this paper proposes a construction of a land-based base station for automated unmanned aerial vehicle (UAV) maintenance. the station is intended for UAV storage, protection from poor weather conditions, battery replac...
详细信息
the aim of this article is to present home automation system which can be easily integrated into existing buildings without expensive cable installation. A novel solution of a Smart Home control system is proposed and...
详细信息
this paper presents a neuro-inspired mapping approach that uses partial information shared by multiple robots to reduce the time to create a map of an entire environment. Robots using a neurobiologically inspired algo...
详细信息
this paper presents a neuro-inspired mapping approach that uses partial information shared by multiple robots to reduce the time to create a map of an entire environment. Robots using a neurobiologically inspired algorithm, namely RatSLAM, map an environment sharing video information among themselves. RatSLAM, which is based on the navigation system present in the hippocampus of rodents' brain, has been widely used on simultaneous localization and mapping (SLAM) problem. this proposal has been able to generate suitable maps mainly when there is redundant information, e.g. a scene is seen more than once, since this fact activates local view cells that inject activity inside the pose cells via an excitatory link. the work here reported extends this approach by merging partial information acquired by multiple robots. the results from the performed experiments show that the final map built by two robots with shared information is similar to one built by two robots performing the same mapping task individually, i.e. without sharing information. However, the time spent to generate the whole map withthe proposed shared approach was smaller than the one without the shared information. thus, the current approach allows creating a complete map of an environment within a reduced time using multiple robots.
Autonomous machines promise more flexibility and robustness changes in their environment compared to manually programmed solutions in industrial applications. However, the autonomous planning of actions involves discr...
详细信息
ISBN:
(纸本)9783030924416
Autonomous machines promise more flexibility and robustness changes in their environment compared to manually programmed solutions in industrial applications. However, the autonomous planning of actions involves discrete as well as continuous properties, which results in a np-hard planning problem. Especially for multiple machines and long planning horizons the design of domains requires a lot of fine tuning and thus manual effort. Modularization and reuse of existing domain knowledge with formalized models is one solution to this issue. However, the models of different projects tend to be misaligned, in particular when several parties contributed to the project, which deteriorates the performance. In this paper, we present two domain optimization and extension algorithms, which adapt the models to facilitate planning. the first algorithm handles inconsistent units, or even misaligned pieces of sub-information. It automatically generates conversions and allows to call operations with a wider range of input types. the second algorithm aligns models from different sources with varying modeling views. After this reformulation, we can compose models more efficiently to a larger domain. For both optimizations, we rely on the formal set-based models that we also use in our previously presented hierarchical planning algorithm. Our hierarchical approach allows an almost linear scalability withthe length of the plan. However, it comes with non-optimality effects due to the imposed intermediate goals that depend on the quality of the model. the optimization algorithms of this paper allow to adapt and extend the model so that valid shortcuts reduce these suboptimalities. We conduct experiments on a task and motion assembly problem, demonstrating scalability for up to 62 parts and plans with over 1000 steps, which either result in discrete state or high-level position changes, with planning times of less than 15 min. Our experiments also include the successful plan execution o
this paper proposes a methodology for the real-time finger gesture following and control of mechatronic systems based on computer vision and machine learning techniques. the goal of this research is to develop a human...
详细信息
this paper proposes a methodology for the real-time finger gesture following and control of mechatronic systems based on computer vision and machine learning techniques. the goal of this research is to develop a human-machine interface that could be able to control a mechatronic system by performing finger gestures in space or on a surface without the use of any kind of keyboard neither a joystick. the finger gestures will be continuously followed and directly mapped with commands of mechatronic systems such as start moving, stop moving, forward moving, backward moving etc. the proposed methodology relies on the finger gesture data acquisition, hand segmentation, fingertips localization/ identification, high-level feature extraction, early recognition and prediction using machine learning techniques and its integration into a mechatronic system. the LEGO MINDSTORMS NXT robotics platform controlled by matlab software could be used in the proposed methodology.
A nonlinear controller is designed for a L 2 formation flying control system, and robust stability is investigated for the closed-loop system with uncertainties. the L 2 formation flying is modeled as a second-order...
详细信息
ISBN:
(数字)9781424478279
ISBN:
(纸本)9781424478286
A nonlinear controller is designed for a L 2 formation flying control system, and robust stability is investigated for the closed-loop system with uncertainties. the L 2 formation flying is modeled as a second-order quasi-linear parameter-varying model, which is obtain from the nonlinear formation flying model with Barbashin method by including explicit dependence of the dynamic derivatives on states and external parameters. Base on this QLPV model, a polynomial eigenstructure assignment approach is applied to complete the controller design for the system. As function of state and external parameters, the controller realize the independence between the closed-loop system and the operating point to ensure the performance of the closed-loop system is independent with every operating equilibrium. Simulation is carried out to validate the control performance. Considering the uncertainties in the controller parameters and dynamic derivatives, parametric stability margins of system are analyzed by using Kharitonov's approach. Analysis results show the controller is fairly robust with respect to these uncertainties.
暂无评论