Toward an idiomatic framework for cognitive robotics.
Ontology highlight
ABSTRACT:
SUBMITTER: Damgaard MR
PROVIDER: S-EPMC9278519 | biostudies-literature | 2022 Jul
REPOSITORIES: biostudies-literature
Publications
Toward an idiomatic framework for cognitive robotics.
Damgaard Malte Rørmose MR Pedersen Rasmus R Bak Thomas T
Patterns (New York, N.Y.) 20220708 7
Inspired by the "cognitive hourglass" model presented by the researchers behind the cognitive architecture called Sigma, we propose a framework for developing cognitive architectures for cognitive robotics. The main purpose of the proposed framework is to ease development of cognitive architectures by encouraging cooperation and re-use of existing results. This is done by proposing a framework dividing development of cognitive architectures into a series of layers that can be considered partly i ...[more]
Similar Datasets
Project description:At present, industrial robotics focuses more on motion control and vision, whereas humanoid service robotics (HSRs) are increasingly being investigated and researched in the field of speech interaction. The problem and quality of human-robot interaction (HRI) has become a widely debated topic in academia. Especially when HSRs are applied in the hospitality industry, some researchers believe that the current HRI model is not well adapted to the complex social environment. HSRs generally lack the ability to accurately recognize human intentions and understand social scenarios. This study proposes a novel interactive framework suitable for HSRs. The proposed framework is grounded on the novel integration of Trevarthen's (2001) companionship theory and neural image captioning (NIC) generation algorithm. By integrating image-to-natural interactivity generation and communicating with the environment to better interact with the stakeholder, thereby changing from interaction to a bionic-companionship. Compared to previous research a novel interactive system is developed based on the bionic-companionship framework. The humanoid service robot was integrated with the system to conduct preliminary tests. The results show that the interactive system based on the bionic-companionship framework can help the service humanoid robot to effectively respond to changes in the interactive environment, for example give different responses to the same character in different scenes.
| S-EPMC8371998 | biostudies-literature
Project description:Physical rehabilitation therapies for children present a challenge, and its success-the improvement of the patient's condition-depends on many factors, such as the patient's attitude and motivation, the correct execution of the exercises prescribed by the specialist or his progressive recovery during the therapy. With the aim to increase the benefits of these therapies, social humanoid robots with a friendly aspect represent a promising tool not only to boost the interaction with the pediatric patient, but also to assist physicians in their work. To achieve both goals, it is essential to monitor in detail the patient's condition, trying to generate user profile models which enhance the feedback with both the system and the specialist. This paper describes how the project NAOTherapist-a robotic architecture for rehabilitation with social robots-has been upgraded in order to include a monitoring system able to generate user profile models through the interaction with the patient, performing user-adapted therapies. Furthermore, the system has been improved by integrating a machine learning algorithm which recognizes the pose adopted by the patient and by adding a clinical reports generation system based on the QUEST metric.
| S-EPMC7506951 | biostudies-literature
Project description:Although advanced robots can adeptly mimic human movement and aesthetics, they are still unable to adapt or evolve in response to external experiences. To address this limitation, we propose an innovative approach that uses parallel-processable retention-engineered synaptic devices in the control system. This approach aims to simulate a human-like learning system without necessitating complex computational systems. The retention properties of the synaptic devices were modulated by adjusting the amount of Ag/AgCl ink sprayed. This changed the voltage drop across the interface between the gate electrode and the electrolyte. Furthermore, the unrestricted movement of ions in the electrolyte enhanced the signal multiplexing capability of the ion gel, enabling device-level parallel processing. By integrating the unique characteristics of the synaptic devices with actuators, we successfully emulated a human-like workout process that includes feedback between acute and chronic responses. The proposed control system offers an innovative approach to reducing system complexity and achieving a human-like learning system in the field of biomimicry.
| S-EPMC11204284 | biostudies-literature
Project description:Evidence from empirical literature suggests that explainable complex behaviors can be built from structured compositions of explainable component behaviors with known properties. Such component behaviors can be built to directly perceive and exploit affordances. Using six examples of recent research in legged robot locomotion, we suggest that robots can be programmed to effectively exploit affordances without developing explicit internal models of them. We use a generative framework to discuss the examples, because it helps us to separate-and thus clarify the relationship between-description of affordance exploitation from description of the internal representations used by the robot in that exploitation. Under this framework, details of the architecture and environment are related to the emergent behavior of the system via a generative explanation. For example, the specific method of information processing a robot uses might be related to the affordance the robot is designed to exploit via a formal analysis of its control policy. By considering the mutuality of the agent-environment system during robot behavior design, roboticists can thus develop robust architectures which implicitly exploit affordances. The manner of this exploitation is made explicit by a well constructed generative explanation.
| S-EPMC7044146 | biostudies-literature
Project description:ObjectiveChemotherapy-related cognitive impairment (CRCI) is a well-known phenomenon among breast cancer survivors. Cognitive impairment among breast cancer survivors can significantly affect their quality of life and ability to function independently. However, there is a lack of specific and focused cognitive intervention to improve their cognitive performances. This study aimed to develop a tailored cognitive intervention framework module by adapting the attention and memory interventions from the Cognitive Rehabilitation Manual of the Brain Injury Interdisciplinary Special Interest Group (BI-SIG) of the American Congress of Rehabilitation Medicine (ACRM) and incorporating them with the relevant exercises for cognitive rehabilitation for Malaysian breast cancer survivors with CRCI based on the consensus agreement of the expert panel.Methods and analysisThe Delphi consensus technique was conducted online to review and evaluate the framework module. A panel of experts, including rehabilitation medicine physicians, occupational therapists, and clinical psychologists in Malaysia, was invited to participate in this study. For each round, the expert consensus was defined as more than 90% of the expert panel agreeing or strongly agreeing with the proposed items.ResultsA total of 33 practitioners completed the three Delphi rounds. 72.7% of the expert panel have been practising in their relevant clinical fields for more than six years (M = 10.67, SD = 5.68). In Round 1, 23% of the experts suggested that the framework module for attention training required further improvements, specifically in the language (M = 1.97, SD = 0.75) and instructions (M = 2.03, SD = 0.71) provided. In Round 2, 15% of the experts recommended additional changes in the instruction (M = 2.15, SD = 0.67) for attention training. Amendments made to the framework module in line with the recommendations provided by the experts resulted in a higher level of consensus, as 94% to 100% of the experts in Round 3 concluded the framework module was suitable and comprehensive for our breast cancer survivors. Following the key results, the objectives were practical, and the proposed approaches, strategies, and techniques for attention and memory training were feasible. The clarity of the instructions, procedures, verbatim transcripts, and timeframe further enhanced the efficacy and utility of the framework module.ConclusionsThis study found out that the cognitive intervention framework module for breast cancer survivors with cognitive impairment following chemotherapy can be successfully developed and feasible to be implemented using Delphi technique.
| S-EPMC9671464 | biostudies-literature
Project description:Four-dimensional (4D) printing has attracted significant attention, because it enables structures to be reconfigured based on an external stimulus, realizing complex architectures that are useful for different applications. Nevertheless, most previously reported 4D-printed components have focused on actuators, which are just one part of a full soft robotic system. In this study, toward achieving fully 4D-printed systems, the design and direct ink writing of sensors with a straining mechanism that mimics the 4D effect are explored. Solution-processable carbon nanotubes (CNTs) were used as the sensing medium, and the effect of a heat-shrinkable shape-memory polymer-based substrate (i.e., potential 4D effect) on the electronic and structural properties of CNTs was assessed, followed by their application in various sensing devices. Herein, we reveal that substrate shrinking affords a more porous yet more conductive film owing to the compressive strain experienced by CNTs, leading to an increase in the carrier concentration. Furthermore, it improves the sensitivity of the devices without the need for chemical functionalization. Interestingly, the results show that, by engineering the potential 4D effect, the selectivity of the sensor can be tuned. Finally, the sensors were integrated into a fully 4D-printed flower structure, exhibiting their potential for different soft robotic applications.
| S-EPMC10976367 | biostudies-literature
Project description:Introduction: Robot-assisted therapy for upper extremity (UE) impairments post-stroke has yielded modest gains in motor capacity and little evidence of improved UE performance during activities of daily living. A paradigm shift that embodies principles of motor learning and exercise dependent neuroplasticity may improve robot therapy outcomes by incorporating active problem solving, salience of trained tasks, and strategies to facilitate the transfer of acquired motor skills to use of the paretic arm and hand during everyday activities. Objective: To pilot and test the feasibility of a novel therapy protocol, the Active Learning Program for Stroke (ALPS), designed to complement repetitive, robot-assisted therapy for the paretic UE. Key ALPS ingredients included training in the use of cognitive strategies (e.g., STOP, THINK, DO, CHECK) and a goal-directed home action plan (HAP) to facilitate UE self-management and skill transfer. Methods: Ten participants with moderate impairments in UE function >6 months after stroke received eighteen 1-h treatment sessions 2-3/x week over 6-8 weeks. In addition to ALPS training, individuals were randomly assigned to either robot-assisted therapy (RT) or robot therapy and task-oriented training (RT-TOT) to trial whether the inclusion of TOT reinforced participants' understanding and implementation of ALPS strategies. Results: Statistically significant group differences were found for the upper limb subtest of the Fugl-Meyer Assessment (FMA-UE) at discharge and one-month follow-up favoring the RT group. Analyses to examine overall effects of the ALPS protocol in addition to RT and RT-TOT showed significant and moderate to large effects on the FMA-UE, Motor Activity Log, Wolf Motor Function Test, and hand portion of the Stroke Impact Scale. Conclusion: The ALPS protocol was the first to extend cognitive strategy training to robot-assisted therapy. The intervention in this development of concept pilot trial was feasible and well-tolerated, with good potential to optimize paretic UE performance following robot-assisted therapy.
| S-EPMC6804158 | biostudies-literature
Project description:PurposeFetoscopic laser photocoagulation of placental anastomoses is the most effective treatment for twin-to-twin transfusion syndrome (TTTS). A robust mosaic of placenta and its vascular network could support surgeons' exploration of the placenta by enlarging the fetoscope field-of-view. In this work, we propose a learning-based framework for field-of-view expansion from intra-operative video frames.MethodsWhile current state of the art for fetoscopic mosaicking builds upon the registration of anatomical landmarks which may not always be visible, our framework relies on learning-based features and keypoints, as well as robust transformer-based image-feature matching, without requiring any anatomical priors. We further address the problem of occlusion recovery and frame relocalization, relying on the computed features and their descriptors.ResultsExperiments were conducted on 10 in-vivo TTTS videos from two different fetal surgery centers. The proposed framework was compared with several state-of-the-art approaches, achieving higher [Formula: see text] on 7 out of 10 videos and a success rate of [Formula: see text] in occlusion recovery.ConclusionThis work introduces a learning-based framework for placental mosaicking with occlusion recovery from intra-operative videos using a keypoint-based strategy and features. The proposed framework can compute the placental panorama and recover even in case of camera tracking loss where other methods fail. The results suggest that the proposed framework has large potential to pave the way to creating a surgical navigation system for TTTS by providing robust field-of-view expansion.
| S-EPMC10632301 | biostudies-literature
Project description:Human decision-making shows systematic simplifications and deviations from the tenets of rationality ('heuristics') that may lead to suboptimal decisional outcomes ('cognitive biases'). There are currently three prevailing theoretical perspectives on the origin of heuristics and cognitive biases: a cognitive-psychological, an ecological and an evolutionary perspective. However, these perspectives are mainly descriptive and none of them provides an overall explanatory framework for the underlying mechanisms of cognitive biases. To enhance our understanding of cognitive heuristics and biases we propose a neural network framework for cognitive biases, which explains why our brain systematically tends to default to heuristic ('Type 1') decision making. We argue that many cognitive biases arise from intrinsic brain mechanisms that are fundamental for the working of biological neural networks. To substantiate our viewpoint, we discern and explain four basic neural network principles: (1) Association, (2) Compatibility, (3) Retainment, and (4) Focus. These principles are inherent to (all) neural networks which were originally optimized to perform concrete biological, perceptual, and motor functions. They form the basis for our inclinations to associate and combine (unrelated) information, to prioritize information that is compatible with our present state (such as knowledge, opinions, and expectations), to retain given information that sometimes could better be ignored, and to focus on dominant information while ignoring relevant information that is not directly activated. The supposed mechanisms are complementary and not mutually exclusive. For different cognitive biases they may all contribute in varying degrees to distortion of information. The present viewpoint not only complements the earlier three viewpoints, but also provides a unifying and binding framework for many cognitive bias phenomena.
| S-EPMC6129743 | biostudies-other
Project description:CRISPR germline editing therapies (CGETs) hold unprecedented potential to eradicate hereditary disorders. However, the prospect of altering the human germline has sparked a debate over the safety, efficacy, and morality of CGETs, triggering a funding moratorium by the NIH. There is an urgent need for practical paths for the evaluation of these capabilities. We propose a model regulatory framework for CGET research, clinical development, and distribution. Our model takes advantage of existing legal and regulatory institutions but adds elevated scrutiny at each stage of CGET development to accommodate the unique technical and ethical challenges posed by germline editing.
| S-EPMC4699477 | biostudies-other