Search

The advent of collaborative robotics in industry has created a closer collaboration between humans and robots. This has led to the need to optimally schedule human and robot tasks to be robust enough to handle variability induced by time-related operator errors caused by the inability to accurately forecast the stochastic nature of human behavior. This article proposes an explicit scheme for tackling time-related variability in human tasks online in applications where humans intervene at a given time in the collaborative workspace. The planning problem is reformulated as a Travelling Salesman Problem combined with a 0/1-Knapsack Problem in order to actively define robot behavior when there is an unmodelled shift in the human execution time sequence. The method uses a two-level adaptation scheme. The first one (offline) inputs the predicted human behaviour in terms of time required for different activities at each work cycle, and then computes an overall task schedule to minimize the robot's operation time and idle time. The second one (online) involves the real-time detection of the human's timing to either stop the prescribed plan or enhance it in order to minimize robot and human idle times, thereby optimizing the sense of ease and fluency in the interaction. The system is simulated in different scenarios where the human predicted time is set to be wrong, and thus the system needs to account for such variation. The effect of the human predicted time on the task schedule is presented and helps to demonstrate the effectiveness of the proposed approach in dealing with human variability without prior modeling knowledge of the human task time distribution.

The emerging needs of human beings are pushing manufacturing companies from mass production to mass customization. The occurrence of these new challenges leads to a change of scenario where the robot no longer works isolated from human to a scenario in which the robot collaborates with the human in the same workspace (collaborative robotics). Wearable sensors using inertial measurement unit (IMU) are widely used to capture human upper body gestures in which the set of gesture being recognize is very large. However, foot gesture approach is starting to gain some places in applications where human’s hands are occupied when interacting with robots. This study presents an insole-based foot gesture recognition method for cobot operation mode selection. The insole is composed of an IMU and four force sensors. The classification algorithm uses a support vector machine (SVM) classifier based on features extracted by means of dynamic time warping (DTW) applied to only one reference gesture signal. Five human participants are used for the dataset. As a case study, the system was interfaced in real time (real-time classification algorithm) using a Simulink 2020a scheme with Universal Robots UR5 (5 kg payload). The worst-case recognition accuracy is around 88%. The algorithm is able to adequately discriminate between 10-foot gestures by means of a wearable insole sensor incorporated into the insole. Moreover, this study shows that, the control gesture can accurately be recognized from other current activities such as walking, turning, climbing the stairs, and similar.

Laboratoire d'Automatique et de Robotique interactive, Université du Québec à Chicoutimi, Québec, Canada LAR.i - UQAC, 16 août 2022 This dataset presents sensor's signal acquired for foot gesture recognition. This dataset was created after an ethic approbation (Research Ethic Board) at UQAC under the number 2022-837. The dataset is composed of 5 participants. For each participant, a set of 11 classes is presented. For each classes, one .csv files are included and are composed of 13 column. Each colum refers to a signal acquisition described in the following list : gesture_participant_X_GY etZ.tab X: Participant Identification Y: Gesture number Z: Trial number See gesture dictionary (type and description) in: Tchane Djogdom, G.V., Otis, M.JD. & Meziane, R. Dynamic time warping–based feature selection method for foot gesture cobot operation mode selection. Int J Adv Manuf Technol 126, 4521–4541 (2023). https://doi.org/10.1007/s00170-023-11280-w See video (real time application): Sharing_pHRI_iCDPM_RamyMeziane.mp4 Gesture crushing a cigarette (8 participants): Part X et Z.mat X: Participant identification Z: Trial number AccX -------- Accelaration on X axis AccY -------- Accelaration on Y axis AccZ -------- Accelaration on Z axis P -------- Euler angle Pitch R -------- Euler angle Roll Y -------- Euler angle Yaw FSR1 -------- Force sensor in forefoot (left side) FSR2 -------- Force sensor in forefoot (right side) FSR3 -------- Force sensor in heel or rearfoot (left side) FSR4 -------- Force sensor in heel or rearfoot (right side) GyX -------- Gyroscope on X axis GyY -------- Gyroscope on Y axis GyZ -------- Gyroscope on Z axis

Productivity can be increased by manipulators tracking the desired trajectory with some constraints. Humans as moving obstacles in a shared workspace are one of the most challenging problems for cable-driven parallel mechanisms (CDPMs) that are considered in this research. One of the essential primary issues in CDPM is collision avoidance among cables and humans in the shared workspace. This paper presents a model and simulation of a reconfigurable, fully constrained CDPM enabling detection and avoidance of cable–human collision. In this method, unlike conventional CDPMs where the attachment points are fixed, the attachment points on the rails can be moved (up and down on their rails), and then the geometric configuration is adapted. Karush–Kuhn–Tucker method is proposed, which focuses on estimating the shortest distance among moving obstacles (human limbs) and all cables. When cable and limbs are close to colliding, the new idea of reconfiguration is presented by moving the cable’s attachment point on the rail to increase the distance between the cables and human limbs while they are both moving. Also, the trajectory of the end effector remains unchanged. Some simulation results of reconfiguration theory as a new approach are shown for the eight-cable-driven parallel manipulator, including the workspace boundary variation. The proposed method could find a collision-free predefined path, according to the simulation results.

Advances in robotics are part of reducing the burden associated with manufacturing tasks in workers. For example, the cobot could be used as a “third-arm” during the assembling task. Thus, the necessity of designing new intuitive control modalities arises. This paper presents a foot gesture approach centered on robot control constraints to switch between four operating modalities. This control scheme is based on raw data acquired by an instrumented insole located at a human’s foot. It is composed of an inertial measurement unit (IMU) and four force sensors. Firstly, a gesture dictionary was proposed and, from data acquired, a set of 78 features was computed with a statistical approach, and later reduced to 3 via variance analysis ANOVA. Then, the time series collected data were converted into a 2D image and provided as an input for a 2D convolutional neural network (CNN) for the recognition of foot gestures. Every gesture was assimilated to a predefined cobot operating mode. The offline recognition rate appears to be highly dependent on the features to be considered and their spatial representation in 2D image. We achieve a higher recognition rate for a specific representation of features by sets of triangular and rectangular forms. These results were encouraging in the use of CNN to recognize foot gestures, which then will be associated with a command to control an industrial robot.

Cable interferences and collisions can lead to unpredictable behavior when a human physically interacts with a cable-driven parallel mechanism through its mobile platform. This paper presents an interactive control approach to prevent two cables in interference from folding onto one another, and thus preserve the cable-mechanism geometry. In this approach, the controller generates a repulsive force to prevent the cables from crossing. Therefore, the task is executed within the cable-driven parallel mechanism’s geometric limits. The repulsive force applied by the controller is derived from the gradient of the minimum distance between any pair of cables of the parallel mechanism. In turn, this minimum distance between cables is computed from the Karush-Kuhn-Tucker conditions of the associated optimization problem. The approach was tested and validated on a parallel mechanism driven by seven cables.

Depuis l'introduction des premiers robots interactifs en industrie, qui étaient à la base des systèmes collaboratifs supposés assister les humains dans les tâches pénibles et éprouvantes physiquement, le domaine de l’interaction humain-robot a fait des progrès considérables. Actuellement, les robots et les humains peuvent coexister conjointement dans un espace hybride afin de partager des tâches de production ou de partager le temps dans l’exécution d’une activité. Cependant, les nouveaux besoins industriels doivent conduire à des recherches pour adapter les chaînes de production et les rendre plus flexible et réactive à la modification des caractéristiques des produits. L’une des solutions consiste à adapter le manipulateur industriel présent dans les lignes de production à des fins d’interaction et de collaboration. Toutefois, la présence de l’humain dans l’espace de travail d’un manipulateur (cellule de travail hybride) représente un réel défi dans le domaine de l’interaction humain-robot puisque cela consiste à l’intégration d’une multitude de variétés de capteurs dits intelligents, surtout dans le cas de l’utilisation d’un mécanisme parallèle entraîné par des câbles. Pour cette raison, plusieurs problématiques ont été soulevées, pour lesquelles peu ou pas de recherches sont réalisées : cette nouvelle technologie est introduite sans entraînement de l’opérateur, l’évaluation de la sécurité a été très peu explorée lors de l’interaction et la performance de son utilisation demeure peu évaluée dans un contexte de réduction des troubles musculosquelettiques (TMS). Le projet de recherche vise l’étude et la conception d’un système interactif permettant d’améliorer la sécurité et l’intuitivité des personnes qui interagissent avec des mécanismes parallèles entraînés par des câbles. Deux modes d’interaction sont étudiés dans le système interactif, à savoir le partage des activités et l’interaction physique. En premier lieu, une méthode de génération de trajectoires avec é

Interactive robot doing collaborative work in hybrid work cell need adaptive trajectory planning strategy. Indeed, systems must be able to generate their own trajectories without colliding with dynamic obstacles like humans and assembly components moving inside the robot workspace. The aim of this paper is to improve collision-free motion planning in dynamic environment in order to insure human safety during collaborative tasks such as sharing production activities between human and robot. Our system proposes a trajectory generating method for an industrial manipulator in a shared workspace. A neural network using a supervised learning is applied to create the waypoints required for dynamic obstacles avoidance. These points are linked with a quintic polynomial function for smooth motion which is optimized using least-square to compute an optimal trajectory. Moreover, the evaluation of human motion forms has been taken into consideration in the proposed strategy. According to the results, the proposed approach is an effective solution for trajectories generation in a dynamic environment like a hybrid workspace.

In a near future, human and industrial manipulator will work together sharing a common workspace and production activities leading to a potential increase of accident. The research project concerns the adaptation of industrial robot already installed in a flexible manufacturing system in order to make it more interactive with human. The aim concerns the reduction of potential risk of injuries while working with an industrial robot. This paper presents a new inexpensive, non-intrusive, non-invasive, and non-vision-based system, for human detection and collision avoidance. One method investigated for improving safety concerns planning of safe path. This system recognizes human activities and locates operator's position in real time through an instrumented safety helmet. This safety helmet includes an IMU (Inertial Measurement Unit) and an indoor localization system such as RSSI (Received Signal Strength Indication) using industrial wireless equipment. A hybrid workspace including a flexible manufacturing system has been designed in order to practice experiments in an industrial-like environment.

It is known that head gesture and mental states can reflect some human behaviors related to a risk of accident when using machine-tools. The research works presented in this paper aim to reduce the number of injury and thus increase worker safety. Instead using camera, this paper presents a Smart Safety Helmet (SSH) in order to track head gestures and mental states of worker able to recognize anomalous behavior. Information extracted from SSH is used for computing risk level of accident (a safety level) for preventing and reducing injury or accidents. The SSH system is an inexpensive, non-intrusive, non-invasive, and non-vision-based system, which consists of 9DOF Inertial Measurement Unit (IMU) and dry EEG electrodes. A haptic device, such as vibrotactile motor, is integrated to the helmet in order to alert the operator when computed risk level (fatigue, high stress or error) reach a threshold. Once the risk level of accident breaks the threshold, a signal will be sent wirelessly to stop the relevant machine tool or process.