Search results

Most manufacturing plants choose the easy way of completely separating human operators from robots to prevent accidents, but as a result, it dramatically affects the overall quality and speed that is expected from human–robot collaboration. It is not an easy task to ensure human safety when he/she has entered a robot’s workspace, and the unstructured nature of those working environments makes it even harder. The purpose of this paper is to propose a real-time robot collision avoidance method to alleviate this problem.

In this paper, a model is trained to learn the direct control commands from the raw depth images through self-supervised reinforcement learning algorithm. To reduce the effect of sample inefficiency and safety during initial training, a virtual reality platform is used to simulate a natural working environment and generate obstacle avoidance data for training. To ensure a smooth transfer to a real robot, the automatic domain randomization technique is used to generate randomly distributed environmental parameters through the obstacle avoidance simulation of virtual robots in the virtual environment, contributing to better performance in the natural environment.

The method has been tested in both simulations with a real UR3 robot for several practical applications. The results of this paper indicate that the proposed approach can effectively make the robot safety-aware and learn how to divert its trajectory to avoid accidents with humans within the workspace.

The method has been tested in both simulations with a real UR3 robot in several practical applications. The results indicate that the proposed approach can effectively make the robot be aware of safety and learn how to change its trajectory to avoid accidents with persons within the workspace.

This paper provides a novel collision avoidance framework that allows robots to work alongside human operators in unstructured and complex environments. The method uses end-to-end policy training to directly extract the optimal path from the visual inputs for the scene.

A transmission tower usually experiences bolt loosening under long-term alternating cyclic load, which may lead to collapse of the tower in extreme operating conditions. The paper aims to propose a data-driven identification method for bolt looseness of complicated tower structures based on reduced-order models and numerical simulations to perceive and evaluate the health state of a tower in operation.

The equivalent stiffnesses of three types of bolt joints under various loosening scenarios are numerically determined by three-dimensional finite element (FE) simulations. The order of the FE model of a tower structure with bolt loosening is reduced by means of the component modal synthesis method, and the dynamic responses of the reducer-order model under calibration loads are simulated and used to create the dataset. An identification model for bolt looseness of the tower structure based on convolutional neural networks driven by the acceleration sensors is constructed.

An identification model for bolt looseness of the tower structure based on convolutional neural networks driven by the acceleration sensors is constructed and the applicability of the model is investigated. It is shown that the proposed method has a high identification accuracy and strong robustness to data noise and data missing. Meanwhile, the method is less dependent on the number and location of sensors and is easier to apply in real transmission lines.

This paper proposes a data-driven identification method for bolt looseness of a complicated tower structure based on reduced-order models and numerical simulations. Non-linear relationships between equivalent stiffness of bolted joints and bolt preload depicting looseness are obtained and reduced-order model of tower structure with bolt looseness is established. Finally, this paper investigates applicability of identification model for bolt looseness.

The purpose of this paper is to solve the ground verification and test method for space robot system capturing the target satellite based on visual servoing with time-delay in 3-dimensional space prior to space robot being launched.

To implement the approaching and capturing task, a motion planning method for visual servoing the space manipulator to capture a moving target is presented. This is mainly used to solve the time-delay problem of the visual servoing control system and the motion uncertainty of the target satellite. To verify and test the feasibility and reliability of the method in three-dimensional (3D) operating space, a set of ground hardware-in-the-loop simulation verification systems is developed, which adopts the end-tip kinematics equivalence and dynamics simulation method.

The results of the ground hardware-in-the-loop simulation experiment validate the reliability of the eye-in-hand visual system in the 3D operating space and prove the validity of the visual servoing motion planning method with time-delay compensation. At the same time, owing to the dynamics simulator of the space robot added in the ground hardware-in-the-loop verification system, the base disturbance can be considered during the approaching and capturing procedure, which makes the ground verification system realistic and credible.

The ground verification experiment system includes the real controller of space manipulator, the eye-in-hand camera and the dynamics simulator, which can veritably simulate the capturing process based on the visual servoing in space and consider the effect of time delay and the free-floating base disturbance.

The performance measure approach (PMA) is widely adopted for reliability analysis and reliability-based design optimization because of its robustness and efficiency compared to reliability index approach. However, it has been reported that PMA involves repeat evaluations of probabilistic constraints therefore it is prohibitively expensive for many large-scale applications. In order to overcome these disadvantages, the purpose of this paper is to propose an efficient PMA-based reliability analysis technique using radial basis function (RBF).

The RBF is adopted to approximate the implicit limit state functions in combination with latin hypercube sampling (LHS) strategy. The advanced mean value method is applied to obtain the most probable point (MPP) with the prescribed target reliability and corresponding probabilistic performance measure to improve analysis accuracy. A sequential framework is proposed to relocate the sampling center to the obtained MPP and reconstruct RBF until a criteria is satisfied.

The method is shown to be better in the computation time to the PMA based on the actual model. The analysis results of probabilistic performance measure are accurately close to the reference solution. Five numerical examples are presented to demonstrate the effectiveness of the proposed method.

The main contribution of this paper is to propose a new reliability analysis technique using reconstructed RBF approximate model. The originalities of this paper may lie in: investigating the PMA using metamodel techniques, using RBF instead of the other types of metamodels to deal with the low efficiency problem.