Search

In this paper, a differential neural network (DNN) implemented as a robust observer estimates the dynamics of perturbed uncertain nonlinear systems affected by exogenous unknown inputs. In the first stage, the identification error converges into a neighborhood around the origin. Then, the second-order sliding mode supertwisting algorithm implemented as a robust exact differentiator reconstructed the unknown inputs. The approach proposed in this paper can be applied in the case of full access to the state vector (identification problem) and in the case of partial access to the state vector (estimation problem). In the second case, the nonlinear system under study must have well-defined full relative degree with respect to the unknown input. Numerical examples showed the effectiveness of the proposed algorithm. The first example tested the DNN working as an identifier into a mathematical model describing the dynamics of a spatial minisatellite. The second example (with a DNN implemented as an observer) tested the methodology of this paper over a single link flexible robot manipulator represented in a canonical (Brunovsky) form. In both examples, the mathematical models served as data generators in the testing of the neural networks. Even when not exact mathematical description of both models was used in the input estimation, the accuracy obtained with the DNN is comparable with the case of applying a high-order differentiator with complete knowledge of the plant.

Robot-assisted rehabilitation is an exciting field which aims to incorporate relevant developments in robotics related to rehabilitation with the intention of defining new methodologies for intervening problems related to muscular, neuromuscular, and osseous diseases. In this study, a systematic and comprehensive literature analysis is conducted to identify the contribution of artificial intelligence applied on robotic devices for motor rehabilitation, highlighting its relation with the rehabilitation cycle, and clarifying the prospective research directions in the development of more autonomous rehabilitation procedures. Considering this main goal, a summarized definition of general rehabilitation techniques is established. Then, such definition is particularized for technological-aided rehabilitating medical treatments implementing artificial intelligence methods, identifying the sections included within the process and the associated interaction degrees. This generic definition is analyzed using the current literature in muscle-skeletal treatment robotics as reference framework. This analysis considers the components and sections included in rehabilitation sequence. This review also describes a more in-depth description of the principal categories for classifying therapeutic robotic devices, including descriptions of the main past and present outcomes for each class of medical robotics for rehabilitation. The existing challenges and open options to develop more efficient autonomous (with the application of diverse artificial intelligence approaches) rehabilitating procedures are discoursed. Besides, taking into account this comprehensive review, a sequence of technical requires which must be taken into consideration when designing, developing and implementing autonomous robotic devices aimed to contribute to rehabilitation medical systems are deliberated. A brief description of the application of artificial intelligence and autonomous medical rehabilitation treatment is analyzed in terms of the exciting technical challenges and the ethical compromises that such a treatment option implies.