm to a series of simulated scenarios, such as an extended Tower of Hanoi where the robot should find the appropriate speed of movement for the interacting child, and to a pointing task where the robot should find the child-specific appropriate level of expressivity of action. We show that the algorithm enables to cope with both global and local non-stationarities in the state space while preserving a stable behavior in other stationary portions of the state space. Altogether, these results suggest a promising way to enable robot learning based on non-verbal cues and the high degree of non-stationarities that can occur during interaction with children.

In this paper, we present a way to lead a swarm of robots through four parameters called repulsion, attraction, orientation, and influence, which are inspired by the behavior of biological societies. Considering the kinematics and dynamics of the robots, we made computational simulations to test the swarm performance and to know the impact of parameters for a prey-predator task. The methodology was experimentally tested in a flock of implemented robots, despite hardware and software limitations. We propose the capture time and statistical metrics to quantify the swarm performance. The results of experimental implementations are consistent with computational simulations based on the robot kinematics and dynamics. Cooperation emerges between the predators while trying to catch the prey, and the change of parameters allows governing on the formation and behavior of the swarm in a decentralized way. Some potential applications for this task include protection, rescue, capture, among others. [ABSTRACT FROM AUTHOR]

Autonomous robotic systems are complex, hybrid, and often safety critical; this makes their formal specification and verification uniquely challenging. Though commonly used, testing and simulation alone are insufficient to ensure the correctness of, or provide sufficient evidence for the certification of, autonomous robotics. Formal methods for autonomous robotics have received some attention in the literature, but no resource provides a current overview. This article systematically surveys the state of the art in formal speci- fication and verification for autonomous robotics. Specially, it identifies and categorizes the challenges posed by, the formalisms aimed at, and the formal approaches for the specification and verification of autonomous robotics. [ABSTRACT FROM AUTHOR]

This paper presents a contribution aiming at testing novel child–robot teaching schemes that could be used in future studies to support the development of social and collaborative skills of children with autism spectrum disorders (ASD). We present a novel experiment where the classical roles are reversed: in this scenario the children are the teachers providing positive or negative reinforcement to the Kaspar robot in order for it to learn arbitrary associations between different toy names and the locations where they are positioned. The objective is to stimulate interaction and collaboration between children while teaching the robot, and also provide them tangible examples to understand that sometimes learning requires several repetitions. To facilitate this game, we developed a reinforcement learning algorithm enabling Kaspar to verbally convey its level of uncertainty during the learning process, so as to better inform the children about the reasons behind its successes and failures. Overall, 30 typically developing (TD) children aged between 7 and 8 (19 girls, 11 boys) and 9 children with ASD performed 25 sessions (16 for TD; 9 for ASD) of the experiment in groups, and managed to teach Kaspar all associations in 2 to 7 trials. During the course of study Kaspar only made rare unexpected associations (2 perseverative errors and 2 win-shifts, within a total of 314 trials), primarily due to exploratory choices, and eventually reached minimal uncertainty. Thus, the robot's behaviour was clear and consistent for the children, who all expressed enthusiasm in the experiment. [ABSTRACT FROM AUTHOR]