RESUMEN

In this paper, balance control of a bicycle robot is studied without either a trail or a mechanical regulator when the robot moves in an approximately rectilinear motion. Based on the principle of moment balance, an input nonaffine nonlinear dynamics model of the bicycle robot is established. A driving velocity condition is proposed to maintain the robot balance. The nonaffine nonlinear system is transformed into an affine nonlinear system by defining the equivalent control. Subsequently, a feedback linearization controller is designed for the equivalent control. We design a combined control algorithm of synchronous policy iteration based on the actor-critic architecture. The actor neural network (NN) is designed based on the feedback linearization control law. Weight tuning laws for the critic and actor NNs are proposed. The system closed-loop stability and convergence of the NN weights are guaranteed based on the Lyapunov analysis. The optimality of the equivalent control policy is guaranteed. To satisfy the driving velocity condition, the values of the steering angle and driving velocity are determined based on the optimal equivalent control. The effectiveness of the proposed algorithm is verified through simulations and real experiments.

RESUMEN

Equipping soft robotic grippers with sensing and perception capabilities faces significant challenges due to their high compliance and flexibility, limiting their ability to successfully interact with the environment. In this work, we propose a sensorized soft robotic finger with embedded marker pattern that integrates a high-speed neuromorphic event-based camera to enable finger proprioception and exteroception. A learning-based approach involving a convolutional neural network is developed to process event-based heat maps and achieve specific sensing tasks. The feasibility of the sensing approach for proprioception is demonstrated by showing its ability to predict the two-dimensional deformation of three points located on the finger structure, whereas the exteroception capability is assessed in a slip detection task that can classify slip heat maps at a temporal resolution of 2 ms. Our results show that our proposed approach can enable complete sensorization of the finger for both proprioception and exteroception using a single camera without negatively affecting the finger compliance. Using such sensorized finger in robotic grippers may provide safe, adaptive, and precise grasping for handling a wide category of objects.

Asunto(s)

RESUMEN

The design of effective rehabilitation protocols relies on the ability to accurately assess the physical condition and the rehabilitative needs of the patient. Monitoring muscle fatigue can increase the usability of rehabilitative and restorative devices as it helps avoiding premature tiring and injury of patients whose resistance is already compromised. In this study, we collected EMG and accelerometer data from one healthy subject during a 30-minute walk on treadmill to determine the variations of muscle activation, and gait acceleration patterns, which, however subtle, could be interpreted as early indicators of muscle fatigue. Results show an increasing Tibialis Anterior (TA) and decreasing Soleus (SOL) and Gastrocnemius (GASL, GASM) activation towards the end of the task as compared to the beginning, as well as increasing acceleration peaks during the middle swing phase. By following the approach outlined here we can assess the efficiency and reduction of metabolic cost achieved by an exoskeleton. Furthermore, muscle fatigue may be linked to the efficacy of gait rehabilitation, where decreased muscle fatigue across sessions possibly indicates longer retention of benefits after training and increased walking capacity. This methodology can be used to benchmark novel exoskeletons, monitor fatigue to avoid premature tiring of patients, and optimize rehabilitation therapies.

Asunto(s)

RESUMEN

In this paper, a novel dynamic Vision-Based Measurement method is proposed to measure contact force independent of the object sizes. A neuromorphic camera (Dynamic Vision Sensor) is utilizused to observe intensity changes within the silicone membrane where the object is in contact. Three deep Long Short-Term Memory neural networks combined with convolutional layers are developed and implemented to estimate the contact force from intensity changes over time. Thirty-five experiments are conducted using three objects with different sizes to validate the proposed approach. We demonstrate that the networks with memory gates are robust against variable contact sizes as the networks learn object sizes in the early stage of a grasp. Moreover, spatial and temporal features enable the sensor to estimate the contact force every 10 ms accurately. The results are promising with Mean Squared Error of less than 0.1 N for grasping and holding contact force using leave-one-out cross-validation method.

RESUMEN

In recent years, robotic sorting is widely used in the industry, which is driven by necessity and opportunity. In this paper, a novel neuromorphic vision-based tactile sensing approach for robotic sorting application is proposed. This approach has low latency and low power consumption when compared to conventional vision-based tactile sensing techniques. Two Machine Learning (ML) methods, namely, Support Vector Machine (SVM) and Dynamic Time Warping-K Nearest Neighbor (DTW-KNN), are developed to classify material hardness, object size, and grasping force. An Event-Based Object Grasping (EBOG) experimental setup is developed to acquire datasets, where 243 experiments are produced to train the proposed classifiers. Based on predictions of the classifiers, objects can be automatically sorted. If the prediction accuracy is below a certain threshold, the gripper re-adjusts and re-grasps until reaching a proper grasp. The proposed ML method achieves good prediction accuracy, which shows the effectiveness and the applicability of the proposed approach. The experimental results show that the developed SVM model outperforms the DTW-KNN model in term of accuracy and efficiency for real time contact-level classification.

RESUMEN

This research work aims at realizing a new compliant robotic actuator for safe human-robotic interaction. In this paper, we present the modeling, control, and numerical simulations of a novel Binary-Controlled Variable Stiffness Actuator (BcVSA) aiming to be used for the development of a novel compliant robotic manipulator. BcVSA is the proof of concept of the active revolute joint with the variable recruitment of series-parallel elastic elements. We briefly recall the basic design principle which is based on a stiffness varying mechanism consisting of a motor, three inline clutches, and three torsional springs with stiffness values ( K 0 , 2 K 0 , 4 K 0 ) connected to the load shaft and the motor shaft through two planetary sun gear trains with ratios (4:1, 4:1 respectively). We present the design concept, stiffness and dynamic modeling, and control of our BcVSA. We implemented three kinds of Multiple Model Predictive Control (MPC) to control our actuator. The main motivation of choosing this controller lies in the fact that working principle of multiple MPC and multiple states space representation (stiffness level) of our actuator share similar interests. In particular, we implemented Multiple MPC, Multiple Explicit MPC, and Approximated Multiple Explicit MPC. Numerical simulations are performed in order to evaluate their effectiveness for the future experiments on the prototype of our actuator. The simulation results showed that the Multiple MPC, and the Multiple Explicit MPC have similar results from the robustness point of view. On the other hand, the robustness performance of Approximated Multiple Explicit MPC is not good as compared to other controllers but it works in the offline framework while having the capability to compute the sub-optimal results. We also performed the comparison of MPC based controllers with the Computed Torque Control (CTC), and Linear Quadratic Regulator (LQR). In future, we are planning to test the presented approach on the hardware prototype of our actuator.

RESUMEN

This paper explores the dynamics of separable coupled rigid body systems, a special class of constrained rigid body systems. These are defined as two systems that interact with each other by forces of contact, resulting in a reduction in dimensionality and complexity. The mechanics and consequences of this reduction are investigated here. The basic hypothesis and an example of the reduction in two successive steps are formulated. A simple mechanical biped model is developed and analyzed in some details by both system theoretical concepts and simulations. The main contribution of this work is the novel extension to the known dynamics of constrained rigid bodies. The modular, versatile and systematic formulation presented here is computationally efficient and has many applications in the studies of the human neuro-musculoskeletal system, robotic systems and humanoids, as well as clinical and sports biomechanics applications. Computer simulations are provided to demonstrate the feasibility and effectiveness of the methodology.