This paper presents a trajectory planning approach, the Rapidly Exploring Random Tree∗ Controller and Planner (RRTCAP∗), combining the planning phase of a RRT∗-based algorithm with the execution phase on a real robot....
详细信息
We developed a line coating robot, which will be used to apply markings on different surfaces like roads, factory floors or the ground of swimming *** implemented a navigation controller for the robot that uses a lase...
详细信息
Robots that cooperate and interact with humans require the capacity to detect and track people, analyze their behavior and understand human social relations and rules. A key piece of information for such tasks are hum...
详细信息
Robots that cooperate and interact with humans require the capacity to detect and track people, analyze their behavior and understand human social relations and rules. A key piece of information for such tasks are human attributes like gender, age, hair or clothing. In this paper, we address the problem of recognizing such attributes in RGB-D data from varying full-body views. To this end, we extend a recent tessellation boosting approach which learns the best selection, location and scale of a set of simple RGB-D features. The approach outperforms the original approach and a HOG baseline for five human attributes including gender, has long hair, has long trousers, has long sleeves and has jacket. Experiments on a multi-perspective RGB-D dataset with full-body views of over a hundred different persons show that the method is able to robustly recognize multiple attributes across different view directions and distances to the sensor with accuracies up to 90%. Our methods runs in real-time, achieving a classification rate of around 300 Hz for a single attribute.
Team oriented plans have become a popular tool for operators to control teams of autonomous agents (or robots) to pursue complex objectives in complex environments. Such plans allow an operator to specify high level d...
详细信息
ISBN:
(纸本)9781450337694
Team oriented plans have become a popular tool for operators to control teams of autonomous agents (or robots) to pursue complex objectives in complex environments. Such plans allow an operator to specify high level directives and allow the team to autonomously determine how to implement such directives. However, the operators will often want to interrupt the activities of individual team members to deal with particular situations, such as a danger to a robot that the robot team cannot perceive. Previously, after such interrupt, the operator would usually need to restart the team plan to ensure its success. In this paper, we present an approach to encoding how unexpected interrupts can be smoothly handled within a team plan. Building on a team plan formalism that uses Colored Petri Net, we describe a mechanism that allows a range of interrupts to be handled smoothly, allowing the team to efficiently continue with its task, after the operator intervention. We validate the approach with an application of robotic watercraft and show improved overall efficiency. In particular, our interrupt mechanism decreases the time to complete the mission (up to 48% reduction) and decreases the operator load (up to 80% reduction in number of user actions).
The paper at hand is part of the autonomous excavator project Thor (Terraforming Heavy Outdoor Robot) who's goal is the development of a construction machine which performs landscaping on a construction site witho...
详细信息
The paper at hand is part of the autonomous excavator project Thor (Terraforming Heavy Outdoor Robot) who's goal is the development of a construction machine which performs landscaping on a construction site without an operator. So far the project mainly focused on the local excavation on one position. Due to the high digging forces the machine permanently changes its position during excavation. Furthermore, the global goal is to shape the complete construction site. Therefore, a final test platform needs to permanently reposition itself on the site. Within this paper the construction site navigation function is described which guarantees safe traveling from one pose to another one. It is based on an extended A* path planning algorithm, executed on a 2D gridmap including region growing for obstacles, including forward and backward movement. In combination with an intelligent path following algorithm the machine proved to safely reach its position with the desired orientation.
This paper presents a new hyperspectral image (HSI) classification method which is capable of automatic feature learning while achieving high classification accuracy. The method contains two major modules: the spectra...
详细信息
ISBN:
(纸本)9781479983407
This paper presents a new hyperspectral image (HSI) classification method which is capable of automatic feature learning while achieving high classification accuracy. The method contains two major modules: the spectral classification module and the spatial constraint module. Spectral classification module uses a deep network named stacked denoising autoencoders (SdA) to learn feature representation of the data. Through SdA, the data are projected nonlinearly from its original hyperspectral space to some higher dimensional space where more compact distribution is obtained. An interesting aspect of this method is that it does not need a feature design/extraction process guided by human prior. The suitable feature for the classification is learned by the deep network itself. Superpixel is utilized to generate the spatial constraints to refine the spectral classification results. By exploiting the spatial consistency of neighborhood pixels, the accuracy of classification is further improved by a big margin. Experiments on the public datasets reveal the superior performance of the proposed method.
When data have a complex manifold structure or the characteristics of data evolve over time, it is unrealistic to expect a graph-based semi-supervised learning method to achieve flawless classification given a small n...
详细信息
ISBN:
(纸本)9781467369657
When data have a complex manifold structure or the characteristics of data evolve over time, it is unrealistic to expect a graph-based semi-supervised learning method to achieve flawless classification given a small number of initial annotations. To address this issue with minimal human interventions, we propose (i) a sample selection criterion used for active query of informative samples by minimizing the expected prediction error, and (ii) an efficient correction propagation method that propagates human correction on selected samples over a gradually-augmented graph to unlabeled samples without rebuilding the affinity graph. Experimental results conducted on three real world datasets validate that our active sample selection and correction propagation algorithm quickly reaches high quality classification results with minimal human interventions.
In this paper, the problem of reducing the risks involved in the critical situations in the techno-social systems with complicated infrastructure and characterized by large crowds, such as airports, train stations, sh...
详细信息
ISBN:
(纸本)9781467374293
In this paper, the problem of reducing the risks involved in the critical situations in the techno-social systems with complicated infrastructure and characterized by large crowds, such as airports, train stations, shopping centers, etc. is considered. The task is to be solved with technical safety system on the basis of fuzzy decision support system and self-organizing sensor system. Architectures of decision support system and self-organizing sensor system are offered. An example of the system simulation is proposed.
3D reconstruction based on images has advantages of low cost with simple equipment compared with other methods based on active equipment. It is an important research issue in computer vision. According to the number o...
详细信息
3D reconstruction based on images has advantages of low cost with simple equipment compared with other methods based on active equipment. It is an important research issue in computer vision. According to the number of images involved, 3D reconstruction methods can be broadly classified into multi-images reconstruction and single image reconstruction. The major reconstruction methods, principles, and latest progress of 3D reconstruction are introduced in the article. The advantages and disadvantages of these methods are also analyzed, aiming to provide a reference for the research in the field.
暂无评论