1,721,074 research outputs found
Soft Robotics: From scientific challenges to technological applications
No full textSoft robotics is a recent and rapidly growing field of research, which aims at unveiling the principles for building robots that include soft materials and compliance in the interaction with the environment, so as to exploit so-called embodied intelligence and negotiate natural environment more effectively. Using soft materials for building robots poses new technological challenges: the technologies for actuating soft materials, for embedding sensors into soft robot parts, for controlling soft robots are among the main ones. This is stimulating research in many disciplines and many countries, such that a wide community is gathering around initiatives like the IEEE TAS TC on Soft Robotics and the RoboSoft CA - A Coordination Action for Soft Robotics, funded by the European Commission. Though still in its early stages of development, soft robotics is finding its way in a variety of applications, where safe contact is a main issue, in the biomedical field, as well as in exploration tasks and in the manufacturing industry. And though the development of the enabling technologies is still a priority, a fruitful loop is growing between basic research and application-oriented research in soft robotics
A vision for future bioinspired and biohybrid robots
No full textBioinspired and biohybrid robots can help respond to diverse, sustainable application needs
RL-Based Adaptive Controller for High Precision Reaching in a Soft Robot Arm
Full text linkHigh precision control of soft robots is challenging due to their stohcastic behavior and material-dependent nature. While RL has been applied in soft robotics, achieving precision in task execution is still a long way off. Traditionally, RL requires substantial data for convergence, often obtained from a training environment. Yet, despite exhibiting high accuracy in the training environment, RL-policies often fall short in reality due to the training-to-reality gap, and the performance is exacerbated by the stochastic nature of soft robots. This study paves the way for the implementation of RL for soft robot control to achieve high precision in task execution. Two sample-efficient adaptive control strategies are proposed that leverage the RL-policy. The schemes can overcome stochasticity, bridge the training-to-reality gap, and attain desired accuracy even in challenging tasks, such as obstacle avoidance. In addition, deliberate and reversible damage is induced to the pneumatic actuation chamber, altering the soft robot's behavior to test the adaptability of our solutions. Despite the damage, desired accuracy was achieved in most scenarios without needing to retrain the RL-policy
Simulation and Analysis of Microspines Interlocking Behavior on Rocky Surfaces: An In-Depth Study of the Isolated Spine
No full textMicrospine grippers address a large variety of possible applications, especially in field robotics and manipulation in extreme environments. Predicting and modeling the gripper behavior remains a major challenge to this day. One of the most complex aspects of these predictions is how to model the spine to rock interaction of the spine tip with the local asperity. This paper proposes a single spine model, in order to fill the gap of knowledge in this specific field. A new model for the anchoring resistance of a single spine is proposed and discussed. The model is then applied to a simulation campaign. With the aid of simulations and analytic functions, we correlated performance characteristics of a spine with a set of quantitative, macroscopic variables related to the spine, the substrate and its usage. Eventually, this paper presents some experimental comparison tests and discusses traversal phenomena observed during the tests
Cerebellar adaptive mechanisms explain the optimal control of saccadic eye movements
No full textCerebellar synaptic plasticity is vital for adaptability and fine tuning of goal-directed movements. The perceived sensory errors between desired and actual movement outcomes are commonly considered to induce plasticity in the cerebellar synapses, with an objective to improve desirability of the executed movements. In rapid goal-directed eye movements called saccades, the only available sensory feedback is the direction of reaching error information received only at end of the movement. Moreover, this sensory error dependent plasticity can only improve the accuracy of the movements, while ignoring other essential characteristics such as reaching in minimum-time. In this work we propose a rate based, cerebellum inspired adaptive filter model to address refinement of both accuracy and movement-time of saccades. We use optimal control approach in conjunction with information constraints posed by the cerebellum to derive bio-plausible supervised plasticity rules. We implement and validate this bio-inspired scheme on a humanoid robot. We found out that, separate plasticity mechanisms in the model cerebellum separately control accuracy and movement-time. These plasticity mechanisms ensure that optimal saccades are produced by just receiving the direction of end reaching error as an evaluative signal. Furthermore, the model emulates encoding in the cerebellum of movement kinematics as observed in biological experiments
Model-Based Reinforcement Learning for Closed-Loop Dynamic Control of Soft Robotic Manipulators
No full textDynamic control of soft robotic manipulators is an open problem yet to be well explored and analyzed. Most of the current applications of soft robotic manipulators utilize static or quasi-dynamic controllers based on kinematic models or linearity in the joint space. However, such approaches are not truly exploiting the rich dynamics of a soft-bodied system. In this paper, we present a model-based policy learning algorithm for closed-loop predictive control of a soft robotic manipulator. The forward dynamic model is represented using a recurrent neural network. The closed-loop policy is derived using trajectory optimization and supervised learning. The approach is verified first on a simulated piecewise constant strain model of a cable driven under-Actuated soft manipulator. Furthermore, we experimentally demonstrate on a soft pneumatically actuated manipulator how closed-loop control policies can be derived that can accommodate variable frequency control and unmodeled external loads
Multimodal sensory representation for object classification via neocortically-inspired algorithm
No full textThis study reports our initial work on multimodal sensory representation for object classification. To form a sensory representation we used the spatial pooling phase of the Hierarchical Temporal Memory - a Neocortically-inspired algorithm. The classification task was carried out on the Washington RGB-D dataset in which the employed method provides extraction of non-hand engineered representations (or features) from different modalities which are pixel values (RGB) and depth (D) information. These representations, both early and lately fused, were used as inputs to a machine learning algorithm to perform object classification. The obtained results show that using multimodal representations significantly improve (by 5 %) the classification performance compared to a when a single modality is used. The results also indicate that the performed method is effective for multimodal learning and different sensory modalities are complementary for the object classification. Therefore, we envision that this method can be employed for object concept formation that requires multiple sensory information to execute cognitive tasks
- …
