Introducing general CAD descriptions in object recognition systems has become a major field of research called CAD based vision (CBV). However, the major problem using free-form object descriptions is how to define re...
详细信息
Introducing general CAD descriptions in object recognition systems has become a major field of research called CAD based vision (CBV). However, the major problem using free-form object descriptions is how to define recognizable features which can be extracted from sensor data. We propose new methods for the extraction of 3D space carves from CAD models and from range data. Object identification is performed by correlating feature vectors from significant subcurves.
Powerful robot controlling systems especially designed for demanding robotic applications like assembly planning strongly depend on its hard- and software resources. In this paper we present a powerful parallel robot ...
详细信息
Powerful robot controlling systems especially designed for demanding robotic applications like assembly planning strongly depend on its hard- and software resources. In this paper we present a powerful parallel robot independent programming and controlling environment with simulation capabilities (PRIPES). Based on an open multiprocessor architecture PRIPES provides an easy programming interface for robotic applications. Due to its full support of dynamic processing and its real-time capable communication subsystem, it provides the basic requirements for high sophisticated processes, e.g. for monitoring purposes in compliant motion applications. Consequently, PRIPES supports the implementation of parallel algorithms, which can be used to significantly reduce calculation times consumed by numerical complex algorithms. Subsequently, we give first results in implementing a parallelized algorithm for calculating stable orientations of assemblies in order to prove the capabilities of PRIPES.
In this paper we propose an interactive multiobjective decision making method based on three criteria functions for image reconstruction. Image reconstruction based on this method is shown to be superior to convention...
详细信息
In this paper we propose an interactive multiobjective decision making method based on three criteria functions for image reconstruction. Image reconstruction based on this method is shown to be superior to conventional iterative reconstruction algorithms such as SIRT (Simultaneous Interactive Reconstruction Technique) from the point of view of accuracy of reconstruction. Computer simulation using the multiobjective method shows a significant improvement in image quality and convergence behavior over the conventional algorithms.
This paper presets an efficient local optimization scheme for redundant serial link manipulators with low degree of redundancy and a complex optimization task. This is done by reducing the degree of the joints space b...
详细信息
This paper presets an efficient local optimization scheme for redundant serial link manipulators with low degree of redundancy and a complex optimization task. This is done by reducing the degree of the joints space by the number of link variables solved by a closed form solution of the inverse kinematics for nonredundant substructures. The optimization problem is solved locally by an algorithm which does not require differentiable task functions.
We propose a new object matching algorithm which can separate overlapping objects and which is robust against erroneous data. The algorithm is based on the well-known iterative closest point (ICP) algorithm. However a...
详细信息
High-level assembly planning systems generate plans for the automated assembly of mechanical products by robots. The sequences to be generated underlie several physical and geometrical constraints, and in addition hav...
We propose a new object matching algorithm which can separate overlapping objects and which is robust against erroneous data. The algorithm is based on the well-known iterative closest point (ICP) algorithm. However a...
详细信息
We propose a new object matching algorithm which can separate overlapping objects and which is robust against erroneous data. The algorithm is based on the well-known iterative closest point (ICP) algorithm. However all published contributions to the ICP algorithm can not provide a proper segmentation of the input data. A fuzzy ICP algorithm can handle these problems by a fuzzy membership valuation at each iteration level. Furthermore, we introduce an evidence accumulation algorithm which allows a determination of the best match. In combination with search routines for the most common CAD models we provide powerful and efficient tools for CAD based object recognition systems.
In this paper we present our high level assembly planning system /sup High/LAP. /sup High/LAP generates and evaluates all assembly sequences of a mechanical assembly with minimal user interaction. For the evaluation o...
详细信息
In this paper we present our high level assembly planning system /sup High/LAP. /sup High/LAP generates and evaluates all assembly sequences of a mechanical assembly with minimal user interaction. For the evaluation of all feasible assembly sequences several criteria are taken into account. /sup High/LAP considers for example the separability and the manipulability of the generated (sub)assemblies, Furthermore, the necessity of reorientation for a mating operation and parallelism during plan execution is considered. Another important criterion is the stability of the generated (sub)assemblies. Most of the assembly planners developed up to date use heuristics or user defined criteria to determine assembly stability for plan evaluation. In order to bring automatic assembly planning closer to reality /sup High/LAP performs a powerful geometrical and physical reasoning. The system presented is the first assembly planning system taking into account the range of all stable orientations of an assembly considering friction for plan evaluation.
To plan collision-free trajectories for mobile robots among moving obstacles most approaches presume the obstacles' trajectories to be known. This is contradictory to practice where motions generally are known-at ...
详细信息
To plan collision-free trajectories for mobile robots among moving obstacles most approaches presume the obstacles' trajectories to be known. This is contradictory to practice where motions generally are known-at best-as average behaviours. Thus, we proposed to use statistical information for path planning. This paper focuses on the derivation of formulae to estimate collision probabilities. By generalizing elementary collision patterns we develop a method to calculate a collision probability field. For any given goal position, it estimates the collision probabilities for paths starting at arbitrary points in the workspace. This provides a powerful tool for path planning in dynamic environments. Using an algorithm similar to path planning based on potential fields, we can calculate paths with (approximately) minimum collision probability.
暂无评论