Robust Appearance Based Visual Route Following in Large Scale Outdoor Environments
نویسندگان
چکیده
Route following is defined as the ability to repeat the same route after having traversed it once under the control of a human operator. This paper presents a fast and robust appearance based route following algorithm that utilises only monocular panoramic vision and odometry in large scale outdoor environments. Extensive experimental results have shown robustness against lighting variations and occlusion not yet demonstrated in the literature. The cumulative distance traveled by the robot in these experiments exceeds 20km and the longest repeated route is 732 meters.
منابع مشابه
Expanding the Limits of Vision-based Localization for Long-term Route-following Autonomy
Vision-based, autonomous, route-following algorithms enable robots to autonomously repeat manually driven routes over long distances. Through the use of inexpensive, commercial vision sensors, these algorithms have the potential to enable robotic applications across multiple industries. However, in order to extend these algorithms to long-term autonomy, they must be able to operate over long pe...
متن کاملMobile Robot Localisation and Mapping in Extensive Outdoor Environments
Tim Bailey Doctor of Philosophy The University of Sydney August 2002 Mobile Robot Localisation and Mapping in Extensive Outdoor Environments This thesis addresses the issues of scale for practical implementations of simultaneous localisation and mapping (SLAM) in extensive outdoor environments. Building an incremental map while also using it for localisation is of prime importance for mobile ro...
متن کاملSIFT, SURF & seasons: Appearance-based long-term localization in outdoor environments
In this paper, we address the problem of outdoor, appearance-based topological localization, particularly over long periods of time where seasonal changes alter the appearance of the environment. We investigate a straight-forward method that relies on local image features to compare single image pairs. We first look into which of the dominating image feature algorithms, SIFT or the more recent ...
متن کاملEditorial: Visual navigation and mapping outdoors
The problem of navigation and mapping using vehicles equipped with sensors has been an extremely active research area in robotics during the past 20 years. The promise of autonomous cars, airplanes, helicopters, and submarines drives these research efforts. Many researchers have reported excellent results, but so far the most successful systems have required the use of laser range-finder sensor...
متن کاملAugmenting RatSLAM using FAB-MAP-based Visual Data Association
This paper investigates the use of the FAB-MAP appearance-only SLAM algorithm as a method for performing visual data association for RatSLAM, a semi-metric full SLAM system. While both systems have shown the ability to map large (60-70km) outdoor locations of approximately the same scale, for either larger areas or across longer time periods both algorithms encounter difficulties with false pos...
متن کامل