In this paper, we propose a two-stage learning framework for visual navigation in which the experience of the agent during exploration of one goal is shared to learn to navigate to other goals. We train a deep neural network for estimating the robot’s position in the environment using ground truth information provided by a classical localization and mapping approach. The second simpler multi-goal Q-function learns to traverse the environment by using the provided discretized map. Transfer learning is applied to the multi-goal Q-function from a maze structure to a 2D simulator and is finally deployed in a 3D simulator where the robot uses the estimated locations from the position estimator deep network. In the experiments, we first compare different architectures to select the best deep network for location estimation, and then compare the effects of the multi-goal reinforcement learning method to traditional reinforcement learning. The results show a significant improvement when multi-goal reinforcement learning is used. Furthermore, the results of the location estimator show that a deep network can learn and generalize in different environments using camera images with high accuracy in both position and orientation.

In this paper we propose a new approach to Deep Neural Networks (DNNs) based on the particular needs of navigation tasks. To investigate these needs we created a labeled image dataset of a test environment and we compare classical computer vision approaches with the state of the art in image classification. Based on these results we have developed a new DNN architecture that outperforms previous architectures in recognizing locations, relying on the geometrical features of the images. In particular we show the negative effects of scale, rotation, and position invariance properties of the current state of the art DNNs on the task. We finally show the results of our proposed architecture that preserves the geometrical properties. Our experiments show that our method outperforms the state of the art image classification networks in recognizing locations.

A robot's local navigation is often done through forward simulation of robot velocities and measuring the possible trajectories against safety, distance to the final goal and the generated path of a global path planner. Then, the computed velocities vector for the winning trajectory is executed on the robot. This process is done continuously through the whole navigation process and requires an extensive amount of processing. This only allows for a very limited sampling space. In this paper, we propose a novel approach to automatically detect the type of surrounding environment based on navigation complexity using unsupervised clustering, and limit the local controller's sampling space. The experimental results in 3D simulation and using a real mobile robot show that we can increase the navigation performance by at least thirty percent while reducing the number of failures due to collision or lack of sampling.

Robotic mapping and localization methods are mostly dominated by using a combination of spatial alignment of sensory inputs, loop closure detection, and a global fine-tuning step. This requires either expensive depth sensing systems, or fast computational hardware at run-time to produce a 2D or 3D map of the environment. In a similar context, deep neural networks are used extensively in scene recognition applications, but are not yet applied to localization and mapping problems. In this paper, we adopt a novel approach by using denoising autoencoders and image information for tackling robot localization problems. We use semi-supervised learning with location values that are provided by traditional mapping methods. After training, our method requires much less run-time computations, and therefore can perform real-time localization on normal processing units. We compare the effects of different feature vectors such as plain images, the scale invariant feature transform and histograms of oriented gradients on the localization precision. The best system can localize with an average positional error of ten centimeters and an angular error of four degrees in 3D simulation.

High performance, reliability, transient and permanentfault-tolerance, and low energy consumption are majorobjectives of Networks-on-Chip (NoCs). Since,different applications impose various communicationrequirements in NoCs, a number of research studieshave revealed that the performance advantages ofrouting schemes are more noticeable on powerconsumption under different traffic patterns. However,the power consumption issues of NoCs have not beenthoroughly investigated in the presence of faultyregions. To the best of our knowledge, this research isthe first attempt to examine the effects of most populartraffic patterns (i.e., Uniform, Local, and Hot-Spot) onpower consumption of NoCs in the presence ofpermanent faults.

Fault-tolerance and network routing have been among the most widely studied topics in the research of parallel processing and computer networking. A fault-tolerant routing algorithm should guarantee the delivery of messages in the presence of faulty components. In this paper, we present a comparative performance study of nine prominent fault-tolerant routings in 2-D wormhole-switched tori. These networks carry the Software-Based routing scheme which has been suggested as an instance of a fault-tolerant method widely used in the literature to achieve high adaptivity and support inter-processor communications in parallel computer networks due to its ability to preserve both communication performance and fault-tolerant demands in such systems. The performance measures studied are the throughput, average message latency, power, and average usage of virtual channels per node. Results obtained through simulation suggest two classes of presented routing schemes as high performance candidates in most faulty networks.

One of the fundamental problems in parallel computing is how to efficiently perform routing in a faulty network each component of which fails with some probability. This paper presents a comparative performance study of ten prominent adaptive fault-tolerant routing algorithms in wormhole-switched 2D mesh interconnect networks. These networks carry a routing scheme suggested by Boppana and Chalasani as an instance of a fault-tolerant method. The suggested scheme is widely used in the literature to achieve high adaptivity and support inter-processor communications in parallel computer systems due to its ability to preserve both communication performance and fault-tolerant demands in these networks. The performance measures studied are the throughput, average message latency and average usage of virtual channels per node. Results obtained through simulation suggest two classes of presented routing schemes as high performance candidate in most faulty networks.