Predictive Maintenance: An Autoencoder Anomaly-Based Approach for a 3 DoF Delta Robot

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 DoF delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data are available. Due to the sequential nature of the data, nonlinearity of the system, and correlations between parameter time-series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method can calculate RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

Reinforcement Learning for Pick and Place Operations in Robotics: A Survey

The field of robotics has been rapidly developing in recent years, and the work related to training robotic agents with reinforcement learning has been a major focus of research. This survey reviews the application of reinforcement learning for pick-and-place operations, a task that a logistics robot can be trained to complete without support from a robotics engineer. To introduce this topic, we first review the fundamentals of reinforcement learning and various methods of policy optimization, such as value iteration and policy search. Next, factors which have an impact on the pick-and-place task, such as reward shaping, imitation learning, pose estimation, and simulation environment are examined. Following the review of the fundamentals and key factors for reinforcement learning, we present an extensive review of all methods implemented by researchers in the field to date. The strengths and weaknesses of each method from literature are discussed, and details about the contribution of each manuscript to the field are reviewed. The concluding critical discussion of the available literature, and the summary of open problems indicates that experiment validation, model generalization, and grasp pose selection are topics that require additional research.

Predictive Maintenance: An Autoencoder Anomaly-based Approach for a 3 DoF Delta Robot

Performing predictive maintenance (PdM) is challenging for many reasons. Dealing with large datasets which may not contain run-to-failure data (R2F) complicates PdM even more. When no R2F data are available, identifying condition indicators (CIs), estimating the health index (HI), and thereafter, calculating a degradation model for predicting the remaining useful lifetime (RUL) are merely impossible using supervised learning. In this paper, a 3 dof delta robot used for pick and place task is studied. In the proposed method, autoencoders (AEs) are used to predict when maintenance is required based on the signal sequence distribution and anomaly detection, which is vital when no R2F data is available. Due to the sequential nature of the data, non-linearity of the system, and correlations between parameter time series, convolutional layers are used for feature extraction. Thereafter, a sigmoid function is used to predict the probability of having an anomaly given CIs acquired from AEs. This function can be manually tuned given the sensitivity of the system or optimized by solving a minimax problem. Moreover, the proposed architecture can be used for fault localization for the specified system. Additionally, the proposed method is capable of calculating RUL using Gaussian process (GP), as a degradation model, given HI values as its input.

Sequential robot imitation learning from observations

This paper presents a framework to learn the sequential structure in the demonstrations for robot imitation learning. We first present a family of task-parameterized hidden semi-Markov models that extracts invariant segments (also called sub-goals or options) from demonstrated trajectories, and optimally follows the sampled sequence of states from the model with a linear quadratic tracking controller. We then extend the concept to learning invariant segments from visual observations that are sequenced together for robot imitation. We present Motion2Vec that learns a deep embedding space by minimizing a metric learning loss in a Siamese network: images from the same action segment are pulled together while being pushed away from randomly sampled images of other segments, and a time contrastive loss is used to preserve the temporal ordering of the images. The trained embeddings are segmented with a recurrent neural network, and subsequently used for decoding the end-effector pose of the robot. We first show its application to a pick-and-place task with the Baxter robot while avoiding a moving obstacle from four kinesthetic demonstrations only, followed by suturing task imitation from publicly available suturing videos of the JIGSAWS dataset with state-of-the-art [Formula: see text]% segmentation accuracy and [Formula: see text] cm error in position per observation on the test set.

Design and Analysis of a Novel Schönflies Motion Parallel Robot with Full Cycle Rotation

Due to the complex structures of multi-limbed parallel robots, conventional parallel robots generally have limited workspace, complex kinematics, and complex dynamics, which increases the application difficulty of parallel robot in industrial engineering. To solve the above problems, this paper proposes a single-loop Schönflies motion parallel robot with full cycle rotation, the robot can generate Schönflies motion by the most simplified structure. The novel Schönflies motion parallel robot is a two-limb parallel mechanism with least links and joints, and each limb is driven by a 2-degree of freedom (DOF) cylindrical driver (C-driver). The full cycle rotation of the output link is achieved by “…R-H…” structure, where the revolute (R) and helical (H) joints are coaxial. Mobility, kinematics, workspace and singularity analysis of novel Schönflies motion parallel robot are analyzed. Then, dynamic model is formulated based on the principle of virtual work. Moreover, a pick-and-place task is implemented by proposed Schönflies motion parallel robot and a serial SCARA robot, respectively. The simulation results verify the correctness of the theoretical model. Furthermore, dynamics performances of Schönflies motion parallel robot and serial SCARA robot are compared, which reveal the performance merits of proposed Schönflies motion parallel robot.

Tactile Sensor Data Interpretation for Estimation of Wire Features

At present, the tactile perception is essential for robotic applications when performing complex manipulation tasks, e.g., grasping objects of different shapes and sizes, distinguishing between different textures, and avoiding slips by grasping an object with a minimal force. Considering Deformable Linear Object manipulation applications, this paper presents an efficient and straightforward method to allow robots to autonomously work with thin objects, e.g., wires, and to recognize their features, i.e., diameter, by relying on tactile sensors developed by the authors. The method, based on machine learning algorithms, is described in-depth in the paper to make it easily reproducible by the readers. Experimental tests show the effectiveness of the approach that is able to properly recognize the considered object’s features with a recognition rate up to 99.9%. Moreover, a pick and place task, which uses the method to classify and organize a set of wires by diameter, is presented.

Hippocampal place cell sequences differ during correct and error trials in a spatial memory task

Theta rhythms temporally coordinate sequences of hippocampal place cell ensembles during active behaviors, while sharp wave-ripples coordinate place cell sequences during rest. We investigated whether such coordination of hippocampal place cell sequences is disrupted during error trials in a delayed match-to-place task. As a reward location was learned across trials, place cell sequences developed that represented temporally compressed paths to the reward location during the approach to the reward location. Less compressed paths were represented on error trials as an incorrect stop location was approached. During rest periods of correct but not error trials, place cell sequences developed a bias to replay representations of paths ending at the correct reward location. These results support the hypothesis that coordination of place cell sequences by theta rhythms and sharp wave-ripples develops as a reward location is learned and may be important for the successful performance of a spatial memory task.

Guidance and Control of a Planar Robot Manipulator Used in an Assembly Line

In order to achieve higher productivity and lower cost requirements, robot manipulators have been enrolled in assembling processes in last decades as well as other implementation areas such as transportation, welding, mounting, and quality control. As a new application of this field, the control of the synchronous movements of a planar robot manipulator and moving belt is dealt with in this study. Here, the mentioned synchronization is tried to be maintained in accordance with a guidance law which leads the robot manipulator to put selected components onto the specific slots on the moving belt without interrupting the assembling process. In this scheme, the control of the manipulator is carried out by considering the PI (proportional plus integral) control law. Having performed the relevant computer simulations based on the engagement geometry between the robot manipulator and moving belt, it is verified that the mentioned pick-and-place task can be successfully accomplished under different operating conditions.

Gait Parameters Measured from Wearable Sensors Reliably Detect Freezing of Gait in a Stepping in Place Task

Freezing of gait (FOG), a debilitating symptom of Parkinson’s disease (PD), can be safely studied using the stepping in place (SIP) task. However, clinical, visual identification of FOG during SIP is subjective and time consuming, and automatic FOG detection during SIP currently requires measuring the center of pressure on dual force plates. This study examines whether FOG elicited during SIP in 10 individuals with PD could be reliably detected using kinematic data measured from wearable inertial measurement unit sensors (IMUs). A general, logistic regression model (area under the curve = 0.81) determined that three gait parameters together were overall the most robust predictors of FOG during SIP: arrhythmicity, swing time coefficient of variation, and swing angular range. Participant-specific models revealed varying sets of gait parameters that best predicted FOG for each participant, highlighting variable FOG behaviors, and demonstrated equal or better performance for 6 out of the 10 participants, suggesting the opportunity for model personalization. The results of this study demonstrated that gait parameters measured from wearable IMUs reliably detected FOG during SIP, and the general and participant-specific gait parameters allude to variable FOG behaviors that could inform more personalized approaches for treatment of FOG and gait impairment in PD.