Abstract: Provided is a method for predicting a location of a fast-moving object. The method includes receiving event information from an event camera, the event information corresponding to an event detected by the event camera, generating a Binary Event History Image (BEHI) based on the event information, providing the BEHI as an input to an event-based neural network, obtaining, as an output of the event-based neural network, a first predicted location of the fast-moving object, a normal distribution indicating prediction uncertainty of the predicted location, and a predicted time-to-collision (TTC). The method further includes estimating a second predicted location of the fast-moving object based on the first predicted location, the normal distribution, and the predicted TTC output by the event-based neural network, and actuating a mechanical catching device to be at the second predicted location.

Abstract: A collaborative control method for tracking Lagrangian coherent structures (LCSs) and manifolds on flows employs at least three autonomous sensors each equipped with a local flow sensor for sensing flow in a designated fluid medium, e.g. water or air. A first flow sensor is a tracking sensor while the other sensors are herding sensors for controlling and determining the actions of the tracking sensor. The tracking sensor is positioned with respect to the herding sensors in the fluid medium such that the herding sensors maintain a straddle formation across a boundary; obtaining a local fluid flow velocity measurement from each sensor. A global fluid flow structure is predicted based on the local flow velocity measurements. In a water medium, mobile autonomous underwater flow sensors may be deployed with each tethered to a watersurface craft.

Abstract: A collaborative control method for tracking Lagrangian coherent structures (LCSs) and manifolds on flows employs at least three autonomous underwater vehicles (AUVs) each equipped with a local flow sensor. A first flow sensor is a tracking sensor and the other sensors are herding sensors for controlling and determining the actions of the tracking sensor. The AUVs are deployed in a body of water whereby the tracking sensor is positioned with respect to the herding sensors such that the herding sensors maintain a straddle formation across a boundary. A local flow velocity measurement is obtained from each AUV; and based on the local flow velocity measurements a global flow structure that is useful for plotting an optimal course for a vessel between two or more locations is predicted.

Abstract: A collaborative control method for tracking Lagrangian coherent structures (LCSs) and manifolds on flows employs at least three autonomous sensors each equipped with a local flow sensor for sensing flow in a designated fluid medium, e.g. water or air. A first flow sensor is a tracking sensor while the other sensors are herding sensors for controlling and determining the actions of the tracking sensor. The tracking sensor is positioned with respect to the herding sensors in the fluid medium such that the herding sensors maintain a straddle formation across a boundary; obtaining a local fluid flow velocity measurement from each sensor. A global fluid flow structure is predicted based on the local flow velocity measurements. In a water medium, mobile autonomous underwater flow sensors may be deployed with each tethered to a watersurface craft.

Abstract: A collaborative control method for tracking Lagrangian coherent structures (LCSs) and manifolds on flows employs at least three autonomous underwater vehicles (AUVs) each equipped with a local flow sensor. A first flow sensor is a tracking sensor and the other sensors are herding sensors for controlling and determining the actions of the tracking sensor. The AUVs are deployed in a body of water whereby the tracking sensor is positioned with respect to the herding sensors such that the herding sensors maintain a straddle formation across a boundary. A local flow velocity measurement is obtained from each AUV; and based on the local flow velocity measurements a global flow structure that is useful for plotting an optimal course for a vessel between two or more locations is predicted.