This paper proposes a computational framework for humanoid robots to learn complex behaviors through combining robotic self-exploration and demonstrations of humans. A modified Rapidly-growing Random Tree (RRT)-Connec...
详细信息
This paper proposes a computational framework for humanoid robots to learn complex behaviors through combining robotic self-exploration and demonstrations of humans. A modified Rapidly-growing Random Tree (RRT)-Connect algorithm is used for exploration, a Linear Global Model (LGM) is used for recording demonstrations, a spatial-temporal extension of Isomap algorithm is used for dimension reduction which enables the exploration in a low-dimensional latent space, and the log likelihood function of the distribution of sampled data in the joint space is used to project the data in the latent space back to the joint space. An experiment of imitating a conducting behavior is carried out to demonstrate the effectiveness of this framework.
The provision of reliable location estimates in case of unpredicted failures or malicious attacks, which inject faults and compromise the performance of the positioning system, is very important. Thus, our main intere...
详细信息
The provision of reliable location estimates in case of unpredicted failures or malicious attacks, which inject faults and compromise the performance of the positioning system, is very important. Thus, our main interest is on the fault tolerance of WLAN fingerprint-based methods, rather than the absolute positioning error in the fault-free case. We study the Nearest Neighbor method and as a first step we develop a robust detection scheme to accurately detect faults. We incorporate this into a hybrid positioning method that switches to a modified distance metric, instead of the Euclidean, if faults are present. Experimental results indicate that the proposed approach exhibits higher resilience to faults compared to other positioning methods.
Particle Swarm Optimization (PSO) has received great attention in recent years as a successful global search algorithm, due to its simple implementation and inexpensive computation overhead. However, PSO still suffers...
详细信息
This paper considers the problem of improving the monitoring capability of a sparse stationary sensor network with mobile sensor nodes. The main idea is that the mobile sensors should sample the areas that are least c...
详细信息
ISBN:
(纸本)9781612848006
This paper considers the problem of improving the monitoring capability of a sparse stationary sensor network with mobile sensor nodes. The main idea is that the mobile sensors should sample the areas that are least covered (monitored) by the static sensors. Thus, a simple path planning strategy is presented that decides the next point to be visited using only "local" information. For a simplified scenario, the paper derives the optimal path strategy and extrapolates some of the properties of the scenario to a more general instance of the problem. Furthermore, the paper proposes a surrogate metric that can be used in order to determine the optimal searching neighborhood and presents extensive simulation results which indicated that this approach can achieve very good results.
This paper presents a social interactive robot Nancy that has been developed in Social robotics Laboratory, National University of Singapore. Fundamentally different from factory robots, Nancy's design focuses on ...
详细信息
This paper develops a filtering approach for distributed fault detection of a class of interconnected continuous-time nonlinear systems with modeling and measurement uncertainties. A distributed fault detection scheme...
详细信息
ISBN:
(纸本)9781612848006;9781612848013
This paper develops a filtering approach for distributed fault detection of a class of interconnected continuous-time nonlinear systems with modeling and measurement uncertainties. A distributed fault detection scheme and corresponding thresholds are designed based on filtering certain signals so that the effect of high frequency measurement uncertainty is diminished. The analysis of the proposed distributed fault detection scheme shows that the derived thresholds guarantee that there are no false alarms and characterizes quantitatively the class of detectable faults.
Hotspots are Network on-Chip (NoC) routers or modules which occasionally receive packetized traffic at a higher rate that they can process. This phenomenon reduces the performance of an NoC, especially in the case wor...
详细信息
This paper proposes and experimentally shows how we combine light penetration concept and simple image processing operations in order to identify gender of a silkworm pupa. Key features include low cost, fast, and hig...
详细信息
Electronic textiles offer possibilities for producing large-area sensors circuits on conformal substrates. To demonstrate this concept, a 5×4 element acoustic array was produced on a 3m × 1m fabric substrate...
Electronic textiles offer possibilities for producing large-area sensors circuits on conformal substrates. To demonstrate this concept, a 5×4 element acoustic array was produced on a 3m × 1m fabric substrate. In the course of fabricating the acoustic array a variety of production issues were identified that impacted the performance of the prototype when experimental tests were carried out with this prototype acoustic array. Fabric-based acoustic array design and production, along with design issues related to scaling an acoustic array to handle larger numbers of microphones on large-area fabrics, are the focus of this paper.
In this paper, We made an algorithm for a mobile robot to determine direction normal to the wall with two cameras in an indoor environment without any direction-notification marks. Furthermore, with this direction det...
详细信息
In this paper, We made an algorithm for a mobile robot to determine direction normal to the wall with two cameras in an indoor environment without any direction-notification marks. Furthermore, with this direction determination ability, made a method with which a mobile robot can navigate and search through an indoor corridor path without any predefined map information is made. the direction determination scheme uses Hough transform and horizontal line search. While the path search algorithm uses SIFT(Scale-Invariant Feature Transformation), 3D reconstruction and binary search tree algorithm. In the direction determination stage, the mobile robot detects lines in the image and detects horizontal lines to determine the normal to the wall direction. After the direction determination stage is completed, the robot determines the corridor path range through SIFT, RANSAC algorithm, and 3D reconstruction, and finally navigates through its pathway. The direction determination and navigation stage constitutes the binary search tree algorithm. After searching through all its pathway in the indoor environment, the robot returns to its original position with various corridor position information.
暂无评论