Tensegrity structures emerged initially as an art form, have recently gained substantial interest among engineering researchers. The distinctive attribute of these structures is using pretensioned tensile elements connected to rigid bars to establish an equilibrium of the whole structure. Thanks to these elements, tensegrity structures are lightweight and yet robust. The main challenge impeding their widespread use is the intricate constrained nonlinear dynamics caused by the tensegrity topology. In this paper, we extend the dynamics of tensegrities by adding damping forces and incorporating forces along the connected strings passing through several nodes. As an experimental platform, a two-stage stacked tensegrity manipulator was constructed. The system was actuated using six actuators and the kinematic information of the system was acquired by measuring the node coordinates using optical motion capture. Afterward, we compared the structure behavior to the simulated one using our dynamics formulation. The results of these experiments show that our dynamics formulation is capable of representing the rich nonlinear dynamics of stacked tensegrity manipulators effectively.

No abstract

Recognizing objects and estimating their poses have a wide range of application in robotics. For instance, to grasp objects, robots need the position and orientation of objects in 3D. The task becomes challenging in a cluttered environment with different types of objects. A popular approach to tackle this problem is to utilize a deep neural network for object recognition. However, deep learning-based object detection in cluttered environments requires a substantial amount of data. Collection of these data requires time and extensive human labor for manual labeling. In this study, our objective was the development and validation of a deep object recognition framework using a synthetic depth image dataset. We synthetically generated a depth image dataset of 22 objects randomly placed in a 0.5 m × 0.5 m × 0.1 m box, and automatically labeled all objects with an occlusion rate below 70%. Faster Region Convolutional Neural Network (R-CNN) architecture was adopted for training using a dataset of 800,000 synthetic depth images, and its performance was tested on a real-world depth image dataset consisting of 2000 samples. Deep object recognizer has 40.96% detection accuracy on the real depth images and 93.5% on the synthetic depth images. Training the deep learning model with noise-added synthetic images improves the recognition accuracy for real images to 46.3%. The object detection framework can be trained on synthetically generated depth data, and then employed for object recognition on the real depth data in a cluttered environment. Synthetic depth data-based deep object detection has the potential to substantially decrease the time and human effort required for the extensive data collection and labeling.