Cooperative Robots Research Articles

Robotics at the University of Pennsylvania from Birth to Maturity: A Review of 30 Years of Research

This article is an attempt to reexamine the evolution of robotics research at the University of Pennsylvania and all that it entailed, covering the successes and struggles of PhD students, postdoctoral researchers, and a few dedicated faculty between 1972 and 2000. In 1945, Penn's Moore School of Electrical Engineering was famous for developing the first electronic digital computer, ENIAC, but after a few years, the research had diminished. In 1972, a new Department of Computer and Information Science was formed. I came to Penn from Stanford University's Artificial Intelligence Laboratory full of energy, enthusiasm, and the goal of establishing a similar lab at Penn. This article demonstrates the creativity and ingenuity of young professionals at the General Robotics, Automation, Sensing, and Perception (GRASP) Laboratory. We built hardware. We built software. We collaborated with psychologists and electrical and mechanical engineers and tried to build a community of roboticists. Our curiosity led us to build new vision and tactile systems and to investigate cooperative robotics systems on the ground and in the air. We used computational models supported and verified by experiments. Today, I am proud to say that almost all of the students who cycled through the GRASP Lab are successful in academia or industry.

Accelerated Transfer Learning for Cooperative Transportation Formation Change via SDPA-MAPPO (Scaled Dot Product Attention-Multi-Agent Proximal Policy Optimization)

A method for cooperative transportation, which required formation change in a traveling environment, is gaining interest. Deep reinforcement learning is used in formation changes for multi-robot cases. The MADDPG (Multi-Agent Deep Deterministic Policy Gradient) method is popularly used for recognized environments. On the other hand, re-learning may be required in unrecognized circumstances by using the MADDPG method. Although the development of MADDPG using model-based learning and imitation learning has been applied to reduce learning time, it is unclear how the learning results are transferred when the number of robots changes. For example, in the GASIL-MADDPG (Generative adversarial self-imitation learning and Multi-agent Deep Deterministic Policy Gradient) method, how the results of three robot training can be transferred to the four robots’ neural networks is uncertain. Nowadays, Scaled Dot Product Attention (SDPA) has attracted attention and is highly impactful for its speed and accuracy in natural language processing. When transfer learning is combined with fast computation, the efficiency of edge-level re-learning is improved. This paper proposes a formation change algorithm that allows easy and fast multi-robot knowledge transfer using SDPA combined with MAPPO (Multi-Agent Proximal Policy Optimization), compared to other methods. This algorithm applies SDPA to multi-robot formation learning and performs fast learning by transferring the acquired knowledge of formation changes to a certain number of robots. The proposed algorithm is verified by simulating the robot formation change and was able to achieve dramatic high-speed learning capabilities. The proposed SDPA-MAPPO (Scaled Dot Product Attention-Multi-Agent Proximal Policy Optimization) learned 20.83 times faster than the Deep Dyna-Q method. Furthermore, using transfer learning from a three-robot to five-robot case, the method shows that the learning time can be reduced by about 56.57 percent. A scenario of three-robot to five-robot is chosen based on the number of robots often used in cooperative robots.

Cooperative Object Transport Via Non-Contact Prehensile Pushing by Magnetic Forces

Abstract Cooperative robot systems are an essential candidate for object transportation solutions. They offer cost-efficient and flexible operation for various types of robotic tasks. The benefits of cooperative robot systems have triggered the improvement of the object transportation field. In this study, a new way of transporting objects by cooperative robots is presented. The proposed method is performed by the pushing action of the magnetic forces of the robots. The permanent magnets mounted on the mobile robots and the cart create this repelling force. The rectangular object carrier cart equipped with passive caster wheels can be manipulated on flat terrains easily and be assigned to carry different shapes of objects. Using a carrier cart has the advantage of eliminating the vertical loads on the robots. Controlling a non-contact pushing method offers a low computational burden since simple velocity and position updates are adequate for operation management. Compared with the other methods of object transportation systems, the non-contact pushing method provides a faster operation with less sensitivity to control errors. Both simulations and real-world experiments are conducted and the performances are given comparatively with a generalized frictional contact object-pushing method. The results show that the proposed method provides 10.48% faster and 20.03% more accurate object transportation compared to the frictional contact method. It is envisioned that the presented method can be a promising candidate for object transportation tasks in the industry.

Distributed Multi-Robot SLAM Algorithm with Lightweight Communication and Optimization

Multi-robot SLAM (simultaneous localization and mapping) is crucial for the implementation of robots in practical scenarios. Bandwidth constraints significantly influence multi-robot SLAM systems, prompting a reliance on lightweight feature descriptors for robot cooperation in positioning tasks. Real-time map sharing among robots is also frequently ignored in such systems. Consequently, such algorithms are not feasible for autonomous multi-robot navigation tasks in the real world. Furthermore, the computation cost of the global optimization of multi-robot SLAM increases significantly in large-scale scenes. In this study, we introduce a novel distributed multi-robot SLAM framework incorporating sliding window-based optimization to mitigate computation loads and manage inter-robot loop closure constraints. In particular, we transmit a 2.5D grid map of the keyframe-based submap between robots to promote map consistency among robots and maintain bandwidth efficiency in data exchange. The proposed algorithm was evaluated in extensive experimental environments, and the results validate its effectiveness and superiority over other mainstream methods.

High Stiffness 6-DOF Dual-Arm Cooperative Robot and Its Application in Blade Polishing

High Stiffness 6-DOF Dual-Arm Cooperative Robot and Its Application in Blade Polishing

Motion priority optimization framework towards automated and teleoperated robot cooperation in industrial recovery scenarios

In this study, we introduce an optimization framework to enhance the efficiency of motion priority design in scenarios involving automated and teleoperated robots within an industrial recovery context. The increasing utilization of industrial robots at manufacturing sites has been instrumental in reducing human workload. Nevertheless, achieving effective human–robot collaboration/cooperation (HRC) remains a challenge, especially when human workers and robots share a workspace for collaborative tasks. For instance, when an industrial robot encounters a failure, such as dropping an assembling part, it triggers the suspension of the corresponding factory cell for safe recovery. Given the limited capacity of pre-programmed robots to rectify such failures, human intervention becomes imperative, requiring entry into the robot workspace to address the dropped object while the robot system is halted. This discontinuous manufacturing process results in productivity loss. Robotic teleoperation has emerged as a promising technology enabling human workers to undertake high-risk tasks remotely and safely. Our study advocates for the incorporation of robotic teleoperation in the recovery process during manufacturing failure scenarios, which is referred to as “Cooperative Tele-Recovery”. Our proposed approach involves formulating priority rules designed to facilitate collision avoidance between manufacturing and recovery robots. This, in turn, ensures a continuous manufacturing process with minimal production loss within a configurable risk limitation. We present a comprehensive motion priority optimization framework composed of an HRC simulator and a cooperative multi-robot controller to identify optimal parameters for the priority function. The framework dynamically adjusts the allocation of motion priorities for manufacturing and recovery robots while adhering to predefined risk limitations. Through quantitative and qualitative assessments, we validate the novelty of our concept and demonstrate its feasibility.

Pick and Place Control of a 3-DOF Robot Manipulator Based on Image and Pattern Recognition

Board games like chess serve as an excellent testbed for human–robot interactions, where advancements can lead to broader human–robot cooperation systems. This paper presents a chess-playing robotic system to demonstrate controlled pick and place operations using a 3-DoF manipulator with image and speech recognition. The system identifies chessboard square coordinates through image processing and centroid detection before mapping them onto the physical board. User voice input is processed and transcribed into a string from which the system extracts the current and destination locations of a chess piece with a word error rate of 8.64%. Using an inverse-kinematics algorithm, the system calculates the joint angles needed to position the end effector at the desired coordinates actuating the robot. The developed system was evaluated experimentally on the 3-DoF manipulator with a voice command used to direct the robot movement in grasping a chess piece. Consideration was made involving both the own pieces as well as capturing the opponent’s pieces and moving the captured piece outside the board workspace.

String‐Like Self‐Capacitance‐Based Proximity and Tactile Sensor that Can be Wrapped Around Robotic Arms

AbstractCooperative robots that perform safety functions as part of cooperative work with humans have been recently drawing attention. Proximity and tactile sensors that can be retrofitted to a robot's surface are important safety measures for existing robots that are not manufactured as cooperative robots to be used as cooperative robots. In this paper, a string‐like self‐capacitance‐based proximity and tactile sensor that can be easily wrapped around various types of existing robots is proposed. The novel and useful point in this paper is that it can be easily mounted on various robots by a flexible string‐like proximity and tactile sensor. The sensor module can be adjusted to the required length by connecting different numbers of modules depending on the mounting surface. As a demonstration, six prototype sensor modules were connected by each connector and wrapped around a robotic arm. The sensor modules on the robot's surface could detect an object within its proximity range and detect the rough pressure after contact. In addition, the robotic arm with the sensor modules could be controlled in real time using the data obtained from the sensor that are object detection data at proximity range. These results confirm that the proposed sensor module can be used in the proximity and tactile sensors of existing robots. © 2024 Institute of Electrical Engineers of Japan and Wiley Periodicals LLC.

Advancements in Cooperative Mobile Robots Control Strategies for Large-Scale Material Transport

This paper explores groundbreaking advancements in control strategies for cooperative mobile robots used in large-scale material transport, a critical aspect of modern industrial, manufacturing, logistics, and construction sectors. It delves into the development of sophisticated systems that enable seamless coordination among multiple mobile robot systems. The research presents a novel hierarchical finite state automaton for dynamic mission adaptation and a null space-based control scheme for precise task execution and enhanced system resilience. The introduction of Mecanum wheels facilitates flexible movement and manipulation of materials, thereby increasing operational efficiency and safety. Cutting-edge sensory technology, including LiDAR, and the implementation of the Robot Operating System are highlighted for their roles in enhancing autonomous navigation and intelligent operation. Additionally, the paper discusses the impact of centralized and decentralized control methods in ensuring safe, cooperative object transport. The findings contribute to the vision of Industry 4.0 by promoting the integration of automation and robotic cooperation in complex environments and present a foundational blueprint for further research. Challenges for future work such as scalability, communication efficiency, collision avoidance, and energy efficiency are also considered, underscoring the need for ongoing development of robust and scalable robotic systems to address modern transport challenges.

Tele-Impedance control of a virtual avatar based on EMG and M-IMU sensors: a proof-of-concept

The broad spread of cooperative robots into many application domains has resulted in a demand for intuitive and effective solutions for teleoperated control. A relevant role in teleoperation has been assumed by impedance controllers, that allow the increase of stability and accuracy during interaction. This paper aims to test a teleoperation method based on an impedance controller, namely tele-impedance control, that is usable in unstructured environments since it relies only on wearable sensors. The proposed solution maps the joint stiffness and position of the human user, computed through six EMG and two M-IMU sensors, into the remote system to be teleoperated. We developed a 2-DoFs virtual task involving virtual physical interactions to compare the performance of our solution with the one of a traditional position-based controller. The study has been conducted on five healthy participants, who experienced both controllers in two different sessions. The tele-impedance approach has proved to be less physically demanding and more intuitive than the position-based one. Experimental data also allow us to investigate the strategy employed by the volunteers in the case of remote interactions, while using the two controllers. Of note, even though with the position controller the variation of subject impedance has no effect on the virtual arm, participants still tend to regulate both impedance and position of their own arm.

Stochastic Initial States Randomization Method for Robust Knowledge Transfer in Multi-Agent Reinforcement Learning

Reinforcement learning, which are also studied in the field of defense, face the problem of sample efficiency, which requires a large amount of data to train. Transfer learning has been introduced to address this problem, but its effectiveness is sometimes marginal because the model does not effectively leverage prior knowledge. In this study, we propose a stochastic initial state randomization(SISR) method to enable robust knowledge transfer that promote generalized and sufficient knowledge transfer. We developed a simulation environment involving a cooperative robot transportation task. Experimental results show that successful tasks are achieved when SISR is applied, while tasks fail when SISR is not applied. We also analyzed how the amount of state information collected by the agents changes with the application of SISR.

Enhancing Adaptability and Autonomy in Cooperative Selective Compliance Assembly Robot Arm Robots: Implementation of Coordination and Rapidly Exploring Random Tree Algorithms for Safe and Efficient Manipulation Tasks

In this study, a cooperative robotic system comprising two Selective Compliance Assembly Robot Arm (SCARA) robots was developed and simulated. An algorithm was proposed for the coordination of robots in cooperative tasks, along with a Rapidly exploring Random Tree (RRT) path planner for obstacle avoidance. The proposed system proved effective in transferring objects between robots and in handling various scenarios of variable complexity without collisions. The implementation of advanced trajectory planning and coordination algorithms significantly improves the adaptability and autonomy of robotic systems, allowing robots to predict and react to the movements of their counterparts and changes in the environment in real time. This capability is crucial for maintaining a safe and efficient work environment. The importance of synchronization and effective communication between robots is highlighted to avoid collisions and optimize trajectories and cycle times. All tests were conducted in virtual environments, allowing for the evaluation and refinement of the performance of the robots’ performance under controlled conditions. The positive results obtained in the simulations suggest that the system is well suited for future practical implementation in industrial and manufacturing applications, such as chemical handling, collaborative welding, quality inspection, among others. These findings underscore the potential of the cooperative SCARA system to improve the efficiency and safety in industrial applications using advanced algorithms and control techniques, establishing a solid foundation for future research and development in the field of cooperative robotics.

Toward a systematic reporting framework for Digital Twins: a cooperative robotics case study

Toward a systematic reporting framework for Digital Twins: a cooperative robotics case study

Stochastic Defect Localization for Cooperative Additive Manufacturing Using Gaussian Mixture Maps

Abstract Robotic additive manufacturing (RAM) offers significant improvements in maximum build volume compared to conventional bounded designs (e.g., gantry) by leveraging high degrees-of-freedom machines and multi-robot cooperation. However, cooperative RAM suffers from the same defect generation challenges as conventional systems, necessitating improvements in the detection and prevention of flaws within fabricated components. Quality assurance can be further bolstered through the integration of AM models, which utilize sensor feedback to localize defects, vastly reducing false positives. This research explores defect localization through a novel dynamic defect model created from simulated sensing data. In particular, two cooperative robots are simulated to estimate defect parameters, while observing the workspace and accurately classifying different regions of the part, generating a Gaussian mixture map that identifies and assigns appropriate actions based on defect types and characteristics. The experimental result shows that the implementation of the dynamic defect model and selective reevaluation achieved an effective defect detection accuracy of 99.9%, an improvement of 9.9% without localization. The proposed framework holds potential for application in domains that utilize high degrees-of-freedom machines and collaborative agents, offering scalability, improved fabrication speeds, and enhanced mechanical properties.

Generative artificial intelligence of things systems, multisensory immersive extended reality technologies, and algorithmic big data simulation and modelling tools in digital twin industrial metaverse

Research background: Multi-modal synthetic data fusion and analysis, simulation and modelling technologies, and virtual environmental and location sensors shape the industrial metaverse. Visual digital twins, smart manufacturing and sensory data mining techniques, 3D digital twin simulation modelling and predictive maintenance tools, big data and mobile location analytics, and cloud-connected and spatial computing devices further immersive virtual spaces, decentralized 3D digital worlds, synthetic reality spaces, and the industrial metaverse. Purpose of the article: We aim to show that big data computing and extended cognitive systems, 3D computer vision-based production and cognitive neuro-engineering technologies, and synthetic data interoperability improve artificial intelligence-based digital twin industrial metaverse and hyper-immersive simulated environments. Geolocation data mining and tracking tools, image processing computational and robot motion algorithms, and digital twin and virtual immersive technologies shape the economic and business management of extended reality environments and the industrial metaverse. Methods: Quality tools: AMSTAR, BIBOT, CASP, Catchii, R package and Shiny app citationchaser, DistillerSR, JBI SUMARI, Litstream, Nested Knowledge, Rayyan, and Systematic Review Accelerator. Search period: April 2024. Search terms: “digital twin industrial metaverse” + “artificial Intelligence of Things systems”, “multisensory immersive extended reality technologies”, and “algorithmic big data simulation and modelling tools”. Selected sources: 114 out of 336. Published research inspected: 2022–2024. PRISMA was the reporting quality assessment tool. Dimensions and VOSviewer were deployed as data visualization tools. Findings & value added: Simulated augmented reality and multi-sensory tracking technologies, explainable artificial intelligence-based decision support and cloud-based robotic cooperation systems, and ambient intelligence and deep learning-based predictive analytics modelling tools are instrumental in augmented reality environments and in the industrial metaverse. The economic and business management of the industrial metaverse necessitates connected enterprise production and big data computing systems, simulation and modelling technologies, and virtual reality-embedded digital twins.

Nonconvex distributed feedback optimization for aggregative cooperative robotics

Distributed aggregative optimization is a recently emerged framework in which the agents of a network want to minimize the sum of local objective functions, each one depending on the agent decision variable (e.g., the local position of a team of robots) and an aggregation of all the agents’ variables (e.g., the team barycenter). In this paper, we address a distributed feedback optimization framework in which agents implement a local (distributed) policy to reach a steady-state minimizing an aggregative cost function. We propose AGGREGATIVE TRACKING FEEDBACK, i.e., a novel distributed feedback optimization law in which each agent combines a closed-loop gradient flow with a consensus-based dynamic compensator reconstructing the missing global information. By using tools from system theory, we prove that AGGREGATIVE TRACKING FEEDBACK steers the network to a stationary point of an aggregative optimization problem with (possibly) nonconvex objective function. The effectiveness of the proposed method is validated through numerical simulations on a multi-robot surveillance scenario.

Research Status and Development Trend of Multi-arm Collaborative Robots

Abstract: Industrial robots are mainly used in metal forming, automotive, and electrical and electronics industries. After decades of unremitting efforts, industrial robots have achieved great success. However, problems such as low safety, weak environmental adaptability, and insufficient humancomputer interaction ability of industrial robots have greatly limited the application of industrial robots, and multi-arm collaborative robots came into being in this case. Multi-arm collaborative robots offer high flexibility and precision. Over the years, the application and development of multiarm collaborative robots have been paid more and more attention. This paper aims to summarize the patents related to multi-arm cooperative robots, including their principles, classification, latest progress and future development, in order to meet the needs of the real world. According to the structural characteristics of multi-arm collaborative robots and the requirements of multi-arm collaborative robots application field, the most typical mobile collaborative robots and stationary dual-arm collaborative robots in multi-arm collaborative robots are summarized. By investigating various patents of multi-arm collaborative robots the main problems of multi-arm collaborative robots are summarized and analyzed, such as collisions or conflicts between robotic arms, low power-to-weight ratio, loose structures, and heavy weight of the robot body. In addition, the development trend of multi-arm collaborative robots is also discussed. Multi-arm robots have broad prospects and potential in future applications and development. With the advancement of new technologies, multi-arm collaborative robots will become more efficient, intelligent, safe, and flexible. More relevant patents are expected to be invented in the future.

Modeling of Cooperative Robotic Systems and Predictive Control Applied to Biped Robots and UAV-UGV Docking with Task Prioritization.

This paper studies a cooperative modeling framework to reduce the complexity in deriving the governing dynamical equations of complex systems composed of multiple bodies such as biped robots and unmanned aerial and ground vehicles. The approach also allows for an optimization-based trajectory generation for the complex system. This work also studies a fast-slow model predictive control strategy with task prioritization to perform docking maneuvers on cooperative systems. The method allows agents and a single agent to perform a docking maneuver. In addition, agents give different priorities to a specific subset of shared states. In this way, overall degrees of freedom to achieve the docking task are distributed among various subsets of the task space. The fast-slow model predictive control strategy uses non-linear and linear model predictive control formulations such that docking is handled as a non-linear problem until agents are close enough, where direct transcription is calculated using the Euler discretization method. During this phase, the trajectory generated is tracked with a linear model predictive controller and addresses the close proximity motion to complete docking. The trajectory generation and modeling is demonstrated on a biped robot, and the proposed MPC framework is illustrated in a case study, where a quadcopter docks on a non-holonomic rover using a leader-follower topology.

Discriminating brainwave patterns of different control and non-control states for enhancing asynchronous brain-computer interfaces

ObjectiveIn asynchronous brain-computer interfaces (BCIs) for real-world applications, the user typically remains in non-control states most of the time and is allowed to perform various types of non-control tasks. Because of the diversity of non-control states, which include stimuli-off-based non-control (SNC), rest-based non-control (RNC), feedback-based non-control (FNC), and game-based non-control (GNC), it is difficult to discriminate between them. The objective of this study was to develop a discrimination method for different control and non-control states to enhance brain–robot cooperation. MethodsAn individualized space-frequency-based optimized complex network (ISF-OCN) was designed to discriminate the electroencephalogram (EEG) patterns of five typical states: a steady-state visual evoked potential (SSVEP)-based control (SC) state and four non-control states, i.e., SNC, RNC, FNC, and GNC. The ISF-OCN individualizes frequency bands and spatial filters to enhance the optimized complex network features for each state and uses random forest classifiers in a one-versus-rest scheme for classification.Main results: The proposed ISF-OCN outperformed four existing algorithms in both binary classification and five-state classification, regardless of data length. Notably, the ISF-OCN algorithm with a data length of 1.5 s achieved an average accuracy of 84.51 % in recognizing the five different states. ConclusionThe results demonstrate the feasibility of discriminating the four non-control states using EEG features and suggest that the proposed method is a promising new approach for discriminating control and non-control states to enhance asynchronous BCIs.

Human–Robot Cooperation Control Strategy Design Based on Trajectory Deformation Algorithm and Dynamic Movement Primitives for Lower Limb Rehabilitation Robots

Compliant physical interactions, interactive learning, and robust position control are crucial to improving the effectiveness and safety of rehabilitation robots. This paper proposes a human–robot cooperation control strategy (HRCCS) for lower limb rehabilitation robots. The high-level trajectory planner of the HRCCS consists of a trajectory generator, a trajectory learner, a desired trajectory predictor, and a soft saturation function. The trajectory planner can predict and generate a smooth desired trajectory through physical human–robot interaction (pHRI) in a restricted joint space and can learn the desired trajectory using the locally weighted regression method. Moreover, a triple-step controller was designed to be the low-level position controller of the HRCCS to ensure that each joint tracks the desired trajectory. A nonlinear disturbance observer is used to observe and compensate for total disturbances. The radial basis function neural networks (RBFNN) approximation law and robust term are adopted to compensate for observation errors. The simulation results indicate that the HRCCS is robust and can achieve compliant pHRI and interactive trajectory learning. Therefore, the HRCCS has the potential to be used in rehabilitation robots and other fields involving pHRI.