Search

Human-robot co-manipulation of soft materials, such as fabrics, composites, and sheets of paper/cardboard, is a challenging operation that presents several relevant industrial applications. Estimating the deformation state of the co-manipulated material is one of the main challenges. Viable methods provide the indirect measure by calculating the human-robot relative distance. In this paper, we develop a data-driven model to estimate the deformation state of the material from a depth image through a Convolutional Neural Network (CNN). First, we define the deformation state of the material as the relative roto-translation from the current robot pose and a human grasping position. The model estimates the current deformation state through a Convolutional Neural Network, specifically a DenseNet-121 pretrained on ImageNet.The delta between the current and the desired deformation state is fed to the robot controller that outputs twist commands. The paper describes the developed approach to acquire, preprocess the dataset and train the model. The model is compared with the current state-of-the-art method based on a skeletal tracker from cameras. Results show that our approach achieves better performances and avoids the various drawbacks caused by using a skeletal tracker.Finally, we also studied the model performance according to different architectures and dataset dimensions to minimize the time required for dataset acquisition, Comment: Pre-print, submitted to Robotics and Computer Integrated Manufacturing

Machine Learning has recently found a fertile ground in EMG signal decoding for prosthesis control. However, its understanding and acceptance are strongly limited by the notion of AI models as black-boxes. In critical fields, such as medicine and neuroscience, understanding the neurophysiological phenomena underlying models’ outcomes is as relevant as classification performance. In this work, we adapt state-of-the-art XAI algorithms to EMG hand gesture classification to understand the outcome of machine learning models with respect to physiological processes, evaluating the contribution of each input feature to the prediction and showing that AI models recognize the hand gestures by mapping and fusing efficiently high amplitude activity of synergic muscles. This allows us to (i) drastically reduce the number of required electrodes without a significant loss in classification performances, ensuring the suitability of the system for a larger population of amputees and simplifying the realization of near real-time applications and (ii) perform an efficient selection of features based on their classification relevance, apprehended by the XAI algorithms. This feature selection leads to classification improvements in term of robustness and computational time, outperforming correlation based methods. Finally, (iii) comparing the physiological explanations produced by the XAI algorithms with the experimental setting highlights inconsistencies in the electrodes positioning over different rounds or users, then improving the overall quality of the process.

Complex parts can be successfully manufactured by means of Additive Manufacturing (AM) techniques based on thermoplastic polymer extrusion, whose use for mass production is restricted by their slow printing speed. To address this limitation, a flexible AM platform for big plastic objects has been realized mounting an industrial screw-based extruder on an anthropomorphic robot. An experimental campaign has been performed to set a suitable range of relevant process parameters, with the aim of ensuring a regular deposited layer geometry. Moreover, a closed-loop control strategy has been developed to correct the robot height based on data measured during the material deposition, thus further improving the process parameter setting and compensating the material shrinkage or other unexpected defects. Eventually, an online re-slicing algorithm has been implemented to preserve the desired height of the manufactured object, despite the layer height changes. The proposed approach allows a deposition flow rate up to 1250 cm3/h within a building volume limited only by the robot workspace.

This paper deals with the control of a collaborative robot manipulator with series elastic actuators. In particular, robust tuning rules for cascade control of the joints are presented. Both the motor velocity and link position control loops are considered. The proposed tuning rules allow the online computation of robust control parameters to cope with the different link reflected inertia. Experimental results show the effectiveness of the method in real applications. (C) 2018, IFAC (International Federation of Automatic Control) Hosting by Elsevier Ltd. All rights reserved.

Conventional material removal systems, like CNC milling machines, have proven to be very effective and accurate. Their major drawbacks are related to machine cost, restricted working area and limitations on the allowed workpiece geometry. In principle, industrial robots (IRs) could be an excellent alternative for machining, being both flexible and cheap (if compared to a CNC machine). On the contrary, IRs do not offer sufficient positioning accuracy and they are prone to vibration onset due to a low capacity of disturbance rejection. These critical aspects currently limit the use of robots in typical machining applications. In this paper, the cutting capability of a serial IR, for light milling operation on aluminum alloy, has been analyzed with respect to the multiple poses allowed by its kinematics redundancy. Firstly, an experimental modal analysis has allowed to identify the variability of the robot static and dynamic compliance over different poses, which influence both tool deflection and vibration onset during milling. The static stiffness of the robot end-effector (EE), which causes tool deflection, has been analyzed by means of an elastic model with lumped parameters. It is shown that the usual static compliance criterion for the optimal pose selection does not guarantee the best performance in terms of vibration level and, thus, surface roughness. This claim has been supported by a set of cutting tests in two significant cases. The results are explained considering the pose-dependent static and the dynamics properties.

While multi-robot cells are being used more often in industry, the problem of work-piece position optimization is still solved using heuristics and the human experience and, in most industrial cases, even a feasible solution takes a considerable amount of trials to be found. Indeed, the optimization of a generic performance index along a path is complex, due to the dimension of the feasible-configuration space. This work faces this challenge by proposing an iterative layered-optimization method that integrates a Whale Optimization and an Ant Colony Optimization algorithm, the method allows the optimization of a user-defined objective function, along a working path, in order to achieve a quasi-optimal, collision free solution in the feasible-configuration space.

Step-changes in safety technologies have opened robotic cells to human workers in real industrial scenarios. However, the lack of methodologies for a productive and effective motion planning and scheduling of human–robot cooperative (HRC) tasks is still limiting the spread of HRC systems. Standard methods fail due to the high-variability of the robot execution time, caused by the necessity to continuously modify the robot motion to grant human safety. In this context, the paper introduces an innovative integrated motion planning and scheduling methodology that (i) provides a set of robot trajectories for each task as well as an interval on the robot execution time for each trajectory and (ii) optimizes, at relevant time steps, a task plan, minimizing the cycle time through trajectory selection, task sequence and task allocation. The application of the approach to an industrial case is presented and discussed.

According to both industrial practice and literature, multi-robot cell design and robot motion planning for vehicle spot welding are two sequential activities, managed by different functional units through different software tools. Due to this sequential computation, the whole process suffers from inherent inefficiency. In this work, a new methodology is proposed, that overcomes the above inefficiency through the simultaneous resolution of design and motion planning problems. Specifically, three mathematical models were introduced that (i) select and positions the resources, (ii) allocate the tasks to the resources and (iii) identify a coordinated robot motion plan. Based on the proposed methodology, we built three ad-hoc cases with the goal to highlight the relations between design, motion planning and environment complexity. These cases could be taken as reference cases so on. Moreover, results on an industrial case are presented.

Recently, the importance of sustainable manufacturing has been widely discussed. The optimization of energy consumption in product manufacture has been deeply analyzed, mainly focusing on the energy directly absorbed by the manufacturing process. On the contrary, this paper focuses on the analysis and optimization of the energy consumption related to auxiliary robotic assembly processes, contributing to the identification of sustainable manufacturing strategies for pick and place robots. It proposes a methodology for the automatic generation of robot trajectories and the sequencing of the robot task, while minimizing the energy consumption. A probabilistic roadmap is created to identify a collision-free and minimum energy consumption trajectory for each couple of feasible tasks. Trajectory power consumption is evaluated exploiting dynamic information coming from the real robot motion planner using a model that takes into account the energy behavior of motors and drives and their operative conditions. A set of generated trajectories is selected, defining the task sequence and minimizing the robot cycle time. The differences between the results deriving by employment of the energy consumption minimization criterion versus time minimization criterion are presented through a simplified case.

The multi-robot cell design for car-body spot welding is faced by industry as a sequence of tasks, where researches are focused on issues of the problem as a whole. In authors’ knowledge, none work in literature have suggested any formalization for the complete process. This paper tries to bridges the gap proposing coherent process formalization, and presenting a corresponding innovative architecture for the automatic optimal cell design. Specifically, the formalization involves the identification and allocation of the resources in terms of a set of decisional variables (e.g. robot model/positioning/number, welding gun models/allocation/number, welding point allocation etc.); then, the design optimization process minimizes the investment costs granting the cycle time. The multi-loop optimization architecture integrates both new algorithms and existent procedures from different fields. Test-bed showing its feasibility is reported.

Notwithstanding laser scanning technology is a mature technology used in widening application fields, a variety of barriers hinds its integration in robotized production lines. To face well know problems, as high-costs and not customizable solutions among others, the authors have developed a new family of laser scanning devices based on off the shelves and low cost hardware components and on a modular design that allow the customization of the device according to the specific application requirements. High accuracy is guaranteed through a computationally efficient non-parametric calibration procedure. Keeping limited the overall cost of the solution provided while increasing in general the sensing capabilities of an Industrial Robot (IR) and in particular the autonomous recognition of position, orientation and furthermore shape and geometrical features of objects within the robotic workspace, can boost the penetration of IRs in typical traditional industrial sectors where SMEs productive scenario is mainly characterized by manual fabrication processes, high product variability, small batches and little capital investments. High added value footwear industry is a paradigmatic example where hard automation is limited from one side by high variability of products and huge request of autonomous adaptation to cope with different loosely structured fabrication processes and from the other side by a low propensity towards high capital investment that make difficult the penetration of industrial robots. Within the framework of the European Project ROBOFOOT (EU-FP7-SMP), authors have conceived and developed a new family of low cost modular and reconfigurable laser scanners and successfully applied in the footwear fabrication scenario. Various operations should be improved by actual measure of the shoe being manufactured, and among the others, the identification of the relative positioning between the last (the plastic element on top of which is built the shoe) and the gripping device is extremely critical because it is still performed manually. Positioning errors in this phase are critical since all robot part-programs depend on the correct alignment of the last with the robot end-effector. To face this problem, a procedure, based on the Iterative Closest Points (ICP) optimization method, has been developed and integrated on board of the laser scanning device that directly communicates with the robot controller to adapt and autonomously correct the part-program to align the tool nominal path with the actual shoe being manufactured. Efficacy of the proposed methods has been proved by measuring the interaction forces between the tool and the last handled by a robot during different technological operations (roughing, polishing etc) typical of the shoe fabrication cycle.

Modern drug discovery for Central Nervous System pathologies has recently focused its attention to in vitro neuronal networks as models for the study of neuronal activities. Micro Electrode Arrays (MEAs), a widely recognized tool for pharmacological investigations, enable the simultaneous study of the spiking activity of discrete regions of a neuronal culture, providing an insight into the dynamics of networks. Taking advantage of MEAs features and making the most of the cross-correlation analysis to assess internal parameters of a neuronal system, we provide an efficient method for the evaluation of comprehensive neuronal network activity. We developed an intra network burst correlation algorithm, we evaluated its sensitivity and we explored its potential use in pharmacological studies. Our results demonstrate the high sensitivity of this algorithm and the efficacy of this methodology in pharmacological dose–response studies, with the advantage of analyzing the effect of drugs on the comprehensive correlative properties of integrated neuronal networks.

This work presents a new reconfigurable parallel-serial hybrid manipulator that can reach 7 degrees of freedom as a whole. The architecture of the parallel part is modular and it can be configured to obtain for the mobile base 3 or 4 degrees of freedom, or 3 degrees of freedom with redundant actuation. The paper presents the new parallel kinematic structure, analyzing the singularities, the workspace and the benefits of the redundant configuration. Finally, the first experimental results are presented.

The complete transformation of a racemate into one single enantiomer is defined as a deracemization. In amino acid chemistry, chemo-enzymatic deracemization is possible due to the ease of racemization of α-amino acids and the numerous enantioselective enzymatic systems operating on this class of compounds. Deracemization by dynamic kinetic resolution is a process in which the enantioselective catalyst is coupled with a second one promoting racemization of the reagent but not of the product. Deracemization by stereo-inversion is a convergent process in which the transformed isomer is finally converted into its enantiomer. These transformations can be applied for the preparation of enantiomerically pure α-amino acids of non-natural configuration or of l -α-amino acid of non-natural structure.