The main contribution of this paper is a new simultaneous localization and mapping ͑SLAM͒ algorithm for building dense three-dimensional maps using information acquired from a range imager and a conventional camera, for robotic search and rescue in unstructured indoor environments. A key challenge in this scenario is that the robot moves in 6D and no odometry information is available. An extended information filter ͑EIF͒ is used to estimate the state vector containing the sequence of camera poses and some selected 3D point features in the environment. Data association is performed using a combination of scale invariant feature transformation ͑SIFT͒ feature detection and matching, random sampling consensus ͑RANSAC͒, and least square 3D point sets fitting. Experimental results are provided to demonstrate the effectiveness of the techniques developed.

No abstract

This paper presents an algorithm for planning efficient trajectories in a bin-picking scenario. The presented algorithm is designed to provide paths, which are applicable for typical industrial manipulators, and does not require customized research interfaces to the robot controller. The method provides paths (almost) instantaneously, which is important for running efficiently in production. To achieve this, the method utilizes that all motions start and end within sub-volumes of the work envelope. A database of paths can thus be pre-computed, such that all paths are optimized with respect to a specified cost function, thereby ensuring close to optimal solutions. When queried, the method searches the database for a feasible path candidate and adapts it to the specific query. To achieve an efficient execution on the robot, blends are added to ensure a smooth transition between segments. Two algorithms for calculating feasible blends based on the clearance between robot and obstacles are therefore provided. Finally, the method is tested in a real bin-picking application where it solves queries efficiently and provides paths, which are significantly faster than those currently used for bin-picking in the industry.