English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Developing mobile robots able to move autonomously and staying operational in unexplored environments is one of the most important aims of intelligent robotics research. Navigation (here in the sense: collision-free goal following behaviour) depends on the amount of a priori available information. It could be assumed that this information comes in the following three categories: (I) complete information about the robot's workspace is available, (II) a priori knowledge about the environment is not available and the robot would have to rely on its sensors at execution time to obtain the information needed to accomplish the task, (III) partial knowledge of the environment is available and sensors are used at the execution time to acquire additional information. The robot may interweave planning and execution monitoring activities, but the more incomplete the prior knowledge, the less important the role of global planning. Most of the global path-planning methods, which assume a static and completely known to the robot environment, are considered to belong to or to be variations of a few basic approaches: roadmap, cell decomposition, and potential field methods (Latombe, 1991; Choset et al., 2005). However, the dynamic and complex features of robot environments make their accurate modelling and predicting fundamentally impossible. Hence, during path following a local re-planning is needed in order to make the robot avoid collisions with unknown obstacles. By combining global and local path-planning methods mobile robots are able to operate in dynamic environments (Yahja et al., 2000). Each of the path-planning methods has its own advantages and drawbacks and is more or less proper to be used in a particular situation. How to select the most suitable approach and how to use local pathplanning in collaboration with the global one in a practical example, related to a partially known or fast-changing environment these are still open research problems. Navigation relies on the tracking and regulation capabilities of the feedback control design (the lower control level of the robot). Standard approaches to non-holonomic control design often deal only with the kinematic steering system, but good performance cannot be obtained without taking into account the vehicle dynamics. A stable control algorithm that considers the complete vehicle dynamics has been developed using back stepping 10

Neural Networks Based Navigation and Control of a Mobile Robot in a Partially Known Environment