Social Odometry: Imitation Based Odometry in Collective Robotics
نویسندگان
چکیده
منابع مشابه
Social Odometry: Imitation Based Odometry in Collective Robotics
The improvement of odometry systems in collective robotics remains an important challenge for several applications. Social odometry is an online social dynamics which confers the robots the possibility to learn from the others. Robots neither share any movement constraint nor access to centralized information. Each robot has an estimate of its own location and an associated confidence level tha...
متن کاملInformation Aggregation Mechanisms in Social Odometry
Multi-robot exploration and navigation is a challenging task, especially within the swarm robotics domain, in which the individual robots have limited capabilities and have access to local information only. An interesting approach to exploration and navigation in swarm robotics is social odometry, that is, a cooperative strategy in which robots exploit odometry for individual navigation, and sh...
متن کاملSocial Odometry in Populations of Autonomous Robots
The improvement of odometry systems in collective robotics remains an important challenge for several applications. In this work, we propose a localisation strategy in which robots have no access to centralised information. Each robot has an estimate of its own location and an associated confidence level that decreases with distance travelled. Robots use estimates advertised by neighbouring rob...
متن کاملHomography-Based Monocular Visual Odometry
In robotics, the problem of robot localization is studied for a long time. One approach to deal with it is the use of cameras whatever their kind. It brings the mobile robot, thanks to the image provided by the sensor, the information of the environment in front of it. Even if vision is often used to correct classical odometry derive, we would want to only use vision approach. The purpose of th...
متن کاملGraph Odometry
We address problem of determining edge weights on a graph using non-backtracking closed walks from a vertex. We show that the weights of all of the edges can be determined from any starting vertex exactly when the graph has minimum degree at least three. We also determine the minimum number of walks required to reveal all edge weights.
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
ژورنال
عنوان ژورنال: International Journal of Advanced Robotic Systems
سال: 2009
ISSN: 1729-8814,1729-8814
DOI: 10.5772/6794