A necessary condition for the creation of robotic systems that would be able to replace a human in hazardous conditions is developing means of intelligent control and autonomous navigation providing the possibility of making independent decisions. The article describes a technique of natural visual landmarks detection and description for mobile robot cognitive navigation. The proposed landmarks are built by simultaneous filtering and clustering of a saliency map and a point map that can be achieved by a visual SLAM method like PTAM. As a result the natural landmarks are selected from the scene and described with point clouds and image patches from different point of views. The method significantly improves robot localization robustness (15% localization error from PTAM is completely removed) and can be used for semantic description of objects in a robot navigation map.
The article describes the general principles of supervisory control organization in extreme robotics scenarios with different levels of autonomy. It is shown that increasing the level of autonomy of the robot allows reducing the operator’s load due to the division of labor between man and machine and to the implementation of the supervisory control mode, the essence of which is the decomposition of the mission into scenarios, which describe algorithms for solving functionally completed tasks and consists of sequence of simple technological operations. Such scenarios are executed automatically. In this case, the operator mainly implements the functions of monitoring and diagnostics, and the control functions are reduced to making decisions about the execution of the next scenario or intervention into execution of the current scenario in cases when the robot makes an obvious mistake or encounters a problem that it cannot solve on its own. Examples of supervisory control implementation when performing work on critical infrastructure facilities, performing search and rescue and other special operations under challenging conditions, including those of heterogeneous groups of robots, are given.
Abstract-This work is devoted to creation of transport and manipulation robotic system (TMS) to work on the surface of the spacecraft. Undoubtedly, the TMS is a powerful tool in solving problems of the study of space, so it is evident that the role of space robotics is continuously increasing due to the need to develop and maintain global communications, navigation and surveillance, permanent manned and visited space stations and bases on the Moon and on the planets of the solar system. As a basic model of a transport subsystem we proposed the symmetrical structure with seven degrees of freedom. The paper describes the structure of the system and provides its kinematics. The article presents the data obtained from the simulation in the MSC.ADAMS package. Thanks to the simulation were obtained predictive characteristics and defined functions of the robotic system. This allowed us to define a technical way to create transport and manipulation robotic system to service the outer surface of the spacecraft. Also this paper deals with the grouped operation of interacting objects (manipulators). These methods of grouped operation are mainly used to control groups of mobile robots, but as specified in [1.2], the general principles of control of the group interaction do not depend on the physical nature (and moreover on the kinematic characteristics) of the interacting objects.
Annotation. In general, almost all fields of activities in the High North and the Arctic Region can be classified as either of high or extreme risks, as any kind of emergency at industrial site/object facility is very likely to lead to a large number of casualties. Rescuing people in distress is a complicated and challenging task. Having experience of numerous rescuing activities, it has shown that application of conventional rescue equipment in northern environments is not so effective: part of rescue facilities (such as medical aircrafts and ships) are based far from location of emergency, whereas the other part (floats, boats) have very limited capabilities. However, if arrived 48 hours after the catastrophe, there is almost zero possibility to find anyone alive, and the situation often becomes even worse because of the fact that rescuers have absolutely no idea about the actual situation and conditions within the emergency area or zone. Use of robotic groups in order to provide searching of survivors, lifting them up from either sea or ice surface, considering also further transporting of the people suffered - to stationary point-of-care or station of medical aid. Should tasks of robot group operation planning and of challenging situations complex analysis be considered, the most important is to implement standardized language with very clearly defined terminology. To solve this task, it is necessary to have appropriate ontology, i.e. it is ontology that determines core constructs, properties and connections. The article indicates core robotic ontologies, standardized and currently applied by international engineering community, as well as proposes extended solution of already existing IEEE standards (CORA, etc.), formulated with application of core SUMO ontology.
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.