International Journal of Humanoid Robotics

Dexterous grasping of a novel object given a single view is an open problem. This paper makes several contributions to its solution. First, we present a simulator for generating and testing dexterous grasps. Second, we present a dataset, generated by this simulator, of 2.4 million simulated dexterous grasps of variations of 294 base objects drawn from 20 categories. Third, we combine an existing approach to learn a grasp generation model with three different learned evaluative models employing ResNet-50 or VGG16 as their visual backbone. Fourth, we train, and evaluate 17 variants of the resulting generative-evaluative architectures on the simulated dataset, showing improvement from 69.53% grasp success rate to 90.49%. Fifth, we present a real robot implementation and evaluate the four most promising variants, executing 196 real robot grasps in total. We show that our best architectural variant achieves a grasp success rate of 87.8% on real novel objects seen from a single view, improving on a baseline of 57.1%. Finally, we explore the inner workings of our best evaluative model and perform an extensive analysis of its results on the simulated dataset.

This paper presents design and performance of a prototype of new humanoid arm that has been developed at the LARM2 laboratory of the University of Rome “Tor Vergata”. This new arm, called LARMbot PK arm, is an upper limb that is designed for the LARMbot humanoid robot. LARMbot is a humanoid robot designed to move freely in open spaces, and able to adapt to task environment. Its objective is to transport objects weighing a few kilograms in order to facilitate the restocking of workstations, or to manage small warehouses and other tasks feasible for humanoids. The LARMbot PK arm is conceived as a solution that is designed on the basis of a parallel tripod structure using linear actuators to provide high agility of movement. This solution is designed with components that can be found on the market or can be created by 3D printing in order to offer a quality and price ratio well convenient for user-oriented humanoid robots. Experimental tests are discussed with the built prototype to demonstrate the capabilities of the proposed solution in terms of agility, autonomy, and power to validate the LARMbot PK arm solution as a satisfactory solution for the new upper limbs of the LARMbot humanoid robot.

The rapid development of computer vision raises a new research area involving patient care robots. Such robotic systems require fast target recognition at long ranges, where detecting smaller objects is notoriously challenging due to the cameras’ low resolution and noise. Spurred by these concerns, this paper develops a novel object recognition algorithm that solves these problems. Specifically, we amend YOLOv5 with our proposed sparse detection algorithm aiming to improve detection efficiency by separating the most significant context features and constructing smaller and less computational expensive models. Furthermore, we extend FReLU and suggest a novel activation function to improve recognition accuracy, which presents an extended nonlinearity increasing the expressiveness of the activation function. Finally, we propose sine annealing, which affords a trajectory that tends to cross over barriers and escape from local minima during training phase, addressing the challenging small object detection problem. The experimental results highlight that our algorithm has a lower memory consumption (Mem) value than the traditional YOLOv5 with a 5% boost down. Additionally, our method runs twice as fast as the traditional YOLOv5 while preserving accuracy, achieving more than 14.5 FPS on a medium-capability CPU. Overall, the detection results prove that our method can faster and accurately classifies and localizes most small-scaled objects.