Robotic Agents Research Articles

A review: Swarm Robotics: Cooperative Control in Multi-Agent Systems

Swarm robotics epitomizes a frontier in cooperative control within multi-agent systems, where the emulation of biological swarms offers a paradigm shift in robotics. This paper delves into the mechanisms of decentralized decision-making and the emergent behaviors that arise from local interactions among autonomous robotic agents without the need for a central controller. It explores the synthesis of simple control rules that yield complex, adaptive, and scalable group behaviors, akin to those found in natural swarms. A critical examination of communication protocols elucidates how information-sharing among agents leads to the robust execution of collective tasks. The research further investigates the dynamics of role allocation, task partitioning, and redundancy, which are crucial for the resilience of swarm robotic systems. Through simulation and empirical analysis, the efficacy of swarm algorithms in various applications, including search and rescue, environmental monitoring, and collective construction, is demonstrated. The study's findings underscore the significance of bio-inspired algorithms and the potential of swarm robotic systems to adapt and thrive in unpredictable environments. The implications for the future of autonomous systems are profound, as swarm robotics paves the way for innovations in distributed artificial intelligence and robotic.

The Emotions and Advice in Virtual Assistants: A Dual Study on Emotion Validation and Agent Suggestions in a Gaming Scenario

In an era where virtual assistants play an increasingly prominent role in our daily lives, this study explores the implications of their advice. We investigate the interplay between trust and virtual agents’ emotional expressions, delving into a critical aspect of human-technology interaction. Conducted through a comprehensive study comprising two interconnected phases, our research examines the dynamics between virtual agents and human decision-making. The first phase involves developing and validating a virtual robotic agent capable of conveying a spectrum of emotions. Through this, gender-based differences in emotional cue perception are disclosed, shedding light on how men and women interpret these cues differently. The second phase employs an interactive memory game, where the virtual agent operates in varied emotional states. Participants’ trust levels and perceptions are meticulously evaluated in different scenarios, ranging from accurate to erroneous agent cues. Our findings elucidate the impact of the agent’s emotional expressions on participants’ perceptions, illustrating how trust is intricately influenced by both the task at hand and the agent’s behavior. This research contributes to understanding the relationship between virtual assistants and human decision-making, emphasizing the necessity of designing more engaging and interactive virtual agents. These insights prepare future research for crafting more effective virtual assistants, fostering increased user trust and engagement.

A GPU-based hydrodynamic simulator with boid interactions

We present a hydrodynamic simulation system using the GPU compute shaders of DirectX for simulating virtual agent behaviors and navigation inside a smoothed particle hydrodynamical (SPH) fluid environment with real-time water mesh surface reconstruction. The current SPH literature includes interactions between SPH and heterogeneous meshes but seldom involves interactions between SPH and virtual boid agents. The contribution of the system lies in the combination of the parallel smoothed particle hydrodynamics model with the distributed boid model of virtual agents to enable agents to interact with fluids. The agents based on the boid algorithm influence the motion of SPH fluid particles, and the forces from the SPH algorithm affect the movement of the boids. To enable realistic fluid rendering and simulation in a particle-based system, it is essential to construct a mesh from the particle attributes. Our system also contributes to the surface reconstruction aspect of the pipeline, in which we performed a set of experiments with the parallel marching cubes algorithm per frame for constructing the mesh from the fluid particles in a real-time compute and memory-intensive application, producing a wide range of triangle configurations. We also demonstrate that our system is versatile enough for reinforced robotic agents instead of boid agents to interact with the fluid environment for underwater navigation and remote control engineering purposes.

Програмний пакет для адаптивного навчання контролерів роборуки на основі нейромереж

The article deals with the development of a software solution for the application of neuroevolution algorithms when creating a controller for controlling a robotic arm. The main principles of the neuroevolutionary approach for training neural network controllers in tasks requiring reinforcement learning are considered. In particular, the advantages of the adaptive approach are determined for a wide class of scenarios in which the working limb can work: implementation of stable grasping, positioning, manipulation of objects. It is noted that the final result of neuroevolution is an optimal network topology, which makes the model more resource-efficient and easier to analyze. The paper considers a software system that provides the developer with all the necessary tools for modeling the behavior of a robotic agent in environments of various levels of complexity: both two-dimensional and three-dimensional. In addition, the possibility of specifying the state of the agent not only as a set of data from sensors, but also as an image of the current environment from the camera is considered. According to the results of the experiments, the high efficiency of the search for the best solution using the NEAT algorithm is noted. It has been established that the proposed solution allows productively obtaining an effective policy in the form of a neural network, which has a minimal configuration, which will allow to increase the speed of the controller, which is critical for the operation of a real system. Thus, the use of a software solution for the adaptive development of a neuroevolutionary controller for solving tasks with a robotic limb allows to increase the efficiency of the learning process and obtain an optimal network topology.

Learning to summarize and answer questions about a virtual robot’s past actions

When robots perform long action sequences, users will want to easily and reliably find out what they have done. We therefore demonstrate the task of learning to summarize and answer questions about a robot agent’s past actions using natural language alone. A single system with a large language model at its core is trained to both summarize and answer questions about action sequences given ego-centric video frames of a virtual robot and a question prompt. To enable training of question answering, we develop a method to automatically generate English-language questions and answers about objects, actions, and the temporal order in which actions occurred during episodes of robot action in the virtual environment. Training one model to both summarize and answer questions enables zero-shot transfer of representations of objects learned through question answering to improved action summarization.

VGR Dataset: A CFD-based Gas Dispersion Dataset for Mobile Robotic Olfaction

There are many potential applications for an autonomous robotic agent capable of sensing gases in the environment, from locating leaks in pipes to monitoring air quality. However, the current state of the art in the field of robotic olfaction is not mature enough for most real-world applications. Due to the complexity of gas dispersion phenomena and the limitations of sensors, a great deal of research into the development of techniques and algorithms remains necessary. A very important part of this research is thorough experimentation, but carrying out robotic olfaction experiments is far from trivial. Real world experiments are usually limited to very simplified, wind-tunnel-like environments, as it is impossible to closely monitor or control the airflow in more complex scenarios. For this reason, simulation with CFD offers the most plausible alternative, allowing researchers to study the behavior of their algorithms in more challenging and complex situations. This work presents a CFD-based gas dispersion dataset composed of 120 cases generated under variable environmental conditions, taking place in 30 realistic and detailed models of real houses. All the data is made available in multiple formats, and is directly accessible through ROS, to permit easy integration with other robotic tools.

Distributed Formation Control of Multi-Robot Systems with Path Navigation via Complex Laplacian.

This paper focuses on the formation control of multi-robot systems with leader-follower network structure in directed topology to guide a system composed of multiple mobile robot agents to achieve global path navigation with a desired formation. A distributed linear formation control strategy based on the complex Laplacian matrix is employed, which enables the robot agents to converge into a similar formation of the desired formation, and the size and orientation of the formation are determined by the positions of two leaders. Additionally, in order to ensure that all robot agents in the formation move at a common velocity, the distributed control approach also includes a velocity consensus component. Based on the realization of similar formation control of a multi-robot system, the path navigation algorithm is combined with it to realize the global navigation of the system as a whole. Furthermore, a controller enabling the scalability of the formation size is introduced to enhance the overall maneuverability of the system in specific scenarios like narrow corridors. The simulation results demonstrate the feasibility of the proposed approach.

Distributed Formation Control for a Multirobotic Fish System With Model-Based Event-Triggered Communication Mechanism

This paper confronts the formation control problem for a multi-robotic fish system with event-triggered communication mechanism. A three-dimensional (3-D) distributed formation control framework is proposed to drive the robotic fish agents to an anticipated configuration aligning with a moving target. In particular, a consensus-based formation control law is intended to realize the two-stage formation control process. Taking the energy-constrained occasions into consideration, the communication structure and event-triggered protocols are initially tailored. Meanwhile, the Lyapunov function is employed and the globally asymptotic stability of the proposed method is fully demonstrated. Afterwards, making use of the local measurements of triggering times, the unscented Kalman filter (UKF) is introduced and a novel model-based event-triggered mechanism is put forward to further mitigate otiose communication consumption. Finally, adequate simulations and experiments are carried out to verify the effectiveness and robustness of the proposed scheme. Thereby, the proposed formation control frame offers great potential for future practical marine operations of the underwater multi-agent systems.

Behavior Learning System for Robot Soccer Using Neural Network

With technological developments, the prospect of a human-robot symbiotic society has emerged. A soccer game has characteristics similar to those expected in such a society. Soccer is a multiagent game in which the strategy employed depends on each agent’s position and actions. This paper discusses the results of the development of a learning system that uses a self-organizing map to select behaviors depending on the scenario (two-dimensional absolute coordinates of the agent, other agents, and the ball). The system can reproduce the action-selection algorithms of all the players on a certain team, and the robot can instantly select the next cooperative action from information obtained during the game. Thus, common-sense rules can be shared to learn an action-selection algorithm for a set of both human and robot agents.

From Brain Models to Robotic Embodied Cognition: How Does Biological Plausibility Inform Neuromorphic Systems?

We examine the challenging "marriage" between computational efficiency and biological plausibility-A crucial node in the domain of spiking neural networks at the intersection of neuroscience, artificial intelligence, and robotics. Through a transdisciplinary review, we retrace the historical and most recent constraining influences that these parallel fields have exerted on descriptive analysis of the brain, construction of predictive brain models, and ultimately, the embodiment of neural networks in an enacted robotic agent. We study models of Spiking Neural Networks (SNN) as the central means enabling autonomous and intelligent behaviors in biological systems. We then provide a critical comparison of the available hardware and software to emulate SNNs for investigating biological entities and their application on artificial systems. Neuromorphics is identified as a promising tool to embody SNNs in real physical systems and different neuromorphic chips are compared. The concepts required for describing SNNs are dissected and contextualized in the new no man's land between cognitive neuroscience and artificial intelligence. Although there are recent reviews on the application of neuromorphic computing in various modules of the guidance, navigation, and control of robotic systems, the focus of this paper is more on closing the cognition loop in SNN-embodied robotics. We argue that biologically viable spiking neuronal models used for electroencephalogram signals are excellent candidates for furthering our knowledge of the explainability of SNNs. We complete our survey by reviewing different robotic modules that can benefit from neuromorphic hardware, e.g., perception (with a focus on vision), localization, and cognition. We conclude that the tradeoff between symbolic computational power and biological plausibility of hardware can be best addressed by neuromorphics, whose presence in neurorobotics provides an accountable empirical testbench for investigating synthetic and natural embodied cognition. We argue this is where both theoretical and empirical future work should converge in multidisciplinary efforts involving neuroscience, artificial intelligence, and robotics.

Systems-theoretic interdependence analysis in robot-assisted warehouse management

The safe and efficient application of collaborative robots requires an understanding of actual work practices transformation, emerging from the adoption of new technological instruments. Functional systems-thinking is largely absent in literature about collaborative robot applications. In this context, this study proposes a framework that combines two safety analysis methods, being the Functional Resonance Analysis Method and Interdependence Analysis. Both safety and efficiency are examined by selected case study highlights to gain an in-depth understanding of human operators’ role as the central driver of human–machine (eco)systems in a warehouse distribution system, in which warehouse robot assistance is provided. Whereas the Functional Resonance Analysis Method first maps the work system interactions as a whole, Interdependence Analysis is subsequently applied to investigate individual inter-agent exchanges by the principles of Observability, Predictability, and Directability as a core principle for goal coordination between multiple agents, including warehouse robot agents. The case study examples reveal the combined effects of the working system environment and the robot application but also demonstrate possible operational solutions to deal with socio-technical complexity.

Integrated system architecture with mixed-reality user interface for virtual-physical hybrid swarm simulations

This paper introduces a hybrid robotic swarm system architecture that combines virtual and physical components and enables human–swarm interaction through mixed reality (MR) devices. The system comprises three main modules: (1) the virtual module, which simulates robotic agents, (2) the physical module, consisting of real robotic agents, and (3) the user interface (UI) module. To facilitate communication between the modules, the UI module connects with the virtual module using Photon Network and with the physical module through the Robot Operating System (ROS) bridge. Additionally, the virtual and physical modules communicate via the ROS bridge. The virtual and physical agents form a hybrid swarm by integrating these three modules. The human–swarm interface based on MR technology enables one or multiple human users to interact with the swarm in various ways. Users can create and assign tasks, monitor real-time swarm status and activities, or control and interact with specific robotic agents. To validate the system-level integration and embedded swarm functions, two experimental demonstrations were conducted: (a) two users playing planner and observer roles, assigning five tasks for the swarm to allocate the tasks autonomously and execute them, and (b) a single user interacting with the hybrid swarm consisting of two physical agents and 170 virtual agents by creating and assigning a task list and then controlling one of the physical robots to complete a target identification mission.

Learning Deep Features for Robotic Inference From Physical Interactions

In order to effectively handle multiple tasks that are not pre-defined, a robotic agent needs to automatically map its high-dimensional sensory inputs into useful features. As a solution, feature learning has empirically shown substantial improvements in obtaining representations that are generalizable to different tasks, compared to feature engineering approaches, but it requires a large amount of data and computational capacity. These challenges are specifically relevant in robotics due to the low signal-to-noise ratios inherent to robotic data, and to the cost typically associated with collecting this type of input. In this paper, we propose a deep probabilistic method based on Convolutional Variational Auto-Encoders (CVAEs) to learn visual features suitable for interaction and recognition tasks. We run our experiments on a self-supervised robotic sensorimotor dataset. Our data was acquired with the iCub humanoid and is based on a standard object collection, thus being readily extensible. We evaluated the learned features in terms of usability for 1) object recognition, 2) capturing the statistics of the effects, and 3) planning. In addition, where applicable, we compared the performance of the proposed architecture with other state-ofthe-art models. These experiments demonstrate that our model is capable of capturing the functional statistics of action and perception (i.e. images) which performs better than existing baselines, without requiring millions of samples or any handengineered features.

All Human Versus Human-Robot Teaming: Measuring Neurophysiological Synchrony, Team Performance, and Trust during Search and Rescue

This study used a multiplayer virtual environment simulating search and rescue to examine teaming behaviors and trust networks in two teaming conditions using the Wizard of Oz approach: (1) an all-human team (three humans) and (2) a human-robot team (two humans, one simulated quadruped robot). Neural, physiological, and subjective responses of trust and workload at the individual and team (e.g., neurophysiological synchrony) levels, along with task performance, were measured. We observed better task performance in human-robot teams and associated higher neural synchrony, but lower trust in the team and the robot agent. Trust between the human dyads remained intact. These findings provide insights into comparing the neural bases of complex and social interactions in all-human versus human-autonomy teams.

Cooperative Manipulation via Internal Force Regulation: A Rigidity Theory Perspective

This paper considers the integration of rigid cooperative manipulation with rigidity theory. Motivated by rigid models of cooperative manipulation systems, i.e., where the grasping contacts are rigid, we introduce first the notion of bearing and distance rigidity for graph frameworks in <inline-formula><tex-math notation="LaTeX">$\mathsf {SE}(3)$</tex-math></inline-formula>. Next, we associate the nodes of these frameworks to the robotic agents of rigid cooperative manipulation schemes and we express the object-agent internal forces by using the graph rigidity matrix, which encodes the infinitesimal rigid body motions of the system. Moreover, we show that the associated cooperative manipulation grasp matrix is related to the rigidity matrix via a range-nullspace relation, based on which we provide novel results on the relation between the arising interaction and internal forces and consequently on the energy-optimal force distribution on a cooperative manipulation system. Finally, simulation results enhance the validity of the theoretical findings.

Cyber-physical systems in non-rigid assemblies: A methodology for the calibration of deformable object reconstruction models

Despite the advances in robot agent cognition and systems’ decision-making, under the prism of cyber-physical systems and industrial metaverse, the manufacturing processes involving the handling of non-rigid product assemblies present a delay in the adoption of smart automation. Model-based planning and control can address the particularities of deformable object manipulation; however, their competence is heavily dependent on the models’ accuracy and reconstruction frequencies. Despite the many breakthroughs that have been achieved in real-time modelling and behavior prediction of deformable objects, the calibration of such models and the measurement of their accuracy remain a significant challenge. In this paper, a method for the definition of the physics parameters of flexible material reconstruction models is presented. The proposed systematic approach, employing a number of optimization algorithms, fine-tunes the model’s parameters for the real-world deformable object, as captured by the perception system, to be aligned with its digital twin. A mass-spring model for the reconstruction of two-dimensional fabric objects is used as an application paradigm. An experimental setup in an industrially relevant environment validates the applicability of the proposed approach and is used for assessing alternative sensing practices and optimization algorithms.

The central amygdala modulates distinctive conflict-like behaviors in a naturalistic foraging task.

Conflict situations elicit a diverse range of behaviors that extend beyond the simplistic approach or avoidance dichotomy. However, many conflict-related studies have primarily focused on approach suppression, neglecting the complexity of these behaviors. In our study, we exposed rats to a semi-naturalistic foraging task, presenting them with a trade-off between a food reward and a predatory threat posed by a robotic agent. We observed that rats displayed two conflict-like behaviors (CLBs)-diagonal approach and stretched posture-when facing a robotic predator guarding a food pellet. After electrolytic lesions to the central amygdala (CeA), both conflict behaviors were significantly reduced, accompanied by a decrease in avoidance behavior (hiding) and an increase in approach behavior (frequency of interactions with the robot). A significant negative correlation between avoidance and approach behaviors emerged after the CeA lesion; however, our data suggest that CLBs are not tightly coupled with either approach or avoidance behaviors, showing no significant correlation to those behaviors. Our findings indicate that the CeA plays a crucial role in modulating conflict behaviors, competing with approach suppression in risky situations.

HARPS: An Online POMDP Framework for Human-Assisted Robotic Planning and Sensing

The ability of autonomous robots to model, communicate, and act on semantic “soft data” remains challenging. The human-assisted robotic planning and sensing (HARPS) framework is presented for active semantic sensing and planning in human–robot teams to address these gaps by formally combining the benefits of online sampling-based partially observable Markov decision process policies, multimodal human–robot interaction, and Bayesian data fusion. HARPS lets humans impose model structure and extend the range of soft data by sketching and labeling new semantic features in uncertain environments. Dynamic model updating lets robotic agents actively query humans for novel and relevant semantic data, thereby improving model and state beliefs for improved online planning. Simulations of a unmanned aerial vehicle-enabled target search in a large-scale partially structured environment show significant improvements in time and beliefs required for interception versus conventional planning with robot-only sensing. A human subject study in the same environment shows an average doubling in dynamic target capture rate compared to the lone robot case and highlights the robustness of HARPS over a range of user characteristics and interaction modalities.

A Distributed, Event-Triggered, Adaptive Controller for Cooperative Manipulation With Rolling Contacts

We present a distributed, event-triggered, and adaptive control algorithm for cooperative object manipulation with rolling contacts and unknown dynamic parameters. Whereas conventional cooperative manipulation methods require rigid contact points, our approach exploits rolling effects of passive end-effectors and does not require force/torque sensing. The removal of rigidity allows for more modular grasping, increased application to more object types, and online adjustment of the grasp. The proposed control algorithm exhibits the following properties: 1) it is distributed, in the sense that the robotic agents calculate their own control signal, under an event-triggered communication scheme. Such a scheme reduces the interagent communication requirements with respect to continuous communication schemes; 2) it uses an online adaptation mechanism to accommodate for unknown dynamic parameters of the object and the agents and 3) it adapts existing internal force controllers to guarantee no slip throughout the manipulation task despite the event-triggered nature of the communication scheme. Hardware implementation validates the effectiveness of the proposed approach.

Anthropomorphism-based causal and responsibility attributions to robots

People tend to expect mental capabilities in a robot based on anthropomorphism and often attribute the cause and responsibility for a failure in human-robot interactions to the robot. This study investigated the relationship between mind perception, a psychological scale of anthropomorphism, and attribution of the cause and responsibility in human-robot interactions. Participants played a repeated noncooperative game with a human, robot, or computer agent, where their monetary rewards depended on the outcome. They completed questionnaires on mind perception regarding the agent and whether the participant’s own or the agent’s decisions resulted in the unexpectedly small reward. We extracted two factors of Experience (capacity to sense and feel) and Agency (capacity to plan and act) from the mind perception scores. Then, correlation and structural equation modeling (SEM) approaches were used to analyze the data. The findings showed that mind perception influenced attribution processes differently for each agent type. In the human condition, decreased Agency score during the game led to greater causal attribution to the human agent, consequently also increasing the degree of responsibility attribution to the human agent. In the robot condition, the post-game Agency score decreased the degree of causal attribution to the robot, and the post-game Experience score increased the degree of responsibility to the robot. These relationships were not observed in the computer condition. The study highlights the importance of considering mind perception in designing appropriate causal and responsibility attribution in human-robot interactions and developing socially acceptable robots.