Reactive navigation in extremely dense and highly intricate environments

Abstract

Reactive navigation is a well-known paradigm for controlling an autonomous mobile robot, which suggests making all control decisions through some light processing of the current/recent sensor data. Among the many advantages of this paradigm are: 1) the possibility to apply it to robots with limited and low-priced hardware resources, and 2) the fact of being able to safely navigate a robot in completely unknown environments containing unpredictable moving obstacles. As a major disadvantage, nevertheless, the reactive paradigm may occasionally cause robots to get trapped in certain areas of the environment—typically, these conflicting areas have a large concave shape and/or are full of closely-spaced obstacles. In this last respect, an enormous effort has been devoted to overcome such a serious drawback during the last two decades. As a result of this effort, a substantial number of new approaches for reactive navigation have been put forward. Some of these approaches have clearly improved the way how a reactively-controlled robot can move among densely cluttered obstacles; some other approaches have essentially focused on increasing the variety of obstacle shapes and sizes that could be successfully circumnavigated; etc. In this paper, as a starting point, we choose the best existing reactive approach to move in densely cluttered environments, and we also choose the existing reactive approach with the greatest ability to circumvent large intricate-shaped obstacles. Then, we combine these two approaches in a way that makes the most of them. From the experimental point of view, we use both simulated and real scenarios of challenging complexity for testing purposes. In such scenarios, we demonstrate that the combined approach herein proposed clearly outperforms the two individual approaches on which it is built.

Towards Fully Autonomous UAVs: A Survey

“…The planning horizon can typically be very short for some period ahead of time or it could be carried out at each control update cycle in a receding horizon fashion. A special class of such methods is made up of reactive approaches where sensor measurements are coupled to control actions either directly [ 51 ] or after light processing [ 52 ]. Sensor-based methods offer solutions with great computational performance which makes them favorable for navigation problems in unknown and dynamic environments.…”

Means of IoT and Fuzzy Cognitive Maps in Reactive Navigation of Ubiquitous Robots

“…They enable to guide a robot under very dynamic conditions at the search optimality cost, that is, reactive navigation is suitable mainly on short distances, and if rapid responses are possible, else a collision can occur. Thus we can find their use in the navigation of robotic cars or drones in dense and cluttered environments [53][54][55]. However, most navigation methods rely on sensory data obtained from own onboard sensors.…”

Advanced Algorithms of Collision Free Navigation and Flocking for Autonomous UAVs

“…The planning horizon can typically be very short for some period ahead of time or it could be done at each control update cycle in a receding horizon fashion. A very special class of such methods is reactive approaches where sensors measurements are coupled to control actions either directly [51] or after light processing [52]. Sensor-based methods offer solutions with great computational performance which makes them favorable for navigation problems in unknown and dynamic environments.…”

“…Quintic Bezier splines are used to generate smooth paths, and real-time smooth deformations are applied based on information interpreted from sensors measurements to provide quick reactions to obstacles. As only light processing of sensory data are needed, the approach can be classified as reactive [52]. The method is developed at a high-level first considering a general 3D kinematic model applicable to different UAV types and AUVs.…”