Search

We present a new approach to robot hand design specifically suited for successfully implementing robot learning methods to accomplish tasks in daily human environments. We introduce BaRiFlex, an innovative gripper design that alleviates the issues caused by unexpected contact and collisions during robot learning, offering robustness, grasping versatility, task versatility, and simplicity to the learning processes. This achievement is enabled by the incorporation of low-inertia actuators, providing high Back-drivability, and the strategic combination of Rigid and Flexible materials which enhances versatility and the gripper's resilience against unpredicted collisions. Furthermore, the integration of flexible Fin-Ray linkages and rigid linkages allows the gripper to execute compliant grasping and precise pinching. We conducted rigorous performance tests to characterize the novel gripper's compliance, durability, grasping and task versatility, and precision. We also integrated the BaRiFlex with a 7 Degree of Freedom (DoF) Franka Emika's Panda robotic arm to evaluate its capacity to support a trial-and-error (reinforcement learning) training procedure. The results of our experimental study are then compared to those obtained using the original rigid Franka Hand and a reference Fin-Ray soft gripper, demonstrating the superior capabilities and advantages of our developed gripper system., Comment: 8 pages, 6 figures, project website: https://robin-lab.cs.utexas.edu/bariflex/

In this study, we present the Differential Spiral Joint (DSJ) mechanism for variable stiffness actuation in tendon-driven robots. The DSJ mechanism semi-decouples the modulation of position and mechanical stiffness, allowing independent trajectory tracking in different parameter space. Past studies show that increasing the mechanical stiffness achieves the wider range of renderable stiffness, whereas decreasing the mechanical stiffness improves the quality of actuator decoupling and shock absorbance. Therefore, it is often useful to modulate the mechanical stiffness to balance the required level of stiffness and safety. In addition, the DSJ mechanism offers a compact form factor, which is suitable for applications where the size and weight are important. The performance of the DSJ mechanism in various areas is validated through a set of experiments.

We introduce a sample-efficient method for learning state-dependent stiffness control policies for dexterous manipulation. The ability to control stiffness facilitates safe and reliable manipulation by providing compliance and robustness to uncertainties. Most current reinforcement learning approaches to achieve robotic manipulation have exclusively focused on position control, often due to the difficulty of learning high-dimensional stiffness control policies. This difficulty can be partially mitigated via policy guidance such as imitation learning. However, expert stiffness control demonstrations are often expensive or infeasible to record. Therefore, we present an approach to learn Stiffness Control from Augmented Position control Experiences (SCAPE) that bypasses this difficulty by transforming position control demonstrations into approximate, suboptimal stiffness control demonstrations. Then, the suboptimality of the augmented demonstrations is addressed by using complementary techniques that help the agent safely learn from both the demonstrations and reinforcement learning. By using simulation tools and experiments on a robotic testbed, we show that the proposed approach efficiently learns safe manipulation policies and outperforms learned position control policies and several other baseline learning algorithms., Comment: Accepted at CoRL 2021

The three-layered, pressurized space suit glove worn by Extravehicular Activity (EVA) crew members during missions commonly causes hand and forearm fatigue. The Spacesuit RoboGlove (SSRG), a Phase VI EVA space suit glove modified with robotic grasp-assist capabilities, has been developed to augment grip strength in order to improve endurance and reduce the risk of injury in astronauts. The overall goals of this study were to i) quantify the neuromuscular modulations that occur in response to wearing a conventional Phase VI space suit glove (SSG) during a fatiguing task, and ii) determine the efficacy of Spacesuit RoboGlove (SSRG) in reversing the adverse neuromuscular modulations and restoring altered muscular activity to barehanded levels. Six subjects performed a fatigue sequence consisting of repetitive dynamic-gripping interspersed with isometric grip-holds under three conditions: barehanded, wearing pressurized SSG, and wearing pressurized SSRG. Surface electromyography (sEMG) from six forearm muscles (flexor digitorum superficialis (FDS), flexor carpi radialis (FCR), flexor carpi ulnaris (FCU), extensor digitorum (ED), extensor carpi radialis longus (ECRL), and extensor carpi ulnaris (ECU)) and subjective fatigue ratings were collected during each condition. Trends in amplitude and spectral distributions of the sEMG signals were used to derive metrics quantifying neuromuscular effort and fatigue that were compared across the glove conditions. Results showed that by augmenting finger flexion, the SSRG successfully reduced the neuromuscular effort needed to close the fingers of the space suit glove in more than half of subjects during two types of tasks. However, the SSRG required more neuromuscular effort to extend the fingers compared to a conventional SSG in many subjects. Psychologically, the SSRG aided subjects in feeling less fatigued during short periods of intense work compared to the SSG. The results of this study reveal the promise of the SSRG as a grasp-assist device that can improve astronaut performance and reduce the risk of injury by offsetting neuromuscular effort. Modifications to the experimental protocol are needed, however, to improve the outcome of the neuromuscular fatigue metrics and determine the effectiveness of SSRG in increasing astronaut endurance. Nevertheless, these findings will improve the understanding of astronaut-spacesuit interaction and provide direction toward designing improved spacesuit gloves and robotic-assist devices, like the SSRG.