We present a look-ahead based trajectory planning algorithm for computation of dynamically feasible trajectories for Unmanned Sea Surface Vehicles (USSV) operating in high seas states. The algorithm combines A* based heuristic search and locally bounded optimal planning under motion uncertainty using a variation of the minimax game-tree search. This allows the algorithm to compute trajectories that explicitly consider the possibility of the vehicle safely deviating from its original course due to the ocean waves within a specified lookahead region. The algorithm can adapt its search based on the user-specified risk thresholds. Moreover, the algorithm produces a contingency plan as a part of the computed trajectory. We demonstrate the capabilities of the algorithm using simulations.
Often generating training instructions for virtual environments is a long and tedious process. In this paper, we discuss the development of a virtual environment (VE) instruction generating tool called Virtual Author which is the main component of the Virtual Training Studio (VTS). VTS is a virtual environment-based training system that provides instructors with a tool to create training instructions and allows trainees to learn assembly operations in a personal virtual environment. The Virtual Author tool is designed to allow an instructor to perform virtual demonstrations using CAD models in the virtual environment in order to quickly generate VE-based training instructions for use in VTS. This paper describes the algorithms used to carry out motion smoothening of instructor's actions, automated text instruction generation based on part and assembly motions, and extraction of alignment constraints from 3D CAD models to support instruction generation. We also present examples to illustrate how the use of the Virtual Author tool leads to a significant reduction in the training instruction generation time.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.