Adaptive Kernel Inference for Dense and Sharp Occupancy Grids

In this paper, we present a new approach, AKIMap, that uses an adaptive kernel inference for dense and sharp occupancy grid representations. Our approach is based on the multivariate kernel estimation, and we propose a simple, two-stage based method that selects an adaptive bandwidth matrix for an efficient and accurate occupancy estimation. To utilize correlations of occupancy observations given sparse and non-uniform distributions of point samples, we propose to use the covariance matrix as an initial bandwidth matrix, and then optimize the bandwidth matrix by adjusting its scale in an efficient, data-driven way for on-the-fly mapping. We demonstrate that the proposed technique estimates occupancy states more accurately than state-of-the-art methods given equal-data or equal-time settings, thanks to our adaptive inference. Furthermore, we show the practical benefits of the proposed work in on-the-fly mapping and observe that our adaptive approach shows the dense as well as sharp occupancy representations in a real environment.

Authors

• Youngsun Kwon
• Bochang Moon
• Sung-Eui Yoon

Keywords

• Shape
• Estimation
• Bandwidth
• Sparse matrices
• Kernel
• Covariance matrices
• Intelligent robots
• Occupancy Grid
• Adaptive Kernel
• Covariance Matrix
• Sample Distribution
• Kernel Estimation
• Occupancy State
• Dense Representation
• Multivariate Estimation
• Occupancy Estimates
• Model Parameters
• Receiver Operating Characteristic Curve
• Sensor Data
• Point Cloud
• Sparse Data
• Gaussian Process
• Red Box
• Gaussian Mixture Model
• Blue Box
• Isotropic Kernel
• Free Samples
• Occupancy Map
• Kernel Shape
• Neighboring Samples
• LiDAR Sensor
• Kernel Bandwidth
• Query Point
• Occupied States
• Gaussian Process Model
• False Estimation
• Sensor Measurements