Complex Tasks In Environments Research Articles

Multi UAV Cooperative Reconnaissance based on Dynamic Programming VDN Algorithm

This paper proposes a multi agent value decomposition network (VDN) based multi UAV collaborative reconnaissance and control method to address the issue of insufficient strategies for multi UAV collaborative reconnaissance and control. By designing corresponding algorithm networks and training processes, the goal of autonomy, collaboration, and intelligence among multiple unmanned aerial vehicle systems has been achieved, assisting unmanned aerial vehicle combat forces in achieving collaborative operations and decision-making. This article uses AirSim as the simulation verification environment to verify the effectiveness of the proposed algorithm. The experimental results show that the algorithm proposed in this paper can achieve multi UAV collaborative reconnaissance tasks in complex environments, providing an intelligent solution for UAV collaborative control.

PAS-GAN: A GAN based on the Pyramid Across-Scale module for visible-infrared image transformation

With the rapid development of computer vision, there is a recent trend for intelligent image understanding based on deep learning. RGB images and infrared images have complementary information in image capture tasks in complex environments due to their different imaging modalities. Therefore, the combination of the two plays an important role in improving video surveillance and target detection capabilities. However, large publicly available infrared image datasets are lacking and acquiring infrared images can be resource-intensive. The lack of samples can lead to a breakdown in the training of deep models. In this paper, to overcome this challenge, we construct a GAN-based visible-infrared image transformation model. The model uses existing visible data to generate infrared images by training an end-to-end generative network. We innovatively propose a lightweight PAS feature extraction module applied to the generator. It enriches the image detail representation of the feature domain from multiple dimensions and greatly improves the model feature representation capability. And the image gradient calculation is used to limit the direction of model optimization. We evaluated our model on three different publicly available datasets, evaluating the quality of the generated images in terms of both visual effects and objective numerical assessments. The experimental results show that the network exhibits excellent results in both qualitative and quantitative evaluation compared to the current state-of-the-art image generation methods. The lightweight feature extraction module also gives PAS-GAN a significant advantage in inference speed.

Soft Polymer Optical Fiber Sensors for Intelligent Recognition of Elastomer Deformations and Wearable Applications.

In recent years, soft robotic sensors have rapidly advanced to endow robots with the ability to interact with the external environment. Here, we propose a polymer optical fiber (POF) sensor with sensitive and stable detection performance for strain, bending, twisting, and pressing. Thus, we can map the real-time output light intensity of POF sensors to the spatial morphology of the elastomer. By leveraging the intrinsic correlations of neighboring sensors and machine learning algorithms, we realize the spatially resolved detection of the pressing and multi-dimensional deformation of elastomers. Specifically, the developed intelligent sensing system can effectively recognize the two-dimensional indentation position with a prediction accuracy as large as ~99.17%. The average prediction accuracy of combined strain and twist is ~98.4% using the random forest algorithm. In addition, we demonstrate an integrated intelligent glove for the recognition of hand gestures with a high recognition accuracy of 99.38%. Our work holds promise for applications in soft robots for interactive tasks in complex environments, providing robots with multidimensional proprioceptive perception. And it also can be applied in smart wearable sensing, human prosthetics, and human-machine interaction interfaces.

APPA-3D: an autonomous 3D path planning algorithm for UAVs in unknown complex environments

Due to their high flexibility, low cost, and ease of handling, Unmanned Aerial Vehicles (UAVs) are often used to perform difficult tasks in complex environments. Stable and reliable path planning capability is the fundamental demand for UAVs to accomplish their flight tasks. Most researches on UAV path planning are carried out under the premise of known environmental information, and it is difficult to safely reach the target position in the face of unknown environment. Thus, an autonomous collision-free path planning algorithm for UAVs in unknown complex environments (APPA-3D) is proposed. An anti-collision control strategy is designed using the UAV collision safety envelope, which relies on the UAV's environmental awareness capability to continuously interact with external environmental information. A dynamic reward function of reinforcement learning combined with the actual flight environment is designed and an optimized reinforcement learning action exploration strategy based on the action selection probability is proposed. Then, an improved RL algorithm is used to simulate the UAV flight process in unknown environment, and the algorithm is trained by interacting with the environment, which finally realizes autonomous collision-free path planning for UAVs. The comparative experimental results in the same environment show that APPA-3D can effectively guide the UAV to plan a safe and collision-free path from the starting point to the target point in an unknown complex 3D environment.

Detection model based on improved faster-RCNN in apple orchard environment

Apple detection in complex orchard environments holds significant research importance for yield estimation. Although convolutional neural networks have been widely used in the field of object detection, they also have certain limitations. One of the major drawbacks is their inductive biases of locality and scale invariance, which often pose challenges in capturing global and long-term dependencies. In this work, we replace the backbone network with a moving window transformer based on Faster RCNN, fusing features from different stages and introducing an enhanced smoothing loss function called Faster RFormer. We created an apple detection dataset called AD-2023 to validate the reliability of the model. The results indicate that the proposed method in this paper achieved impressive results with 0.692 mAP, 0.796 AP@0.75 and 0.941 AP@0.5, surpassing existing algorithms. More importantly, our study not only provides a reliable idea for the inadequacy of convolutional neural networks for detection tasks in complex environments, but also establishes a new benchmark in apple detection methodologies, showcasing the potential for broader applications in agricultural automation and robotics.

Social Network Evolution of Multiagent Groups in Task Allocation

The social network and group structure can improve the effectiveness of tasks and the management of multiagent systems (MASs). However, in complex task environments, the fixed network and social relation are not necessarily the optimal design. Therefore, agents should be able to adjust social relations in a distributed and self-organized manner to adapt to different task demands. To solve this problem, a hybrid social evolution mechanism based on Q-learning is proposed in this article. The evolution of social relations is realized from the perspective of individual, group, and global situations to improve the success rate and comprehensive effectiveness of task allocation in the system while reducing the communication cost during task execution. In addition, the hybrid evolution mechanism considers the balance of interests between the global and the individual, which can guarantee the rationality of task benefit distribution while improving the global effectiveness. The experiments show that compared with the single-form evolution method, the hybrid mechanism proposed in this article has more advantages in the success rate, communication cost, and comprehensive effectiveness of task allocation. Moreover, the rationality of benefit distribution is also improved, and a strong and harmonious social system is realized.

ISA: Ingenious Siamese Attention for object detection algorithms towards complex scenes

The interference of complex environments on object detection tasks dramatically limits the application of object detection algorithms. Improving the detection accuracy of the object detection algorithms is able to effectively enhance the stability and reliability of the object detection algorithm-based tasks in complex environments. In order to ameliorate the detection accuracy of object detection algorithms under various complex environment transformations, this work proposes the Siamese Attention YOLO (SAYOLO) object detection algorithm based on ingenious siamese attention structure. The ingenious siamese attention structure includes three aspects: Attention Neck YOLOv4 (ANYOLOv4), siamese neural network structure and special designed network scoring module. In the Complex Mini VOC dataset, the detection accuracy of SAYOLO algorithm is 12.31%, 48.93%, 17.80%, 10.12%, 18.79% and 1.12% higher than Faster-RCNN (Resnet50), SSD (Mobilenetv2), YOLOv3, YOLOv4, YOLOv5-l and YOLOX-x, respectively. Compared with traditional object detection algorithms based on image preprocessing, the detection accuracy of SAYOLO is 4.88%, 11.51%, 1.73%, 23.27%, 18.12%, and 5.76% higher than Image-Adaptive YOLO, MSBDN-DFF + YOLOv4, Dark Channel Prior + YOLOv4, Zero-DCE + YOLOv4, MSBDN-DFF + Zero-DCE + YOLOv4, and Dark Channel Prior + Zero-DCE + YOLOv4, respectively.

How do Blame Attributions Impact Trust in Complex Task Environments?

Trust in automation is a multidimensional process in predicting the proper use of automated systems. Trust can be generalized across components in multi-component systems, leading to contagion effects. However, no research has considered how blame attributions influence the size of contagion effects. We conducted an experiment to address how attributions of blame and responsibility influenced the magnitude of contagion effects for trust. Participants were presented with a hypothetical scenario depicting an airplane environment consisting of six human and six automation components. Participants rated their trust in each component before and after an oxygen mask failure. The findings indicate that the percentage of blame attributed to a component predicted the degree to that trust decreased following an error. Thus, more research should focus on how users assign blame across systems.

YOLOv5-OCDS: An Improved Garbage Detection Model Based on YOLOv5

As the global population grows and urbanization accelerates, the garbage that is generated continues to increase. This waste causes serious pollution to the ecological environment, affecting the stability of the global environmental balance. Garbage detection technology can quickly and accurately identify, classify, and locate many kinds of garbage to realize the automatic disposal and efficient recycling of waste, and it can also promote the development of a circular economy. However, the existing garbage detection technology has some problems, such as low precision and a poor detection effect in complex environments. Although YOLOv5 has achieved good results in garbage detection, the detection results cannot meet the requirements in complex scenarios, so this paper proposes a garbage detection model, YOLOv5-OCDS, based on an improved YOLOv5. Replacing the partial convolution in the neck with Omni-Dimensional Dynamic Convolution (ODConv) improves the expressiveness of the model. The C3DCN structure is constructed, and parts of the C3 structures in the neck are replaced by C3DCN structures, allowing the model to better adapt to object deformation and target scale change. The decoupled head is used for classification and regression tasks so that the model can learn each class’s characteristics and positioning information more intently, and flexibility and extensibility can be improved. The Soft Non-Maximum Suppression (Soft NMS) algorithm can better retain the target’s information and effectively avoid the problem of repeated detection. The self-built garbage classification dataset is used for related experiments, and the mAP@50 of the YOLOv5-OCDS model is 5.3% higher than that of the YOLOv5s; the value of mAP@50:95 increases by 12.3%. In the experimental environment of this study, the model’s Frames Per Second (FPS) was 61.7 f/s. In practical applications, when we use some old GPU, such as the GTX1060, it can still reach 50.3 f/s, so that real-time detection can be achieved. Thus, the improved model suits garbage detection tasks in complex environments.

A novel multimodal multi-objective optimization algorithm for multi-robot task allocation

Multi-robot task allocation (MRTA) is widely used in various fields and plays an important role in some complex task environments due to its ability to distribute parallel processing tasks. However, the multi-robot cooperative system is susceptible to actual environments or preferences of decision-makers. Therefore, providing enough solutions/schemes in the MRTA is important. To improve the reliability and feasibility of obtained solution set, an improved multimodal multi-objective differential evolution algorithm hybrid with a simulated annealing algorithm (IMMODE-SA) is proposed to solve MRTA problems in this study. In the proposed IMMODE-SA, a novel population initialization method is used to improve the population quality, and a redundant solution deletion method is employed to delete redundant solutions during the search process. Moreover, a simulated annealing algorithm is utilized to improve the exploitation capability in the last generation of evolutionary process. To verify the performance of the proposed algorithm, extensive simulation experiments are conducted on three MRTA instances. Experimental results show that the proposed algorithm performs better than other competitors on MRTA instances in terms of Hypervolume (HV). Also, the validity of the proposed algorithm is demonstrated via three experiments and experimental analysis results indicate that the IMMODE-SA can provide more equivalent optimal schemes to decision makers. Finally, it is crucial to solve MRTA problems with time window constraints.

AUV 3D docking control using deep reinforcement learning

Autonomous docking can enable AUV to have long endurance, so it is necessary to consider the issue of robust docking control under current and wave disturbances. In this work, based on the proximal policy optimization (PPO) algorithm, we developed a model-free docking controller to complete three-dimensional docking tasks under disturbances. To improve the performance of PPO, two mechanisms are proposed, including adaptive rollback clipping and self-generated demonstration replay. A simulation environment is constructed, including fuzzy hydrodynamic parameters, ocean current and wave disturbance model. Simulation results demonstrate that our proposed method has faster learning speed, higher robustness, and can control AUV to achieve 3D docking tasks in complex environments with a high success rate.

Real-time planning and collision avoidance control method based on deep reinforcement learning

Real time planning and collision avoidance is an important part of the motion planning for USVs, its core is to design effective planning and collision avoidance methods. This paper proposes a real-time planning and collision avoidance method based on deep reinforcement learning for USVs in complex environments. Firstly, a novel reward function is designed, which transforms the collision avoidance problem into a deep reinforcement learning strategy solution problem that includes distance, direction, speed, and GOLREGs constraints, it ensures the smooth and safe operation of the USV. Secondly, inefficient exploration and exploitation methods make it difficult for intelligent agents to discover key information in the environment, high value experience is obtained through the designed layered sampling exploration mechanism in this article, the intelligent agent learns effective control strategies through this mechanism, which accelerates the convergence of the strategies and reduces the waste of computing resources. Finally, a real-time collision avoidance simulation platform for the USV is established, and experimental results of different exploration mechanisms are compared, the efficiency of the layered sampling exploration mechanism has been verified. The simulation scenarios from easy to difficult are designed, and the results indicate that the USV can complete real-time planning and collision avoidance tasks in complex environments.

Multi-UAV Aerial Mission Intelligent Assignment Algorithm Based on LightGBM Model

Abstract With the development of UAV technology, UAVs have the advantages of convenience, speed, and small size. However, when faced with a complex task environment, some traditional artificial intelligence algorithms will significantly increase computation time, and the algorithms that perform better in time performance often fail to adapt to the type and number of random tasks to be assigned. In this paper, we combine the Hungarian algorithm with improving the LightGBM model, simulate the implementation in various task scenarios, and verify that the improved LightGBM model completes the intelligent assignment of multiple UAVs without increasing time cost compared to the classical algorithm through comparative analysis. It is shown that the improved LightGBM model has an average time of 26.39s for 10 runs, which is higher than 16.91s for NSGA-II and 14.73s for PESA, but lower than 46.92s for SPEA2 and 50.01s for SPGA2. For a non-real-time assignment system, a better mission intelligence assignment at a certain time cost scheme is more in line with the system’s performance requirements. Therefore, the improved LightGBM model in this paper can obtain better solutions than the other four algorithms in solving the multi-objective multi-UAV task intelligence assignment problem, and the solution set coverage is larger than several other algorithms. This indicates that the algorithm studied in this paper is feasible in solving the multi-objective multi-UAV task intelligence assignment problem, and it also has some reference significance for solving the multi-objective problem and improving the coverage of the multi-objective solution set.

Humble leadership and project success: underpinning service-oriented organizational citizenship behavior and task complexity

PurposeThe aim of the study is to investigate the relationship between humble leadership, project success, and service-oriented organizational citizenship behavior (OCB) and how task complexity may moderate this relationship. The study aims to determine if humble leaders are more likely to promote service-oriented OCB among team members and if this behavior in turn leads to greater project success, especially in complex task environments. These relationships are examined through the lens of the conservation of resources theory.Design/methodology/approachThe data were collected from the employees working in software companies using a closed-ended questionnaire, and a total of 214 complete questionnaires were analyzed. The research model was tested using structural equation modeling with the help of Smart PLS 3 software.FindingsHumble leadership is positively associated with service-oriented organizational citizenship behavior (OCB), which in turn is linked to project success. Task complexity does not appear to have a significant impact on this relationship.Practical implicationsHumble leadership is positively related to IT project success through its influence on service-oriented organizational citizenship behavior and task complexity. Implications include the importance of fostering a humble leadership style to enhance IT project success, as well as the potential benefits of promoting service-oriented behavior among employees. It also highlights the need to consider task complexity when evaluating project success.Originality/valueThe research explores the relationship between “humble leadership” and project success, and how it relates to “service-oriented organizational citizenship behavior” and “task complexity”. It presents an original perspective on the role of leadership in project success and the impact of organizational culture on project outcomes through the lens of the conservation of resources theory.

A worm-snake-inspired metameric robot for multi-modal locomotion: Design, modeling, and unified gait control

Worm-like and snake-like robots have attracted a great deal of research attention due to their slender bodies and excellent mobility. Based on different locomotion mechanisms, worm-like robots are more suited for movement in restricted environments, while snake-like robots excel in fast movements in open spaces but have limited mobility in confined areas. To complement their advantages, this paper presents a new design and prototype of a Worm-Snake-Inspired Metameric (WSIM) robot with multi-modal locomotion capability, which can execute peristaltic planar locomotion by exploiting the contracting of the worm-like modules and serpentine planar locomotion via active swing of the snake-like joints. We also propose a unified gait control framework that unifies the gait signals of worm-like and snake-like locomotion modes by using the parameter vector, and the conditions that need to be satisfied by the control parameters for generating different gaits are derived. This study also takes a major step forward in establishing dynamic models for the worm-like and snake-like locomotion modes, which can effectively predict the robot's locomotion performance, including the average velocity, slope, and radius of the trajectory. Gait experiments and complex scenario locomotion experiments demonstrate that the WSIM robot indeed has multi-modal locomotion capability and is well suited to execute tasks in complex environments including tubes, open areas, and narrow corridors. The findings of this paper would provide a useful basis for the design, modeling, and control of future bioinspired multi-modal robots.

Multi-classification deep neural networks for identification of fish species using camera captured images.

Regular monitoring of the number of various fish species in a variety of habitats is essential for marine conservation efforts and marine biology research. To address the shortcomings of existing manual underwater video fish sampling methods, a plethora of computer-based techniques are proposed. However, there is no perfect approach for the automated identification and categorizing of fish species. This is primarily due to the difficulties inherent in capturing underwater videos, such as ambient changes in luminance, fish camouflage, dynamic environments, watercolor, poor resolution, shape variation of moving fish, and tiny differences between certain fish species. This study has proposed a novel Fish Detection Network (FD_Net) for the detection of nine different types of fish species using a camera-captured image that is based on the improved YOLOv7 algorithm by exchanging Darknet53 for MobileNetv3 and depthwise separable convolution for 3 x 3 filter size in the augmented feature extraction network bottleneck attention module (BNAM). The mean average precision (mAP) is 14.29% higher than it was in the initial version of YOLOv7. The network that is utilized in the method for the extraction of features is an improved version of DenseNet-169, and the loss function is an Arcface Loss. Widening the receptive field and improving the capability of feature extraction are achieved by incorporating dilated convolution into the dense block, removing the max-pooling layer from the trunk, and incorporating the BNAM into the dense block of the DenseNet-169 neural network. The results of several experiments comparisons and ablation experiments demonstrate that our proposed FD_Net has a higher detection mAP than YOLOv3, YOLOv3-TL, YOLOv3-BL, YOLOv4, YOLOv5, Faster-RCNN, and the most recent YOLOv7 model, and is more accurate for target fish species detection tasks in complex environments.

Bioinspired Synergy Strategies Empower Small‐Scale Robots with Higher Performance

Small‐scale robots need to be agile to perform various tasks in complex environments and the design faces great challenges with limited size and power consumption. However, the advent of advanced functional materials, compliant structures/mechanisms, and flexible fabrication techniques has brought new evolution directions to robotics. These technologies enrich the robots' actuation strategies, improving their performance of small robots while simplifying the complexity of the system and thus making it possible to be applied in diverse scenarios, such as disaster rescue, medical, and environmental exploration. In nature, small organisms have shown numerous efficient survival strategies. They can easily achieve locomotion tasks with low energy consumption. For example, dragonflies complete long flights with the help of wind, and stenus (one kind of rove beetle) uses the surface tension of liquids to dodge prey quickly. Insects are usually considered to be agile, efficient, and intelligent, which is the same requirement as for small robots. Yet the corresponding bioinspired design strategies bring new opportunities and challenges to the development of small‐scale robots. Herein, the development trends of small‐scale robots are analyzed and discussed, and several potential bioinspired synergy strategies are induced, which may be useful for the future design of insect‐level soft robots.

Establishing Human Observer Criterion in Evaluating Artificial Social Intelligence Agents in a Search and Rescue Task.

Artificial social intelligence (ASI) agents have great potential to aid the success of individuals, human-human teams, and human-artificial intelligence teams. To develop helpful ASI agents, we created an urban search and rescue task environment in Minecraft to evaluate ASI agents' ability to infer participants' knowledge training conditions and predict participants' next victim type to be rescued. We evaluated ASI agents' capabilities in three ways: (a) comparison to ground truth-the actual knowledge training condition and participant actions; (b) comparison among different ASI agents; and (c) comparison to a human observer criterion, whose accuracy served as a reference point. The human observers and the ASI agents used video data and timestamped event messages from the testbed, respectively, to make inferences about the same participants and topic (knowledge training condition) and the same instances of participant actions (rescue of victims). Overall, ASI agents performed better than human observers in inferring knowledge training conditions and predicting actions. Refining the human criterion can guide the design and evaluation of ASI agents for complex task environments and team composition.

A modified YOLOv5 helmet detection algorithm based on Swin Transformer

For the current stage of helmet detection in complex environments with low accuracy, missed detection and not easy to manage wearing, this paper proposes a YOLOv5 face helmet detection algorithm based on Swin Transformer improvement from the overall semantics of the image. In this paper, experiments are conducted using a self-built dataset to further enhance the performance of the model and improve the accuracy of face helmet detection through Mosaic data enhancement, label smoothing processing, adaptive weighted features combined with Wconcat module and the application of C3TR and C3STR modules to fuse multi-scale information, enhance the feature extraction capability of the network, and improve the generalization and robustness of the model with a self-built dataset . Experiments show that the improved YOLOv5 face helmet detection algorithm mAP based on Swin Transformer improves 5.7% compared with Faster RCNN, 6.1% compared with YOLOV3, 5.3% compared with YOLOV4, and 1.6% compared with the original algorithm. It performs well in helmet face detection tasks in complex environments, achieving real-time detection and higher accuracy, while reducing missed detections.

Conflict, Chaos, and the Art of Institutional Design

The metaphor of an organization as a garbage can is often invoked as a playful insult. However, as was recognized early on by management theorists studying garbage can ideas, the unpredictability arising from garbage can decision making has the potential to be adaptively rational for organizations facing complex task environments. The chaos produced by preference conflict and fluid participation in collective decision making can aid in search by enabling organizations to escape local performance peaks or competency traps. The decades-old hypothesis that conflict and chaos could promote adaptively rational search, however, has largely been overlooked in research on organizational design. This paper uses an agent-based model to evaluate these competing views and, in the process, identify conditions under which garbage can decision making is adaptively rational for executives searching for high-quality strategies. I show that the biased and chaotic outcomes that emerge as a result of garbage can decision making—the very features of garbage cans that lead them to be perceived to be dysfunctional—can facilitate short-term exploitation and long-term exploration of uncertain technical landscapes when organizations engage in serial judgment of local alternatives if internal conflict over desired outcomes is not too extreme. I conclude that decision-making routines that encourage chaotic conflict are robust to bounded rationality and complex task uncertainty and thus should be included in the organizational designer’s portfolio. Supplemental Material: The online supplement is available at https://doi.org/10.1287/orsc.2023.1662 .