Topic
Mobile robot navigation
About: Mobile robot navigation is a research topic. Over the lifetime, 14713 publications have been published within this topic receiving 263092 citations.
Papers published on a yearly basis
Papers
More filters
••
24 Apr 2000TL;DR: A navigation algorithm, which integrates a virtual obstacle concept with a potential-field-based method to manoeuvre cylindrical mobile robots in unknown or unstructured environments, is presented.
Abstract: Presents a navigation algorithm, which integrates a virtual obstacle concept with a potential-field-based method to manoeuvre cylindrical mobile robots in unknown or unstructured environments. This study focuses on the real-time feature of the navigation algorithm for fast moving mobile robots. We mainly consider the potential-field method in conjunction with virtual obstacle concept as the basis of our navigation algorithm. Simulation and experiments of our algorithm shows good performance and ability to overcome the local minimum problem associated with potential field methods.
102 citations
•
TL;DR: The reinforcement learning approach, which the authors call BADGR, is an end-to-end learning-based mobile robot navigation system that can be trained with autonomously-labeled off-policy data gathered in real-world environments, without any simulation or human supervision.
Abstract: Mobile robot navigation is typically regarded as a geometric problem, in which the robot's objective is to perceive the geometry of the environment in order to plan collision-free paths towards a desired goal. However, a purely geometric view of the world can can be insufficient for many navigation problems. For example, a robot navigating based on geometry may avoid a field of tall grass because it believes it is untraversable, and will therefore fail to reach its desired goal. In this work, we investigate how to move beyond these purely geometric-based approaches using a method that learns about physical navigational affordances from experience. Our approach, which we call BADGR, is an end-to-end learning-based mobile robot navigation system that can be trained with self-supervised off-policy data gathered in real-world environments, without any simulation or human supervision. BADGR can navigate in real-world urban and off-road environments with geometrically distracting obstacles. It can also incorporate terrain preferences, generalize to novel environments, and continue to improve autonomously by gathering more data. Videos, code, and other supplemental material are available on our website this https URL
101 citations
••
09 May 2005TL;DR: This talk will provide an overview of the approach to multi-robot exploration and mapping, which was developed within the CentiBots project, and results from this evaluation demonstrate that the system is highly robust and that the maps generated by the robots are more accurate thanMaps generated by a human.
Abstract: Efficient exploration of unknown environments is a fundamental problem in mobile robotics. As autonomous exploration and map building becomes increasingly robust on single robots, the next challenge is to extend these techniques to large teams of robots. This talk will provide an overview of our approach to multi-robot exploration and mapping, which we developed within the CentiBots project. This project aimed at fielding 100 robots in an indoor exploration and surveillance task. A general solution to distributed exploration must consider some difficult issues, including limited communication between robots, no assumptions about relative start locations of the robots, and dynamic assignments of processing tasks. The focus of this talk will be on our current solutions to the problems of robot localization, map building, and coordinated exploration. As part of the CentiBots project, our system was evaluated rigorously by an outside team. We present results from this evaluation that demonstrate that the system is highly robust and that the maps generated by our robots are more accurate than maps generated by a human.
101 citations
••
06 May 2015
TL;DR: In this article, the authors propose a solution to solve the problem of the problem: this article ] of unstructured data, which is also referred to as data augmentation.
Abstract: ........................................................................................................................................................ i
101 citations
••
15 Jun 1993TL;DR: It is shown how a difficult task like navigating through a funneled corridor with obstacles is possible without the need for metric depth estimation.
Abstract: A qualitative approach to visually guided navigation based on the computation of optical flow field is presented. The approach is based on the use of two cameras mounted on a mobile robot and with the optical axis directed in opposite directions, such that the two visual fields do not overlap (divergent stereo). Range computation is based on the computation of the apparent image speed on images acquired during the robot's motion. An example of reflex-type control of motion, driven by differential estimation of the flow field measured by the two eyes, is presented. It is shown how a difficult task like navigating through a funneled corridor with obstacles is possible without the need for metric depth estimation. >
101 citations