The development of vehicles that perceive their environment, in particular those using computer vision, indispensably requires large databases of sensor recordings obtained from real cars driven in realistic traffic situations. These datasets should be time shaped for enabling synchronization of sensor data from different sources. Furthermore, full surround environment perception requires high frame rates of synchronized omnidirectional video data to prevent information loss at any speeds.This paper describes an experimental setup and software environment for recording such synchronized multi-sensor data streams and storing them in a new open source format. The dataset consists of sequences recorded in various environments from a car equipped with an omnidirectional multi-camera, height sensors, an IMU, a velocity sensor, and a GPS. The software environment for reading these data sets will be provided to the public, together with a collection of long multi-sensor and multi-camera data streams stored in the developed format.
In this paper, a framework for guidance, navigation and control of marine vehicles is proposed. The focus is on application of unmanned surface vehicle for performing high accuracy measuring tasks. The desired maneuvering path is defined as a combination of standard path sections and delivered to the guidance system. The measurements are filtered and the unmeasurable states are estimated in navigation system and fed back to the guidance and control systems. An extended Kalman filter based approach is used in navigation system, in order to take the nonlinear behaviors of the system into consideration. The proposed control scheme is a modular system consisting of a cascade structure, where the unified inner loop is responsible for velocity control and the outer loop can be adapted independently to various missions. The model parameters are estimated based on subspace identification method using data obtained from a measuring vehicle, MESSIN. The results have been further used for design of control and navigation systems. The performance and effectiveness of the proposed framework are demonstrated on a model for a path following mission.
The need for fast and precise positioning of marine vessels is growing when it comes to offshore applications. Voith Schneider Propellers have huge potential for those tasks since their technical setup allows significantly faster reaction than propeller-based thrusters. This contribution presents a system for Dynamic Positioning using this propulsion system. A PID control structure with dynamic allocation of the manipulating variable to several thrusters was developed to achieve accurate positioning. Furthermore, a control loop extension for active roll damping was investigated. Lumped parameter models are used for controller synthesis. A simulation based validation of the control approach is presented.
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.