Autonomous system (mathematics)

About: Autonomous system (mathematics) is a research topic. Over the lifetime, 1648 publications have been published within this topic receiving 38373 citations.

Autonomous 3D Modeling of Unknown Objects for Active Scene Exploration

Abstract: The thesis Autonomous 3D Modeling of Unknown Objects for Active Scene Exploration presents an approach for efficient model generation of small-scale objects applying a robot-sensor system Active scene exploration incorporates object recognition methods for analyzing a scene of partially known objects as well as exploration approaches for autonomous modeling of unknown parts Here, recognition, exploration, and planning methods are extended and combined in a single scene exploration system, enabling advanced techniques such as multi-view recognition from planned view positions and iterative recognition by integration of new objects from a scene In household or industrial environments, novel and unknown objects appear regularly and need to be modeled in order for a robot to be able to recognize the object and manipulate it Nowadays, 3D models of hand-sized objects are usually obtained by manual scanning which represents a tedious and time consuming task for the human operator For an autonomous system to take over this task, the robot needs to autonomously obtain the model within the object scene and thereby cope with challenges such as bad incidence angle, sensor noise, reflections, collisions or occlusions In this thesis, sensor paths denoted as Next-Best-Scan are iteratively determined by a boundary search and surface trend estimation of the acquired model In each iteration, 3D measurements are merged into a probabilistic voxel space, which considers sensor uncertainties It is used for scene exploration, planning collision-free paths, avoiding occlusions, and verifying the poses of the recognized objects against all previous information In order to account for both a fast acquisition rate and a high model quality, a Next-Best-Scan is selected that maximizes a utility function integrating an exploration and a mesh-quality component The mesh-quality component allows for the algorithm to terminate once the quality required by the application is reached The Next-Best-Scan algorithm is verified in simulation by comparison with state-of-the-art approaches concerning processing time and final model quality and in real scenes The versatile applicability of the method is shown by several experiments with different cultural heritage, household, and industrial objects Modeling of single objects is evaluated on an industrial and a mobile robot On the industrial robot, the robot moves around the object, whereas on the mobile robot, the object is moved in front of an external range sensor using the same method For modeling of larger workspaces, the mobile platform moves around the scene The active scene exploration approach is demonstrated using several scenes with different levels of complexity Here, Next-Best-Scan planning is performed for improving both recognition and modeling Concluding, the developed methods enable the robot to learn object models of unknown objects, to directly apply these models to the individual application and therefore to become more autonomous Here, the autonomously acquired object models are successively inserted into an object database and utilized by an object recognition module

Multi-Path Planning Method for UAVs Swarm Purposes

Abstract: Advances in the field of robotics have culminated in the cooperative and autonomous use of different types of vehicles, to efficiently tackle a wide range of tasks. One of the main elements, to allow the use of a collaborative and autonomous system of multiple vehicles, is the planning of safe routes, which the movement of different agents is guaranteed through the work area, without colliding with obstacles in the environment. Consequently, in this document, multiple path planning is proposed for a Multi-Robot System consisting of several Unmanned Aerial Vehicles; based on the creation of Probabilistic Roadmaps (PRM). The objective of this paper is the implementation of a multi-path planning method, for a Multi-Robot system, which must achieve different objectives in a set of proposed situations and the demonstration that the development of Probabilistic Roadmaps constitute an optimal and effective solution for multi-path problem solving. In addition, this solution is integrated in a Robot Operating System (ROS) architecture that provides simple implementation of the algorithms presented in a real fleet of vehicles. Finally, the results obtained show that methods based on PRM create optimal solutions in terms of computing time in swarms of scalable agents and for different situations analyzed, along with the possible integration in a versatile framework such as ROS.

Human–AI Collaboration

Abstract: The ability to collaboratively reason within an autonomous information processing system denotes a need and an ability to infer about information, knowledge, observations, and experiences to affect changes within the system which support performing new tasks previously unknown, or performing tasks already learned, more efficiently and effectively (Crowder, Reusable launch vehicle automated mission planning concepts, Lockheed Martin, Littleton, 1996). The act of reasoning and inferring enables an autonomous system to construct or modify representations of concepts or knowledge that the system is experiencing and learning. Artificial reasoning enables an Artificially Intelligent System (AIS) to flesh out skeletal or incomplete information or specifications about one or more of its domains (self-assessment). The research described here details architectures and algorithms for a cognitive system of Intelligent information Software Agents (ISAs) to facilitate collaborative communication between humans and artificially intelligent systems (Scally et al., Proceedings of the Advanced Maui Optical and Space Surveillance Technologies Conference, Maui, HI, 2011).

Vision-based Control for Unmanned Rotorcraft

Abstract: Removing the pilot from the cockpit of an aircraft leads to complex control challenges. An autonomous system must be capable of obtaining real-time position fixes for which some sensors are commercially available. For example, global positioning systems can give a definitive answer to the problem of knowing the current location. Problems can arise when using global positioning systems for navigation due to the availability of signals, the uncertainty in physical data or when tracking moving objects. Using visual sensors facilitates the tracking of moving targets within visual range. Rotorcraft are ideally suited to the tracking of targets, such as vehicles, which may be stationary for periods, due to their ability to hover in a fixed point in space for short periods. The ability to autonomously track and land on a target that is able to move in up to 6 degrees of freedom would have numerous applications, and would benefit from vision-based control. The work presented here is a first step toward achieving this aim through investigation of limited degree of freedom models in order to explore the capabilities of vision software as a control system sensor, and integration within control system architectures. In all, three experiments are presented; single degree of freedom pitch control using vision feedback as the main sensor; yaw control of an Ikarus ECO-8 model helicopter using inertial sensors and drift correction through visual control; and moving target tracking in 2 degrees of freedom incorporating a vision sensor alongside more standard sensor solutions. The initial work presented here shows that vision-based control of a rotary wing unmanned vehicle is a challenging yet feasible problem.

Work In Progress - building MatBot - a platform for freshman robotics with use throughout the engineering curriculum

Abstract: We intend to develop a unique "platform for education" that will be developed initially for the George Fox University freshmen engineering sequence and will enable our students to utilize a familiar platform in future engineering courses, providing for a cohesive design experience throughout the curriculum. Building on the foundation provided by the TekBot - Oregon State University's "Platform for Learning," we are developing MatBot. MatBot development is driven by two fundamental principles: 1) autonomous system control via Matlab and 2) independent module control. This Work-in- Progress describes the development philosophy of MatBot and the migration from controlling a robot arm to an autonomous platform such as a MatBot car. Currently, the MatBot controller board, sensor board, and motor driver board have been developed and tested. These systems communicate via a CAN interface and have been successful in controlling the robot arm. We are currently designing different controller options and will be developing an autonomous vehicle controllable via Matlab.