Metric occupancy maps are widely used in autonomous robot navigation systems. However, when a robot is deployed in an unseen environment, building an accurate metric map is time-consuming. Can an autonomous robot directly navigate in previously unseen environments using coarse maps? In this work, we propose the Coarse Map Navigator (CMN), a navigation framework that can perform robot navigation in unseen environments using different coarse maps. To do so, CMN addresses two challenges: (1) novel and realistic visual observations; (2) error and misalignment on coarse maps. To tackle novel visual observations in unseen environments, CMN learns a deep perception model that maps the visual input from various pixel spaces to the local occupancy grid space. To tackle the error and misalignment on coarse maps, CMN extends the Bayesian filter and maintains a belief directly on coarse maps using the predicted local occupancy grids as observations. Using the latest belief, CMN extracts a global heuristic vector that guides the planner to find a local navigation action. Empirical results demonstrate that CMN achieves high navigation success rates in unseen environments, significantly outperforming baselines, and is robust to different coarse maps.

We address the problem of finding representative points of datasets by learning from multiple datasets and their ground-truth summaries. We develop a supervised subset selection framework, based on the facility location utility function, which learns to map datasets to their ground-truth representatives. To do so, we propose to learn representations of data so that the input of transformed data to the facility location recovers their ground-truth representatives. Given the NP-hardness of the utility function, we consider its convex relaxation based on sparse representation and investigate conditions under which the solution of the convex optimization recovers ground-truth representatives of each dataset. We design a loss function whose minimization over the parameters of the data representation network leads to satisfying the theoretical conditions, hence guaranteeing recovering ground-truth summaries. Given the non-convexity of the loss function, we develop an efficient learning scheme that alternates between representation learning by minimizing our proposed loss given the current assignments of points to ground-truth representatives and updating assignments given the current data representation. By experiments on the problem of learning key-steps (subactivities) of instructional videos, we show that our proposed framework improves the state-of-the-art supervised subset selection algorithms.

Fast Fourier Transform (FFT) algorithm has an important role in the image processing and scientific computing, and it's a highly parallel divide-and-conquer algorithm. In this paper, we exploited the Compute Unified Device Architecture CUDA technology and contemporary graphics processing units (GPUs) to achieve higher performance. We focused on two aspects to optimize the ordinary FFT algorithm, multi-threaded parallelism and memory hierarchy. We also proposed parallelism optimization strategies when the data volume occurs and predicted the possible situation when the amount of data increased further.it can be seen from the results that Parallel FFT algorithm is more efficient than the ordinary FFT algorithm.