The fleet size of a multi-robot system is an important parameter to be considered for real robotics applications since it will determine the cost and the time of execution of any given task. Unfortunately, it is a top...
详细信息
ISBN:
(纸本)9781479969340
The fleet size of a multi-robot system is an important parameter to be considered for real robotics applications since it will determine the cost and the time of execution of any given task. Unfortunately, it is a topic that has received little attention in the robotics literature. The study of the fleet size will allow for the design and implementation of more effective techniques and coordination methods for multi-robot systems. In this paper we study the effects of the fleet size on the time of exploration of a structured environment. We present an analysis that allows us to specify the maximum fleet size that provides the maximum reduction on the exploration time when the structured environment is modeled as a tree. The analysis is applied to the Multi-Robot Depth First Search (MRDFS) algorithm that allows for maximum parallelism when an exploration process starts from a single point. The analysis provides an expression for the average time of exploration of a tree and for the maximum number of robots that produces a significant reduction on the exploration time.
A new variant of the genetic algorithm for finding the location and size of small holes in the domain described by the non-linear boundary value problem is considered. The expansion of the shape functional defined in ...
详细信息
A new variant of the genetic algorithm for finding the location and size of small holes in the domain described by the non-linear boundary value problem is considered. The expansion of the shape functional defined in non-linear domain is provided in order to determine the form of topological derivative. The value of topological derivative is used for computing the probability density applied later to generate location and size of holes by the genetic algorithm.
The introduction of Wireless Sensor Networks (WSNs) has sparked a transformative shift in healthcare, offering answers for real-time affected person monitoring, chronic disorder management, and emergency response. By ...
详细信息
in this paper, we address the issue of two-stage visual servoing using pure 2D visual data. For robotics visual control, Imaged based visual servoing(IBVS) is considered more efficient and robust. Classical IBVS syste...
详细信息
ISBN:
(纸本)9781479970988
in this paper, we address the issue of two-stage visual servoing using pure 2D visual data. For robotics visual control, Imaged based visual servoing(IBVS) is considered more efficient and robust. Classical IBVS system is usually defined in the Cartesian coordinate space as image points. It is known that classical IBVS may cause unexpected camera movements for cases involve large rotation motion around optical axis, while IBVS based on polar coordinate can overcome this problem. We made a further study on polar-based IBVS control, and proposed a two-stage strategy combining both basic IBVS methods. Based on task decomposition using information from homography, we designed a novel two-stage controller considering strengths of both basic IBVS systems. Simulations are taken to compare with the basic IBVS methods. Finally, the results are presented to illustrate the effectiveness and optimal performance of the proposed method.
In the process of building speech recognition models, accurate labeling of speech utterances is extremely time consuming and requires trained linguists. For fast building the speech recognition models in some industri...
详细信息
Monitoring widespread environmental fields is a complex task that is of great use in many areas, such as building models of natural phenomenon: e.g. moisture in a crop field, oil reservoirs, etc. A successful monitori...
详细信息
In this work we focus on the role of Multibody Simulation in creating Reinforcement Learning virtual environments for robotic manipulation, showing a versatile, efficient and open source toolchain to create directly f...
详细信息
ISBN:
(纸本)9781450372886
In this work we focus on the role of Multibody Simulation in creating Reinforcement Learning virtual environments for robotic manipulation, showing a versatile, efficient and open source toolchain to create directly from CAD models. Using the Chrono::Solidworks plugin we are able to create robotic environments in the 3D CAD software Solidworks (R) and later convert them into PyChrono models (PyChrono is an open source Python module for multibody simulation). In addition, we demonstrate how collision detection can be made more efficient by introducing a limited number of contact primitives instead of performing collision detection and evaluation on complex 3D meshes, still reaching a policy able to avoid unwanted collisions. We tested this approach on a 6DOF robot Comau Racer3: the robot, together with a 2 fingers gripper (Hand-E by Robotiq) was modelled using Solidworks (R), imported as a PyChrono model and then a NN was trained in simulation to control its motor torques to reach a target position. To demonstrate the versatility of this toolchain we also repeated the same procedure to model and then train the ABB IRB 120 robotic arm.
This paper proposes a Neural Network Adaptive Compensator augmented Computed Torque architecture for manipulator control. The scheme has been developed such that parameter estimate errors can be learned. The proposed ...
详细信息
In this paper, we propose a sampling-based policy iteration for optimal planning under temporal logic constraints. The method integrates approximate optimal control, importance sampling, and formal methods. For a subc...
详细信息
Contact mode Atomic Force Microscopy (AFM) is popularly used by the biophysics community to study mechanical properties of cells and tissue due to its ability to quantify biological processes like disease proliferatio...
详细信息
ISBN:
(纸本)9781457712005
Contact mode Atomic Force Microscopy (AFM) is popularly used by the biophysics community to study mechanical properties of cells and tissue due to its ability to quantify biological processes like disease proliferation and stem cell differentiation. While AFM indentation experiments are relatively straightforward, interpretation of the AFM data is subject to some debate. Three factors make the AFM force data prone to incorrect interpretation, namely, the appropriate contact model to use to fit the post-contact AFM data, identifying the point when the AFM probe contacts the cell, and variability in the stiffness of the probe used to estimate material properties of cells. A lot of research has been directed towards developing constitutive models based on sample material property assumptions, however, variability in the AFM probe stiffness and contact point uncertainty has received limited attention. This suggests the need to have an integrated probabilistic model to estimate mechanical properties from the AFM force data which can account for errors contributed from these two sources. In this work, we have developed an Error-In-Variables (EIV) based Bayesian Changepoint model to estimate the contact point and the Young's Modulus from AFM force curves on fixed mouse Embryonic Stem cells (mESC) in the indentation range of 1-1.5 mu m. Our results indicate that the EIV-based Bayesian Approach can be used to obtain robust estimates of material properties of biomaterials.
暂无评论