No abstract

Deploying robots to explore venues that are inaccessible to humans, or simply inhospitable, has been a longstanding ambition of scientists, engineers, and explorers across numerous fields. The deep sea exemplifies an environment that is largely uncharted and denies human presence. Central to exploration is the capacity to deliver dexterous robotic manipulation to this unstructured environment. Unmanned underwater vehicles (UUVs) are successful in providing passive solutions for observation and mapping but currently are far from capable of delivering human‐level dexterity. The ones providing manipulation typically are UUVs coupled with position‐controlled hydraulic arms using disjoint controllers for navigation and manipulation that require expert operators. Ocean One is a humanoid underwater robot designed specifically for underwater manipulation. In this paper, we present Ocean One's control architecture that, through a collaboration between this humanoid robot and a human pilot, enables the deployment of dexterous robotic manipulation to the deep sea. We provide detailed descriptions of this architecture's two main components: first, a whole‐body controller that creates functional autonomy by coordinating manipulation, posture, and constraint tasks, and second, a set of haptic and visual human interfaces that enable intimate interaction while avoiding micromanagement. We test the presented methods in simulation and validate them in pool experiments and in two field deployments. On its maiden mission into the Mediterranean Sea, Ocean One explored the Lune, a French naval vessel that sank in 1664 off the coast of Toulon, France. In its second expedition, Ocean One assisted human divers in investigating underwater volcanic structures at Santorini, Greece.

Abstract-A challenging problem in motor control neuroimaging studies is the inability to perform complex human motor tasks given the Magnetic Resonance Imaging (MRI) scanner's disruptive magnetic fields and confined workspace. In this paper, we propose a novel experimental platform that combines Functional MRI (fMRI) neuroimaging, haptic virtual simulation environments, and an fMRI-compatible haptic device for real-time haptic interaction across the scanner workspace (above torso~.65x.40x.20m3 ). We implement this Haptic fMRI platform with a novel haptic device, the Haptic fMRI Interface (HFI), and demonstrate its suitability for motor neuroimaging studies. HFI has three degrees-of-freedom (DOF), uses electromagnetic motors to enable high-fidelity haptic rendering (>350Hz), integrates radio frequency (RF) shields to prevent electromagnetic interference with fMRI (temporal SNR >100), and is kinematically designed to minimize currents induced by the MRI scanner's magnetic field during motor displacement (<2cm). HFI possesses uniform inertial and force transmission properties across the workspace, and has low friction (.05-.30N). HFI's RF noise levels, in addition, are within a 3 Tesla fMRI scanner's baseline noise variation (~.85± .1%). Finally, HFI is haptically transparent and does not interfere with human motor tasks (tested for .4m reaches). By allowing fMRI experiments involving complex three-dimensional manipulation with haptic interaction, Haptic fMRI enables-for the first time-non-invasive neuroscience experiments involving interactive motor tasks, object manipulation, tactile perception, and visuo-motor integration.

No abstract

No abstract