This paper proposes a novel three dimensional (3D) velocity estimation method by using differential flow techniques for the dynamic path planning of Autonomous Ground Vehicles (AGV) in a cluttered environment. We prov...
详细信息
ISBN:
(纸本)9789898565211
This paper proposes a novel three dimensional (3D) velocity estimation method by using differential flow techniques for the dynamic path planning of Autonomous Ground Vehicles (AGV) in a cluttered environment. We provide a frame work for the computation of dense and non rigid 3D flow vectors from the range data, obtained from the time-of-flight camera. Combined Lucas/Kanade and Horn/schunck approach is used to estimate the velocity of the dynamic obstacles. The trajectory of the dynamic obstacle is predicted from the direction of the 3D flow field and the estimated velocity. By experiments, the utility of the approach is demonstrated with the results.
This paper proposes a new feature based design software, called RFD. The main goal of the presented software, together with another software developed by the author in the purpose of the assisted generation of the num...
详细信息
ISBN:
(纸本)9781467307024
This paper proposes a new feature based design software, called RFD. The main goal of the presented software, together with another software developed by the author in the purpose of the assisted generation of the numeric conduct files for turning operations, is to make up a Low Cost CAD/CAM program package configured according to the requirements, the needs and the facilities of a certain type of client. The commercial CAD systems work with primitives, but too many modeling operations are needed, when dealing with complex parts design. The RFD software represents a method and an example on how the SME's (Small and medium enterprises) could build their own feature libraries, which could be implemented by adapting the general CAD systems to specific industrial products. A case study is presented using the RFD program, to test its capabilities and its compatibility with other CAD systems.
This paper presents control method of an inverted pendulum with an inertial drive (IWP Inertia Wheel Pendulum). This is a non-linear, underactuated mechanical system and therefore it has more degrees of freedom than c...
详细信息
The main objective of this work is the development of a Vehicle Ad Hoc NETwork (VANET) to collect data from GPS equipped mobile phones used as noise detectors. In this system, sensor nodes perioadically transmit acous...
详细信息
ISBN:
(纸本)9781467307024
The main objective of this work is the development of a Vehicle Ad Hoc NETwork (VANET) to collect data from GPS equipped mobile phones used as noise detectors. In this system, sensor nodes perioadically transmit acoustic noise levels to neighboring cars, data packets being shared and temporary stored by participating VANET nodes and ultimately forwarded to a collector node connected to the Internet, providing public real-time data. A routing technique called MP-OLSR that takes into account the spatially separation between the multiple paths is used, for better transmission reliability and congestion avoidance as well as for control message overhead minimization.
In this paper a novel approach to the problem of 3D reconstruction from stereovision is proposed. The analyzed solution is based on the identification of suitable metrics of image pixels able to measure their (dis)sim...
详细信息
ISBN:
(纸本)9789898565211
In this paper a novel approach to the problem of 3D reconstruction from stereovision is proposed. The analyzed solution is based on the identification of suitable metrics of image pixels able to measure their (dis)similarity using rectangular, fixed-size, local support windows. Every local support window, centred in a given pixel, is weighted based on colour proximity and colour segmentation of surrounding pixels. Then a metrics for dissimilarity computation between potentially homologous pixels across the images is applied using an aggregation (convolution) of raw costs together a measure of colour affinities. Finally the resulting measures are used to build two disparity maps (left-to-right and right-to-left) and the maps fused in a final one.
The paper introduces a new measurement device which allows collecting the chipping force in three directions and additionally the process temperature. The apparatus consists of a specially designed tool holder with in...
详细信息
The paper presents a solution of finding the Pareto front for the intermodal and multi-objective time-dependent shortest path problem from, a source to a destination. In the considered case, the travel time and route ...
详细信息
ISBN:
(纸本)9781467307024
The paper presents a solution of finding the Pareto front for the intermodal and multi-objective time-dependent shortest path problem from, a source to a destination. In the considered case, the travel time and route cost must be minimized. A mathematical model of the multimodal time dependent freight transport network is constructed and then an exact multi-objective algorithm is proposed and implemented. Finally, the performance and effectiveness of the method are assessed by analyzing the algorithm's behavior when different network's parameters change.
Software development for embedded systems is a fast growing industry. Development for a mid-range complexity embedded system is usually based on custom built templates and tools, or on commercially developed solutions...
详细信息
This paper presents some motion path tracking algorithms of mobile robot based on machine vision. The machine vison subsystem of robot capture the information of motion path in real-time, which is stored and processed...
详细信息
Limited knowledge and limited deduction abilities are among the main restraints of autonomous robots for acting truly autonomously. This especially becomes obvious in the area of object recognition and classification,...
详细信息
ISBN:
(纸本)9789898565211
Limited knowledge and limited deduction abilities are among the main restraints of autonomous robots for acting truly autonomously. This especially becomes obvious in the area of object recognition and classification, where many methods rely on knowledge teached manually in a prior setup step. Self-generating this knowledge from environment perception with a set of rules would significantly increase the robots autonomy as well as supersede manual training effort. In this paper, we propose a novel approach to rule-based classification for 3D point clouds by means of object shape, which additionally overcomes typical problems from a separate prior segmentation by integrating classification feedback into the segmentation process. Although it is still in its conceptual state, we explain in detail why we consider this approach to be very promising.
暂无评论