Using Vision for Outdoor - SLAM
نویسندگان
چکیده
In this paper we outline how we seek to augment existing mapping technology with visual competencies designed to enable Simultaneous Localization and Mapping (SLAM) in outdoor settings. We briefly describe the notion of visual similarity between scenes and discuss how it can be applied to scene labelling, loop closure and the definition of distinctive places. However, the main questions are, how topological constraints can improve state-of-the-art SLAM techniques for outdoor environments, which role play metric measurements in large scale mapping, and what is an appropriate description for such maps. Due to the complexity of those problems, we do not yet seek to present full answers or solutions. The intention of this paper is rather to present and discuss our ideas and research objectives in the context of related previous work both our own and external.
منابع مشابه
Slam with Klt Point Features
In the simultaneous localization and mapping (SLAM) problem, a mobile robot must localize itself in an unknown environment using its sensors and at the same time construct a map of that environment. While SLAM utilizing costly (expensive, heavy and slow) laser range finders as a sensor has been very successful in both indoor and outdoor environments, large-scale SLAMwith cost-effective visionba...
متن کاملFeatureless Vehicle-Based Visual SLAM with a Consumer Camera
The Simultaneous Localisation And Mapping (SLAM) problem is one of the major challenges in mobile robotics. Probabilistic techniques using high-end range finding devices are well established in the field, but recent work has investigated vision-only approaches. We present an alternative approach to the leading existing techniques, which extracts approximate rotational and translation velocity i...
متن کاملStereo Vision Based SLAM Issues and Solutions
1Simultaneous Localization and Mapping (SLAM) has been one of the active research areas in robotic research community for the past few years. When a robot is placed in an unknown environment a SLAM solution attempts to build a perfect map of the environment while localising the robot with respect to this map simultaneously. Traditionally SLAM utilised endogenous sensor data in the process. Succ...
متن کاملGamma-SLAM: Stereo Visual SLAM in Unstructured Environments Using Variance Grid Maps
We introduce a new method for stereo visual SLAM (simultaneous localization and mapping) that works in unstructured, outdoor environments. Observations use dense stereo vision to measure the variance of the heights in each cell of a 2D grid. Unlike other grid-based SLAM algorithms, which use occupancy grid maps, our algorithm uses a new mapping technique that maintains a posterior distribution ...
متن کاملOutdoor exploration and SLAM using a compressed filter
In this paper we describe the use of automatic exploration for autonomous mapping of outdoor scenes. We describe a real-time SLAM implementation along with an autonomous exploration algorithm. We have implemented SLAM with a compressed extended Kalman filter (CEKF) on an outdoor robot. Our implementation uses walls of buildings as features. The state predictions are made by using a combination ...
متن کاملRobust Landmark Estimation for SLAM in Dynamic Outdoor Environment
In this paper, we propose techniques which make SLAM accurate and practical in dynamic outdoor environment. In order to achieve the objective, stable feature detection by a laser range finder and efficient data management are introduced. The stable feature detection is used to select static and characteristic landmarks, it is possible to estimate every position of landmark accurately in the dyn...
متن کاملذخیره در منابع من
با ذخیره ی این منبع در منابع من، دسترسی به آن را برای استفاده های بعدی آسان تر کنید
عنوان ژورنال:
دوره شماره
صفحات -
تاریخ انتشار 2006