In this paper, we present a method for pose-estimate-based target tracking (PBTT) that enables the performance of autonomous aerial manipulation operations in unstructured environments using fully on-board computation for both UAV localization and target tracking. The PBTT method does not depend on extracting traditional visual features (e.g. using SIFT, SURF, ORB, etc.) on or near the target. Instead, the algorithm combines input from an RGB-D camera and the UAV's position estimator (which utilizes a downward-facing optical flow camera for horizontal localization) to track a target point selected by a human operator. The effectiveness of the PBTT method is evaluated through several autonomous flight tests performed with the Interacting-Boomcopter (I-BC) UAV platform in unstructured environments and in the presence of light wind disturbances.

This paper presents a microforce-sensing mobile microrobot (μFSMM) for use in automated micromanipulation tasks. The design consists of a planar vision-based microforce sensor end-effector, while the microrobot body is made of chemically etched nickel that is driven by an exterior magnetic field. With a known stiffness, the manipulation forces can be determined from observing the deformation of the end-effector through a camera attached to an optical microscope. After analyzing and calibrating the stiffness of a micromachined prototype, the mobility and in situ force-sensing capabilities are verified through real-time, closed loop, force controlled manipulation tests with automated path planning and navigation. The calibrated stiffness of the microforce sensor end-effectors fabricated is on the order of 10-3N/m. The online (real time) force-sensing resolution is approximately 1.5 μN. The sensing range is 0-20 μN along the two planar directions. In automated micromanipulation experiments with a microcomponent, the μFSMM utilizes realtime force control to apply a prescribed force of 6 μN to a desired location on a fixed microobject. Similarly, in another automated micromanipulation experiment, the μFSMM demonstrates the use of real-time force control to limit the manipulation forces experienced by the microobject to remain below a threshold of 12 μN.