Journal of Intelligent and Robotic Systems manuscript No. (will be inserted by the editor) Francisco Bonin-Font, Alberto Ortiz and Gabriel Oliver Department of Mathematics and Computer Science, University of the Balearic Islands, Palma de Mallorca, Spain Visual Navigation for Mobile Robots: a Survey Abstract Mobile robot vision-based navigation has been the source of countless research contribu- tions, from the domains of both vision and control. Vision is becoming more and more common in applications such as localization, automatic map construction, autonomous navigation, path following, inspection, monitoring or risky situation detection. This survey presents those pieces of work, from the nineties until nowadays, which constitute a wide progress in visual navigation techniques for land, aerial and autonomous underwater vehicles. The paper deals with two major approaches: map-based naviga- tion and mapless navigation. Map-based navigation has been in turn subdivided in metric map-based navigation and topological map-based navigation. Our outline to mapless navigation includes reactive techniques based on qualitative characteristics extraction, appearance-based localization, optical flow, features tracking, plane ground detection/tracking, etc... The recent concept of visual sonar has also been revised. 1 Introduction Navigation can be roughly described as the process of determining a suitable and safe path between a starting and a goal point for a robot travelling between them [18,72]. Different sensors have been used to this purpose, which has led to a varied spectrum of solutions. In particular, in the last three decades, visual navigation for mobile robots has become a source of countless research contributions since navigation strategies based on vision can increase the scope of application of autonomous mobile vehicles. Among the different proposals, this paper surveys the most recent ones. In many cases, the performance of a good navigation algorithm is deeply joined to an accurate robot localization in the environment. Therefore, some vision-based localization solutions applied and developed for autonomous vehicles have also been included in this survey. Traditionally, vision-based navigation solutions have mostly been devised for Autonomous Ground Vehicles (AGV), but, recently, visual navigation is gaining more and more popularity among researchers developing Unmanned Aerial Vehicles (UAV). UAVs offer great perspectives in many applications, such as surveillance, patrolling, search and rescue, outdoor and indoor building inspection, real-time This work is partially supported by DPI 2005-09001-C03-02 and FEDER funding Francisco Bonin-Font Tel.: +34-971-172813 E-mail: francisco.bonin@uib.es Alberto Ortiz Tel.: +34-971-172992 E-mail: alberto.ortiz@uib.es Gabriel Oliver Tel.: +34-971-173201 E-mail: goliver@uib.es