首页 | 本学科首页   官方微博 | 高级检索  
相似文献
 共查询到20条相似文献,搜索用时 56 毫秒
1.
2.
We present in this paper a methodology for computing the maximum velocity profile over a trajectory planned for a mobile robot. Environment and robot dynamics as well as the constraints of the robot sensors determine the profile. The planned profile is indicative of maximum speeds that can be possessed by the robot along its path without colliding with any of the mobile objects that could intercept its future trajectory. The mobile objects could be arbitrary in number and the only information available regarding them is their maximum possible velocity. The velocity profile also enables one to deform planned trajectories for better trajectory time. The methodology has been adopted for holonomic and non-holonomic motion planners. An extension of the approach to an online real-time scheme that modifies and adapts the path as well as velocities to changes in the environment such that both safety and execution time are not compromised is also presented for the holonomic case. Simulation and experimental results demonstrate the efficacy of this methodology.  相似文献   

3.
《Advanced Robotics》2012,26(17):1967-1993
A current trend in robotics is to define robot motions so that they can be easily adopted to situations beyond those for which the motion was originally designed. In this work, we show how the challenging task of playing minigolf can be efficiently tackled by first learning a basic hitting motion model, and then learning to adapt it to different situations. We model the basic hitting motion with an autonomous dynamical systems, and solve the problem of learning the parameters of the model from a set of demonstrations through a constrained optimization. To hit the ball with the appropriate hitting angle and speed, a nonlinear model of the hitting parameters is estimated based on a set of examples of good hitting parameters. We compare two statistical methods, Gaussian Process Regression and Gaussian Mixture Regression in the context of inferring the hitting parameters for the minigolf task. We demonstrate the generalization ability of the model in various situations. We validate our approach on the 7 Degrees of Freedom (DoF) Barrett WAM arm and 6-DoF Katana arm in both simulated and real environments.  相似文献   

4.
A new approach to the design of a neural network (NN) based navigator is proposed in which the mobile robot travels to a pre-defined goal position safely and efficiently without any prior map of the environment. This navigator can be optimized for any user-defined objective function through the use of an evolutionary algorithm. The motivation of this research is to develop an efficient methodology for general goal-directed navigation in generic indoor environments as opposed to learning specialized primitive behaviors in a limited environment. To this end, a modular NN has been employed to achieve the necessary generalization capability across a variety of indoor environments. Herein, each NN module takes charge of navigating in a specialized local environment, which is the result of decomposing the whole path into a sequence of local paths through clustering of all the possible environments. We verify the efficacy of the proposed algorithm over a variety of both simulated and real unstructured indoor environments using our autonomous mobile robot platform.  相似文献   

5.
This paper introduces a novel neuro-dynamical model that accounts for possible mechanisms of action imitation and learning. It is considered that imitation learning requires at least two classes of generalization. One is generalization over sensory–motor trajectory variances, and the other class is on cognitive level which concerns on more qualitative understanding of compositional actions by own and others which do not necessarily depend on exact trajectories. This paper describes a possible model dealing with these classes of generalization by focusing on the problem of action compositionality. The model was evaluated in the experiments using a small humanoid robot. The robot was trained with a set of different actions concerning object manipulations which can be decomposed into sequences of action primitives. Then the robot was asked to imitate a novel compositional action demonstrated by a human subject which are composed from prior-learned action primitives. The results showed that the novel action can be successfully imitated by decomposing and composing it with the primitives by means of organizing unified intentional representation hosted by mirror neurons even though the trajectory-level appearance is different between the ones of observed and those of self-generated.  相似文献   

6.
When multiple robots perform tasks in a shared workspace, they might be confronted with the risk of blocking each other’s ways, which will lead to conflicts or interference among them. Planning collision-free paths for all the robots is a challenge for a multi-robot system, which is also known as the multi-robot cooperative pathfinding problem in which each robot has to navigate from its starting location to the destination while keeping avoiding stationary obstacles as well as the other robots. In this paper, we present a novel fully decentralized approach to this problem. Our approach allows robots to make real-time responses to dynamic environments and can resolve a set of benchmark deadlock situations subject to complex spatial constraints in a shared workspace by means of altruistic coordination. Specifically, when confronted with congested situations, each robot can employ waiting, moving-forwards, dodging, retreating and turning-head strategies to make local adjustments. Most importantly, each robot only needs to coordinate and communicate with the others that are located within its coordinated network in our approach, which can reduce communication overhead in fully decentralized multi-robot systems. In addition, experimental results also show that our proposed approach provides an efficient and competitive solution to this problem.  相似文献   

7.
复杂实时嵌入式系统建模与设计方法研究   总被引:6,自引:0,他引:6  
提出了一种面向角色(Actor-Oriented)的复杂实时嵌入式系统建模与设计方法.该方法首先根据不同的计算模型(Computation Model)和不同的抽象层次(Abstract Hierarchy)将嵌入式系统划分为多个具有单一计算模型的子系统,然后按某一领域的专业知识构造这些子系统.再将这些子系统综合成一个整体模型,加以仿真.最后从调试好的模型自动生成软件代码和硬件描述语言,从而完成设计工作.还介绍了面向角色集成开发环境,并根据实例分析了该方法的有效性和优点。  相似文献   

8.
《Control Engineering Practice》2007,15(11):1416-1426
In industrial production lines, for example in the automotive industry, cells with multiple industrial robots are common. In such cells, each robot has to avoid running into static obstacles and when the robots work together in a shared space they must also avoid colliding with each other. Typically, the latter is enforced by manually implementing interlocks in programmable logic controllers (PLCs). This is a tedious, error-prone task that is a bottleneck in the development of production lines. The PLC-code being man-made also greatly complicates the maintenance and reconfiguration of such production lines. However, in industry today, a lot of development of robot cells is made offline in 3D simulation environments which enables the use of computers also for deciding and implementing the necessary coordination. This paper presents a method that makes use of information in a robot simulation environment in order to automatically extract finite state models. These models can be used to generate supervisors for ensuring that the deadlock situations that may arise as a consequence of the introduced interlocks are avoided. It is also possible to optimize the work cycle time for the cell. Finally, PLC-code to supervise the production cell can be automatically generated from the deadlock-free and possibly optimized system model. This approach results in a high flexibility in that the coordination function can be quickly reimplemented whenever necessary. A prototype implementation has been developed making use of a commercial 3D robot simulation tool, and a software tool for supervisor synthesis and code generation. The approach is general and should be possible to implement in most offline robot simulation tools.  相似文献   

9.
The artificial potential method of constrained robot control is presented. The method does not imply knowledge of a detailed robot model and, nevertheless, makes it possible to drive a robot in the environment with obstacles of any shape and along a desired trajectory as well as to take into account constructive constraints. The method is based on the construction of an artificial potential that provides the absence of intermediate equilibriums in which the robot can be locked.  相似文献   

10.
This paper presents the design of a neuro-fuzzy visual servoing controller for robot guiding fabrics with curved edges towards sewing. Fabrics comprising real cloths consist of curved edges of arbitrary curvatures that can not be standardized. To overcome this difficulty, the idea is to train the robot sewing system and to apply this methodology in a real-time operation environment. The proposed approach for robot sewing is based on visual servoing and a learning technique that combines neural networks and fuzzy logic. A novel genetic-oriented clustering method is used to construct the initial FIS models and then, adaptive neuro-fuzzy inference systems allow tuning them so that it is possible to obtain better estimates. Extensive experiments were carried out in order to build data sets using fabrics with curved edges of various curvatures. The proposed model is validated using fabrics that had not been included in the training process and the results demonstrate that the proposed approach is efficient and effective for robot guiding fabrics with arbitrary curved edges towards sewing.  相似文献   

11.
The computation burden of intensive numerical real-time algorithms is a problem encountered in robotics and many other fields. A cost-effective solution for the implementation of these algorithms requires knowledge of computer architecture, compiler technology and algorithms. A cost-effective numeric processing methodology using a combined hardware-software approach and taking advantage of logic programming tools is presented. The methodology is based on optimizing the numerical calculation process of the algorithm. It also enables the specification of hardware resources. The process uses a rule-based-system (RBS) implemented in the logic programming language Prolog to automatically reduce the number of operations in the numerical execution of the algorithm and optimizes the use of hardware resources. The methodology provides a solution for the problems of handshake overhead and algorithm translation efficiency.The Direct Kinematics Solution (DKS), a robot arm control algorithm, is presented as a case study to illustrate the methodology. The proposed methodology has a general potential which can be extended to the optimization or implementation of different algorithms.  相似文献   

12.
The latest Deep Learning (DL) models for detection and classification have achieved an unprecedented performance over classical machine learning algorithms. However, DL models are black-box methods hard to debug, interpret, and certify. DL alone cannot provide explanations that can be validated by a non technical audience such as end-users or domain experts. In contrast, symbolic AI systems that convert concepts into rules or symbols – such as knowledge graphs – are easier to explain. However, they present lower generalization and scaling capabilities. A very important challenge is to fuse DL representations with expert knowledge. One way to address this challenge, as well as the performance-explainability trade-off is by leveraging the best of both streams without obviating domain expert knowledge. In this paper, we tackle such problem by considering the symbolic knowledge is expressed in form of a domain expert knowledge graph. We present the eXplainable Neural-symbolic learning (X-NeSyL) methodology, designed to learn both symbolic and deep representations, together with an explainability metric to assess the level of alignment of machine and human expert explanations. The ultimate objective is to fuse DL representations with expert domain knowledge during the learning process so it serves as a sound basis for explainability. In particular, X-NeSyL methodology involves the concrete use of two notions of explanation, both at inference and training time respectively: (1) EXPLANet: Expert-aligned eXplainable Part-based cLAssifier NETwork Architecture, a compositional convolutional neural network that makes use of symbolic representations, and (2) SHAP-Backprop, an explainable AI-informed training procedure that corrects and guides the DL process to align with such symbolic representations in form of knowledge graphs. We showcase X-NeSyL methodology using MonuMAI dataset for monument facade image classification, and demonstrate that with our approach, it is possible to improve explainability at the same time as performance.  相似文献   

13.
A longstanding goal of robotics has been to introduce intelligent machines into environments dangerous to humans. These environments also pose hazards to the robots themselves. By embedding sensing devices as a means for monitoring the internal state of the robot, dynamic plan reformulation can occur in situations that threaten the existence of the robot. A method exploiting an analogy to the endocrine control system is forwarded as the preferred method for homeostatic control—the maintenance of a safe internal environment for the machine. Examples are given describing the impact of fuel reserve depletion and global temperature stress. A methodology using signal schemas as a means to supplement the existing motor schema control found in the Autonomous Robot Architecture (AuRA) is presented.  相似文献   

14.
This paper discusses a possible neurodynamic mechanism that enables self-organization of two basic behavioral modes, namely a ‘proactive mode’ and a ‘reactive mode,’ and of autonomous switching between these modes depending on the situation. In the proactive mode, actions are generated based on an internal prediction, whereas in the reactive mode actions are generated in response to sensory inputs in unpredictable situations. In order to investigate how these two behavioral modes can be self-organized and how autonomous switching between the two modes can be achieved, we conducted neurorobotics experiments by using our recently developed dynamic neural network model that has a capability to learn to predict time-varying variance of the observable variables. In a set of robot experiments under various conditions, the robot was required to imitate other’s movements consisting of alternating predictable and unpredictable patterns. The experimental results showed that the robot controlled by the neural network model was able to proactively imitate predictable patterns and reactively follow unpredictable patterns by autonomously switching its behavioral modes. Our analysis revealed that variance prediction mechanism can lead to self-organization of these abilities with sufficient robustness and generalization capabilities.  相似文献   

15.
16.
This paper evaluates the usefulness of various psychological techniques that can be utilized to elicit and model expert knowledge for subsequent representation in rule-based expert systems. Interviewing, protocol analysis and multidimensional scaling are described and evaluated as complementary methods of knowledge elicitation. In addition ‘context-focusing’ and card-sorting are introduced as short-cut methods for the knowledge engineer's ‘tool box’.It is argued that expert knowledge about uncertainty can be represented as subjective probabilities and that these assessments can (and therefore should) be checked for consistency and coherence as a pre-condition for realism.Finally, the issue of whether it is possible to improve upon expert judgement is discussed and evidence is reviewed which shows that, in repetitive decision-making situations, statistical models of the expert can out-perform the expert on whom the models are based. Statistical modelling has a valid but limited application as a replacement for expert judgement.  相似文献   

17.
《Advanced Robotics》2013,27(18):2233-2254
Robots are increasingly being used in domestic environments and should be able to interact with inexperienced users. Human–human interaction and human–computer interaction research findings are relevant, but often limited because robots are different from both humans and computers. Therefore, new human–robot interaction (HRI) research methods can inform the design of robots suitable for inexperienced users. A video-based HRI (VHRI) methodology was here used to carry out a multi-national HRI user study for the prototype domestic robot BIRON (BIelefeld RObot companioN). Previously, the VHRI methodology was used in constrained HRI situations, while in this study HRIs involved a series of events as part of a 'hometour' scenario. Thus, the present work is the first study of this methodology in extended HRI contexts with a multi-national approach. Participants watched videos of the robot interacting with a human actor and rated two robot behaviors (Extrovert and Introvert). Participants' perceptions and ratings of the robot's behaviors differed with regard to both verbal interactions and person following by the robot. The study also confirms that the VHRI methodology provides a valuable means to obtain early user feedback, even before fully working prototypes are available. This can usefully guide the future design work on robots, and associated verbal and non-verbal behaviors.  相似文献   

18.
高水平的智能机器人要求能够独立地对环境进行感知并进行正确的行动推理.在情境演算行动理论中表示带有感知行动及知识的行动推理需要外部设计者为agent写出背景公理、感知结果及相应的知识变化,这是一种依赖于设计者的行动推理.情境演算行动理论被适当扩充,感知器的表示被添加到行动理论的形式语言中,并把agent新知识的产生建立在感知器的应用结果之上.扩充后的系统能够形式化地表示机器人对环境的感知并把感知结果转换为知识,还能进行独立于设计者的行动推理,同时让感知行动的“黑箱”过程清晰化.  相似文献   

19.
The paper describes the application of fuzzy techniques to analyze motion problems in a mobile robot. The robot is equipped with ultrasound sensors used for obstacle detection, but, in some cases, small obstacles are out of the range of the sensors and can be dragged by the robot without being detected. Using other variables as, measured velocity, undershoots of that velocity or changes in battery voltage, a fuzzy system is able to determine those situations. The paper also analyzes the knowledge extraction process for the application using expert and induced knowledge (from data collected during navigation tasks) in a cooperative way, dealing with integration and simplification issues. The expert knowledge was used for describing the robot behaviour in order to identify the variables that should be used with the aim of detecting a collision of the vehicle against an undetected obstacle, as well as proposing a suitable recovery action. Data collected in real trials were used for inducing knowledge so as to complete and validate the expert knowledge. Both kind of knowledge were integrated in the final fuzzy-based system. The aim is to build up a knowledge base, which is interpretable and accurate at the same time, and it is used by our fuzzy system in order to solve the motion problems under consideration.  相似文献   

20.
A new type of high‐level robot command library is presented and demonstrated. Three robot programming languages have been analyzed and new robot command libraries created for three types of robot. The programming of three robots using the new high‐level robot command library demonstrated that it was possible to program robots with different kinematic configurations without the programmer having any knowledge of the physical structure of the robots. The library commands contained simulations of the abilities of the robots as well as having the ability to control the physical robots. This paper shows how simulation can be incorporated into a high‐level robot command library and how the command library can be used for the programming of three industrial robots. ©1999 John Wiley & Sons, Inc.  相似文献   

设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号