Task Performance Research Articles

Leadership Qualities of the Future Officers as an Innovative Way of Developing Moral Resistance

In today's world, where the situation is constantly escalating and new geopolitical challenges are being created, some leaders-officers possess the quality of leadership and moral stability to perform various tasks and lead their units to victory. The author analyzes the main components of leadership that contribute to the military personnel’s effective training and determines the relationship between leadership qualities and the ability of officers to withstand moral and ethical challenges. It is especially important to pay attention to innovative methods of education that contribute to increasing the personal responsibility and moral stability of future military leaders in modern conditions. It is noted that future officers’ moral stability is a key aspect of the successful performance of tasks in conditions of danger and stress, officers must not only physical training but also a strong moral spirit that allows them to defend their principles and values, independent of complex requirements. Therefore, leadership qualities are one of the key components that contribute to the formation of moral stability of future officers of the Armed Forces of Ukraine and help create a strong foundation for professional development and success in a military career. A researched type of resilience that allows officers to remain strong and determined even in the most difficult situations without compromising their principles and duties. Leadership and moral stability, which are integral aspects of successful professional training of future officers of the Armed Forces of Ukraine, are characterized.

Generative artificial intelligence (GAI): From large language models (LLMs) to multimodal applications towards fine tuning of models, implications, investigations

This research explores the transformative integration of artificial intelligence (AI), robotics, and language models, with a particular emphasis on the PaLM-E model. The exploration aims to assess PaLM-E’s decision-making processes and adaptability across various robotic environments, demonstrating its capacity to convert textual prompts into very precise robotic actions. In addition, the research investigates Parameter-Efficient Fine-Tuning (PEFT) techniques, such as Low-Rank Adaptation (LoRA) and Quantized Low-Rank Adaptation (QLoRA), providing a historical overview of PEFT and highlighting their significance in enhancing task performance while reducing the number of trainable parameters. The broader scope of Generative AI is examined through an analysis of influential models like GPT-3, GPT-4, Copilot, Bard, LLaMA, Stable Diffusion, Midjourney, and DALL-E. These models’ abilities to process natural language prompts and generate a wide range of outputs are thoroughly investigated. The research traces the historical evolution of AI, from its roots in science fiction to its practical applications today, with a focus on the rise of Generative AI in the 21st century. Furthermore, the research delves into the various modalities of Generative AI, covering applications in text, code, images, and more, and assesses their real-world impact on robotics, planning, and business intelligence. The implications of synthetic data generation for business analytics are also explored. The research inspects within both software and hardware landscapes, comparing local deployment on consumer-grade hardware along with cloud-based services, and underscores the benefits of local model deployment in terms of privacy protection, intellectual property security, and censorship resistance. Ethical considerations are central to this research, addressing concerns related to privacy, security, societal impact, biases, and misinformation. The research proposes ethical guidelines for the responsible development and deployment of AI technologies. Ultimately, this work reveals the deep interconnections between vision, language, and robotics, pushing the boundaries of AI capabilities and providing crucial insights for future AI model development and technological innovation. These findings are intended to guide the field through the emerging challenges of the rapidly evolving Generative AI landscape.

Research on Medical Text Parsing Method Based on BiGRU-BiLSTM Multi-Task Learning

With the development of technology, the popularity of online medical treatment is becoming more and more widespread. However, the accuracy and credibility of online medical treatment are affected by model design and semantic understanding. In particular, there are still some problems in the accurate understanding of complex structured texts, which affects the accuracy of judging users’ intentions and needs. Therefore, this paper proposes a new method for medical text parsing, which realizes core tasks such as named entity recognition, intention recognition, and slot filling through a multi-task learning framework; uses BERT to obtain contextual semantic information; and combines BiGRU and BiLSTM neural networks, and uses CRF to realize sequence annotation and DPCNN to realize classification prediction. Thus, the task of entity recognition and intention recognition can be accomplished. On this basis, this paper builds a multi-task learning model based on BiGRU-BiLSTM, and uses CBLUE and CMID databases to verify the method. The verification results show that the accuracy of named entity recognition and intention recognition reaches 86% and 89%, respectively, which improves the performance of various tasks. The ability of the model to process complex text is enhanced. This method can improve the text generalization ability and improve the accuracy of online medical intelligent dialogue when it is used to analyze medical texts.

The Double-Edged Sword of Tension: How Moderate Stress Enhances Performance While Over-Focus Impairs It

Tension, often considered a negative emotional state, has traditionally been viewed as detrimental to performance, particularly when excessive. However, emerging research suggests that tension, when experienced at moderate levels, may have a facilitating effect on task performance by activating physiological and cognitive resources. This study explores the dual effects of tension on behavioral outcomes, proposing that moderate tension improves performance by enhancing arousal and resource mobilization, while excessive focus on tension can lead to cognitive overload, impairing task performance. Two hypotheses are tested: (H1) moderate tension enhances task performance through physiological arousal mechanisms such as increased adrenaline secretion, and (H2) excessive focus on tension increases cognitive load, leading to poorer performance. A randomized experimental design will be employed, with participants assigned to a moderate tension group, an excessive tension focus group, and a control group. Physiological measures, including heart rate and galvanic skin response (GSR), along with task performance indicators, will be collected. The expected results will provide empirical evidence supporting the positive role of moderate tension in enhancing behavioral outcomes and highlight the detrimental effects of excessive tension focus. This study offers theoretical insights into the dual nature of tension and practical implications for managing tension in high-pressure task environments.

The Trail Making Test in Virtual Reality (TMT-VR): The Effects of Interaction Modes and Gaming Skills on Cognitive Performance of Young Adults

Virtual Reality (VR) is increasingly used in neuropsychological assessments due to its ability to simulate real-world environments. This study aimed to develop and evaluate the Trail Making Test in VR (TMT-VR) and investigate the effects of different interaction modes and gaming skills on cognitive performance. A total of 71 young female and male adults (aged 18–35) with high and low gaming skills participated in this study. Participants completed the TMT-VR using three interaction modes as follows: eye-tracking, head movement, and controller. Performance metrics included task completion time and accuracy. User experience, usability, and acceptability of TMT-VR were also examined. Results showed that both eye tracking and head movement modes significantly outperformed the controller in terms of task completion time and accuracy. No significant differences were found between eye tracking and head movement modes. Gaming skills did not significantly influence task performance using any interaction mode. The TMT-VR demonstrates high usability, acceptability, and user experience among participants. The findings suggest that VR-based assessments can effectively measure cognitive performance without being influenced by prior gaming skills, indicating potential applicability for diverse populations.

DP-Poison: Poisoning Federated Learning under the Cover of Differential Privacy

Federated learning (FL) enables resource-constrained node devices to learn a shared model while keeping the training data local. Since recent research has demonstrated multiple privacy leakage attacks in FL, e.g., gradient inference attacks and membership inference attacks, differential privacy (DP) is applied to serve as one of the most effective privacy protection mechanisms. Despite the benefit DP brings, we observe that the introduction of DP also brings random changes to client updates, which will affect the robust aggregation algorithms. We reveal a novel poisoning attack under the cover of DP, named the DP-Poison attack in FL. Specifically, the DP-Poison attack is designed to achieve four goals: 1) maintaining the main task performance; 2) launching a successful attack; 3) escaping the robust aggregation algorithms in FL; and 4) keeping the effectiveness of DP privacy protection. To achieve these goals, we design multiple optimization goals to generate DP noise through a genetic algorithm. The optimization ensures that while the benign updates change randomly, the malicious updates can change towards the global model after adding the DP noise, so that it is easier to be accepted by the robust aggregation algorithms. Extensive experiments show that DP-Poison achieves a nearly 100% attack success rate while maintaining the proposed four goals.

Mind wandering is associated with worsening attentional vigilance.

The tendency for our minds to wander is a pervasive and disruptive influence on continued task performance. Models of sustained attention have implicated mind wandering, moments when attention has turned inwards toward task-unrelated thought, in characteristic patterns of worsening performance with greater time-on-task, known as the vigilance decrement. Despite their theoretical connection, associations between mind wandering and the vigilance decrement have not been investigated systematically. Across two studies (N = 730), we evaluated covariance between within-task change in rates of probe-caught mind wandering and patterns of worsening behavioral task performance that characterize the vigilance decrement. Bivariate growth curve models characterized patterns of intraindividual linear change in mind wandering alongside concomitant changes in task accuracy, response time (RT), and RT variability. Importantly, models assessing the covariance between intraindividual change in mind wandering and behavioral outcome measures confirmed that increases in mind wandering are associated with patterns of worsening behavioral performance with greater time-on-task. In addition, we investigated the role of several moderating factors associated with patterns of within-task change: self-reported task interest and motivation, and individuals' propensity for mind wandering, and mindfulness in their daily lives. These factors moderated either the overall level or rate of within-task change in mind wandering. Our results provide support for models of sustained attention that directly implicate mind wandering in worsening behavioral performance with greater time-on-task in continuous performance tasks requiring sustained attention. (PsycInfo Database Record (c) 2024 APA, all rights reserved).

Coordinating multi-agent reinforcement learning via dual collaborative constraints

Many real-world multi-agent tasks exhibit a nearly decomposable structure, where interactions among agents within the same interaction set are strong while interactions between different sets are relatively weak. Efficiently modeling the nearly decomposable structure and leveraging it to coordinate agents can enhance the learning efficiency of multi-agent reinforcement learning algorithms for cooperative tasks, while existing works typically fail. To overcome this limitation, this paper proposes a novel algorithm named Dual Collaborative Constraints (DCC) that identifies the interaction sets as subtasks and achieves both intra-subtask and inter-subtask coordination. Specifically, DCC employs a bi-level structure to periodically distribute agents into multiple subtasks, and proposes both local and global collaborative constraints based on mutual information to facilitate both intra-subtask and inter-subtask coordination among agents. These two constraints ensure that agents within the same subtask reach a consensus on their local action selections and all of them select superior joint actions that maximize the overall task performance. Experimentally, we evaluate DCC on various cooperative multi-agent tasks, and its superior performance against multiple state-of-the-art baselines demonstrates its effectiveness.

Working memory related functional connectivity in adult ADHD and its amenability to training: A randomized controlled trial

BackgroundWorking memory (WM) deficits are among the most prominent cognitive impairments in attention deficit hyperactivity disorder (ADHD). While functional connectivity is a prevailing approach in brain imaging of ADHD, alterations in WM-related functional brain networks and their malleability by cognitive training are not well known. We examined whole-brain functional connectivity differences between adults with and without ADHD during n-back WM tasks and rest at pretest, as well as the effects of WM training on functional and structural brain connectivity in the ADHD group. MethodsForty-two adults with ADHD and 36 neurotypical controls performed visuospatial and verbal n-back tasks during functional magnetic resonance imaging (fMRI). In addition, seven-minute resting state fMRI data and diffusion-weighted MR images were collected from all participants. The adults with ADHD continued into a 5-week randomized controlled WM training trial (experimental group training on a dual n-back task, n = 21; active control group training on Bejeweled II video game, n = 21), followed by a posttraining MRI. Brain connectivity was examined with Network-Based Statistic. ResultsAt the pretest, adults with ADHD had decreased functional connectivity compared with the neurotypical controls during both n-back tasks in networks encompassing fronto-parietal, temporal, occipital, cerebellar, and subcortical brain regions. Furthermore, WM-related connectivity in widespread networks was associated with performance accuracy in a continuous performance test. Regarding resting state connectivity, no group differences or associations with task performance were observed. WM training did not modulate functional or structural connectivity compared with the active controls. ConclusionOur results indicate large-scale abnormalities in functional brain networks underlying deficits in verbal and visuospatial WM commonly faced in ADHD. Training-induced plasticity in these networks may be limited

Eye of the beholder: A meta-analysis of personality traits' relationships with psychological contract breach and job performance

Psychological contract breach (PCB) is a subjective perception that one's employer has failed to live up to promised obligations. Because PCB is subjective, personality traits should play an important role. However, existing research on the relationships between personality traits and PCB is scattered and explores a variety of subsets of personality traits, with little agreement on which traits are most important to PCB. Thus, we focus on personality traits selected based on insights from a reneging-incongruence framework suggesting that personality traits will be important to the degree that they influence the likelihood that employees are targeted for a “real” PCB (i.e., reneging) or bias their perspective of their PCB (i.e., incongruence). Further, drawing from social exchange theory, we examined PCB as a mechanism by which personality traits relate to job performance. Meta-analytic results indicated that the multiple correlation between personality traits and PCB was R = 0.34, and they continued to account for variance in PCB beyond social exchange quality. Emotional stability and equity sensitivity were the strongest predictors of PCB. Results also demonstrated that PCB mediates the relationships equity sensitivity and emotional stability have with task performance, organizational citizenship behavior, and counterproductive work behavior, even controlling for job satisfaction as an alternative mediator.

Visual Perceptual Confidence: Exploring Discrepancies Between Self-reported and Actual Distance Perception In Virtual Reality.

Virtual Reality (VR) systems are widely used, and it is essential to know if spatial perception in virtual environments (VEs) is similar to reality. Research indicates that users tend to underestimate distances in VR. Prior work suggests that actual distance judgments in VR may not always match the users self-reported preference of where they think they most accurately estimated distances. However, no explicit investigation evaluated whether user preferences match actual performance in a spatial judgment task. We used blind walking to explore potential dissimilarities between actual distance estimates and user-selected preferences of visual complexities, VE conditions, and targets. Our findings show a gap between user preferences and actual performance when visual complexities were varied, which has implications for better visual perception understanding, VR applications design, and research in spatial perception, indicating the need to calibrate and align user preferences and true spatial perception abilities in VR.

Automated Machine Learning in Insurance

Machine Learning (ML) has gained popularity in actuarial research and insurance industrial applications. However, the performance of most ML tasks heavily depends on data preprocessing, model selection, and hyperparameter optimization, which are considered to be intensive in terms of domain knowledge, experience, and manual labor. Automated Machine Learning (AutoML) aims to automatically complete the full life-cycle of ML tasks and provides state-of-the-art ML models without human intervention or supervision. This paper introduces an AutoML workflow that allows users without domain knowledge or prior experience to achieve robust and effortless ML deployment by writing only a few lines of code. This proposed AutoML is specifically tailored for the insurance application, with features like the balancing step in data preprocessing, ensemble pipelines, and customized loss functions. These features are designed to address the unique challenges of the insurance domain, including the imbalanced nature of common insurance datasets. The full code and documentation are available on the GitHub repository.1

Advancements in Data Augmentation and Transfer Learning: A Comprehensive Survey to Address Data Scarcity Challenges

Abstract: Deep Learning (DL) models have demonstrated remarkable proficiency in image classification and recognition tasks, surpassing human capabilities. The observed enhancement in performance can be attributed to the utilization of extensive datasets. Nevertheless, DL models have huge data requirements. Widening the learning capability of such models from limited samples even today remains a challenge, given the intrinsic constraints of small datasets. The trifecta of challenges, encompassing limited labeled datasets, privacy, poor generalization performance, and the costliness of annotations, further compounds the difficulty in achieving robust model performance. Overcoming the challenge of expanding the learning capabilities of Deep Learning models with limited sample sizes remains a pressing concern even today. To address this critical issue, our study conducts a meticulous examination of established methodologies, such as Data Augmentation and Transfer Learning, which offer promising solutions to data scarcity dilemmas. Data Augmentation, a powerful technique, amplifies the size of small datasets through a diverse array of strategies. These encompass geometric transformations, kernel filter manipulations, neural style transfer amalgamation, random erasing, Generative Adversarial Networks, augmentations in feature space, and adversarial and meta- learning training paradigms. : Furthermore, Transfer Learning emerges as a crucial tool, leveraging pre-trained models to facilitate knowledge transfer between models or enabling the retraining of models on analogous datasets. Through our comprehensive investigation, we provide profound insights into how the synergistic application of these two techniques can significantly enhance the performance of classification tasks, effectively magnifying scarce datasets. This augmentation in data availability not only addresses the immediate challenges posed by limited datasets but also unlocks the full potential of working with Big Data in a new era of possibilities in DL applications.

Optogenetic Manipulation of Covert Attention in the Nonhuman Primate.

Optogenetics affords new opportunities to interrogate neuronal circuits that control behavior. In primates, the usefulness of optogenetics in studying cognitive functions remains a challenge. The technique has been successfully wielded, but behavioral effects have been demonstrated primarily for sensorimotor processes. Here, we tested whether brief optogenetic suppression of primate superior colliculus can change performance in a covert attention task, in addition to previously reported optogenetic effects on saccadic eye movements. We used an attention task that required the monkey to detect and report a stimulus change at a cued location via joystick release, while ignoring changes at an uncued location. When the cued location was positioned in the response fields of transduced neurons in the superior colliculus, transient light delivery coincident with the stimulus change disrupted the monkey's detection performance, significantly lowering hit rates. When the cued location was elsewhere, hit rates were unaltered, indicating that the effect was spatially specific and not a motor deficit. Hit rates for trials with only one stimulus were also unaltered, indicating that the effect depended on selection among distractors rather than a low-level visual impairment. Psychophysical analysis revealed that optogenetic suppression increased perceptual threshold, but only for locations matching the transduced site. These data show that optogenetic manipulations can cause brief and spatially specific deficits in covert attention, independent of sensorimotor functions. This dissociation of effect, and the temporal precision provided by the technique, demonstrates the utility of optogenetics in interrogating neuronal circuits that mediate cognitive functions in the primate.

SecKG2vec: A Novel Security Knowledge Graph Relational Reasoning Method based on Semantic and Structural Fusion Embedding

Knowledge graph technology is widely used in network security design, analysis, and detection. By collecting, organizing, and mining various security knowledge, it provides scientific support for security decisions. Some public Security Knowledge Repositories (SKRs) are frequently used to construct security knowledge graphs. The quality of SKRs affects the efficiency and effectiveness of security analysis. However, the current situation is that the identification of relational information among security knowledge elements is not sufficient and timely, and a large number of key relational information is missing. In view of this, we propose a security knowledge graph relational reasoning method, based on the fusion embedding of semantic correlation and structure correlation, named SecKG2vec. By SecKG2vec, the embedded vector simultaneously presents both semantic and structural characteristics, and it can exhibit better relational reasoning performance. In qualitative evaluation and quantitative experiments with baseline methods, SecKG2vec has better performance in relationship reasoning task and entity reasoning task, and potential capability of 0-shot scenario prediction.

Evaluation of ComBat Harmonization for Reducing Across-Tracer Differences in Regional Amyloid PET Analyses.

Differences in amyloid positron emission tomography (PET) radiotracer pharmacokinetics and binding properties lead to discrepancies in amyloid-β uptake estimates. Harmonization of tracer-specific biases is crucial for optimal performance of downstream tasks. Here, we investigated the efficacy of ComBat, a data-driven harmonization model, for reducing tracer-specific biases in regional amyloid PET measurements from [18F]-florbetapir (FBP) and [11C]-Pittsburgh compound-B (PiB). One hundred thirteen head-to-head FBP-PiB scan pairs, scanned from the same subject within 90 days, were selected from the Open Access Series of Imaging Studies 3 (OASIS-3) dataset. The Centiloid scale, ComBat with no covariates, ComBat with biological covariates, and GAM-ComBat with biological covariates were used to harmonize both global and regional amyloid standardized uptake value ratios (SUVR). Variants of ComBat, including longitudinal ComBat and PEACE, were also tested. Intraclass correlation coefficient (ICC) and mean absolute error (MAE) were computed to measure the absolute agreement between tracers. Additionally, longitudinal amyloid SUVRs from an anti-amyloid drug trial were simulated using linear mixed effects modeling. Differences in rates-of-change between simulated treatment and placebo groups were tested, and change in statistical power/Type-I error after harmonization was quantified. In the head-to-head tracer comparison, ComBat with no covariates was the best at increasing ICC and decreasing MAE of both global summary and regional amyloid PET SUVRs between scan pairs of the same group of subjects. In the clinical trial simulation, harmonization with both Centiloid and ComBat increased statistical power of detecting true rate-of-change differences between groups and decreased false discovery rate in the absence of a treatment effect. The greatest benefit of harmonization was observed when groups exhibited differing FBP-to-PiB proportions. ComBat outperformed the Centiloid scale in harmonizing both global and regional amyloid estimates. Additionally, ComBat improved the detection of rate-of-change differences between clinical trial groups. Our findings suggest that ComBat is a viable alternative to Centiloid for harmonizing regional amyloid PET analyses.

Investigating visuo-tactile mirror properties in borderline personality disorder: A TMS-EEG study

ObjectivesPatients with borderline personality disorder (pw-BPD) have decreased levels of cognitive empathy, which may be subtended by mirror-like mechanisms in the somatosensory cortices, i.e., the Tactile Mirror System (TaMS). Here, we aimed to shed light on the TaMS and empathic deficits in pw-BPD focusing on connectivity, using transcranial magnetic stimulation and electroencephalography (TMS-EEG). MethodsAfter study preregistration, we collected self-report measures of empathic abilities, behavioral performance in a visuo-tactile spatial congruency task investigating TaMS activity, and TMS-evoked potentials (TEPs) from 20 pw-BPD and 20 healthy controls. TMS was delivered over the right primary somatosensory cortex (S1) during touch observation and real touch delivery. ResultsPw-BPD reported significantly lower levels of cognitive empathy than controls and made significantly more errors in reporting the side of real touches during touch observation. Moreover, pw-BPD presented an altered connectivity pattern from S1-TEPs during touch perception and touch observation, in the last case without differences between human- and object-directed touches. ConclusionsThe results do not support a specific impairment of TaMS in pw-BPD, but reveal significant behavioral and connectivity alterations within the somatosensory network during touch processing. SignificanceThe present findings temper the proposed role of the TaMS in BPD, while still highlighting the involvement of somatosensory network alterations.

Too much of a good thing: How varying levels of automation impact user performance in a simulated intrusion detection task

Cyber analysts face a demanding task when prioritizing alerts from intrusion detection systems, balancing the challenge of numerous false positives from rule-based methods with the critical need to detect genuine cyber threats, necessitating unwavering vigilance and imposing a significant cognitive burden. In this field, there exists pressure to incorporate artificial intelligence techniques to enhance the automation of analyst workflows, yet without a clear grasp of how elevating the Level of Automation impacts the allocation of attentional and cognitive resources among analysts. This paper describes a simulated AI-assisted intrusion detection task which varies five degrees of automation as well as the sensitivity of the assistant, evaluating performance-based (e.g., accuracy, response time, sensitivity, response bias) and subjective (e.g., surveys on workload and trust) measures. Participants white-listed a series of time-sensitive alerts in a simulated Snort® environment. Our findings indicate that elevating the level of automation altered participants’ behavior, evident in their tendency to display a response bias towards rejecting hits (reduced hit rate and false alarm rate) when overriding an AI’s decision. Additionally, participants subjectively reported experiencing a decreased cognitive workload with a more precise algorithm, irrespective of any variance in their actual performance. Our findings suggest the necessity for additional research before implementing further automation into analyst workflows, as the demands of tasks evolve with escalating levels of automation.

A Feature Fusion Model Based on Temporal Convolutional Network for Automatic Sleep Staging Using Single-Channel EEG.

Sleep staging is a crucial task in sleep monitoring and diagnosis, but clinical sleep staging is both time-consuming and subjective. In this study, we proposed a novel deep learning algorithm named feature fusion temporal convolutional network (FFTCN) for automatic sleep staging using single-channel EEG data. This algorithm employed a one-dimensional convolutional neural network (1D-CNN) to extract temporal features from raw EEG, and a two-dimensional CNN (2D-CNN) to extract time-frequency features from spectrograms generated through continuous wavelet transform (CWT) at the epoch level. These features were subsequently fused and further fed into a temporal convolutional network (TCN) to classify sleep stages at the sequence level. Moreover, a two-step training strategy was used to enhance the model's performance on an imbalanced dataset. Our proposed method exhibits superior performance in the 5-class classification task for healthy subjects, as evaluated on the SHHS-1, Sleep-EDF-153, and ISRUC-S1 datasets. This work provided a straightforward and promising method for improving the accuracy of automatic sleep staging using only single-channel EEG, and the proposed method exhibited great potential for future applications in professional sleep monitoring, which could effectively alleviate the workload of sleep technicians.

Robot Cognitive Learning by Considering Physical Properties

Humans achieve cognitive development through continuous interaction with their environment, enhancing both perception and behavior. However, current robots lack the capacity for human-like action and evolution, posing a bottleneck to improving robotic intelligence. Existing research predominantly models robots as one-way, static mappings from observations to actions, neglecting the dynamic processes of perception and behavior. This paper introduces a novel approach to robot cognitive learning by considering physical properties. We propose a theoretical framework wherein a robot is conceptualized as a three-body physical system comprising a perception-body (P-body), a cognition-body (C-body), and a behavior-body (B-body). Each body engages in physical dynamics and operates within a closed-loop interaction. Significantly, three crucial interactions connect these bodies. The C-body relies on the P-body’s extracted states and reciprocally offers long-term rewards, optimizing the P-body’s perception policy. In addition, the C-body directs the B-body’s actions through sub-goals, and subsequent P-body-derived states facilitate the C-body’s cognition dynamics learning. At last, the B-body would follow the sub-goal generated by the C-body and perform actions conditioned on the perceptive state from the P-body, which leads to the next interactive step. These interactions foster the joint evolution of each body, culminating in optimal design. To validate our approach, we employ a navigation task using a four-legged robot, D’Kitty, equipped with a movable global camera. Navigational prowess demands intricate coordination of sensing, planning, and D’Kitty’s motion. Leveraging our framework yields superior task performance compared with conventional methodologies. In conclusion, this paper establishes a paradigm shift in robot cognitive learning by integrating physical interactions across the P-body, C-body, and B-body, while considering physical properties. Our framework’s successful application to a navigation task underscores its efficacy in enhancing robotic intelligence.