The detection analysis of neurodegenerative diseases by means of low-cost sensors and suitable classification algorithms is a key part of the widely spreading telemedicine techniques. The choice of suitable sensors and the tuning of analysis algorithms require a large amount of data, which could be derived from a large experimental measurement campaign involving voluntary patients. This process requires a prior approval phase for the processing and the use of sensitive data in order to respect patient privacy and ethical aspects. To obtain clearance from an ethics committee, it is necessary to submit a protocol describing tests and wait for approval, which can take place after a typical period of six months. An alternative consists of structuring, implementing, validating, and adopting a software simulator at most for the initial stage of the research. To this end, the paper proposes the development, validation, and usage of a software simulator able to generate movement disorders-related data, for both healthy and pathological conditions, based on raw inertial measurement data, and give tri-axial acceleration and angular velocity as output. To present a possible operating scenario of the developed software, this work focuses on a specific case study, i.e., the Parkinson’s disease-related tremor, one of the main disorders of the homonym pathology. The full framework is reported, from raw data availability to pathological data generation, along with a common machine learning method implementation to evaluate data suitability to be distinguished and classified. Due to the development of a flexible and easy-to-use simulator, the paper also analyses and discusses the data quality, described with typical measurement features, as a metric to allow accurate classification under a low-performance sensing device. The simulator’s validation results show a correlation coefficient greater than 0.94 for angular velocity and 0.93 regarding acceleration data. Classification performance on Parkinson’s disease tremor was greater than 98% in the best test conditions.

In this work, the problem of reliably checking collisions between robot manipulators and the surrounding environment in short time for tasks, such as replanning and object grasping in clutter, is addressed. Geometric approaches are usually applied in this context; however, they can result not suitable in highly time-constrained applications. The purpose of this paper is to present a learning-based method able to outperform geometric approaches in clutter. The proposed approach uses a neural network (NN) to detect collisions online by performing a classification task on the input represented by the depth image or point cloud containing the robot gripper projected into the application scene. Specifically, several state-of-the-art NN architectures are considered, along with some customization to tackle the problem at hand. These approaches are compared to identify the model that achieves the highest accuracy while containing the computational burden. The analysis shows the feasibility of the robot collision checker based on a deep learning approach. In fact, such approach presents a low collision detection time, of the order of milliseconds on the selected hardware, with acceptable accuracy. Furthermore, the computational burden is compared with state-of-the-art geometric techniques. The entire work is based on an industrial case study involving a KUKA Agilus industrial robot manipulator at the Technology $\&$ Innovation Center of KUKA Deutschland GmbH, Germany. Further validation is performed with the Amazon Robotic Manipulation Benchmark (ARMBench) dataset as well, in order to corroborate the reported findings.

In this paper, the problem of retrieving a target object from a cluttered environment through a mobile manipulator is considered. The task is solved by combining Task and Motion Planning; in detail, at a higher level, the task planner is in charge of planning the sequence of objects to relocate while, at a lower level, the motion planner is in charge of planning the robot movements taking into consideration robot and environment constraints. In particular, the latter provides feedback to the former about the feasibility of object sequences; this information is exploited to train a Reinforcement Learning agent that, according to an objects-weight based metrics, builds a dynamic decision-tree where each node represents a sequence of relocated objects, and edge values are weights updated via Q-learning-inspired algorithm. Three learning strategies differing in how the tree is explored are analysed. Moreover, each exploration approach is performed using two different tree-search methods: the Breadth first and Depth first techniques. Finally, the proposed learning strategies are numerically validated and compared in three scenarios of growing-complexity.