Michał Nowicki

Mikołaj Łysakowski, Kamil Żywanowski, Adam Banaszczyk et al.

This paper introduces a software architecture for real-time object detection using machine learning (ML) in an augmented reality (AR) environment. Our approach uses the recent state-of-the-art YOLOv8 network that runs onboard on the Microsoft HoloLens 2 head-mounted display (HMD). The primary motivation behind this research is to enable the application of advanced ML models for enhanced perception and situational awareness with a wearable, hands-free AR platform. We show the image processing pipeline for the YOLOv8 model and the techniques used to make it real-time on the resource-limited edge computing platform of the headset. The experimental results demonstrate that our solution achieves real-time processing without needing offloading tasks to the cloud or any other external servers while retaining satisfactory accuracy regarding the usual mAP metric and measured qualitative performance

Kamil Żywanowski, Adam Banaszczyk, Michał R. Nowicki et al.

The 3D LiDAR place recognition aims to estimate a coarse localization in a previously seen environment based on a single scan from a rotating 3D LiDAR sensor. The existing solutions to this problem include hand-crafted point cloud descriptors (e.g., ScanContext, M2DP, LiDAR IRIS) and deep learning-based solutions (e.g., PointNetVLAD, PCAN, LPDNet, DAGC, MinkLoc3D), which are often only evaluated on accumulated 2D scans from the Oxford RobotCar dataset. We introduce MinkLoc3D-SI, a sparse convolution-based solution that utilizes spherical coordinates of 3D points and processes the intensity of 3D LiDAR measurements, improving the performance when a single 3D LiDAR scan is used. Our method integrates the improvements typical for hand-crafted descriptors (like ScanContext) with the most efficient 3D sparse convolutions (MinkLoc3D). Our experiments show improved results on single scans from 3D LiDARs (USyd Campus dataset) and great generalization ability (KITTI dataset). Using intensity information on accumulated 2D scans (RobotCar Intensity dataset) improves the performance, even though spherical representation doesn't produce a noticeable improvement. As a result, MinkLoc3D-SI is suited for single scans obtained from a 3D LiDAR, making it applicable in autonomous vehicles.

Russell Buchanan, Jakub Bednarek, Marco Camurri et al.

Legged robot navigation in extreme environments can hinder the use of cameras and laser scanners due to darkness, air obfuscation or sensor damage. In these conditions, proprioceptive sensing will continue to work reliably. In this paper, we propose a purely proprioceptive localization algorithm which fuses information from both geometry and terrain class, to localize a legged robot within a prior map. First, a terrain classifier computes the probability that a foot has stepped on a particular terrain class from sensed foot forces. Then, a Monte Carlo-based estimator fuses this terrain class probability with the geometric information of the foot contact points. Results are demonstrated showing this approach operating online and onboard a ANYmal B300 quadruped robot traversing a series of terrain courses with different geometries and terrain types over more than 1.2km. The method keeps the localization error below 20cm using only the information coming from the feet, IMU, and joints of the quadruped.

Kamil Żywanowski, Adam Banaszczyk, Michał Nowicki

Loop closure based on camera images provides excellent results on benchmarking datasets, but might struggle in real-world adverse weather conditions like direct sun, rain, fog, or just darkness at night. In automotive applications, the sensory setups include 3D LiDARs that provide information complementary to cameras. The presented article focuses on the evaluation of camera-based, LiDAR-based, and joint camera-LiDAR-based loop closures applying a similar processing pipeline consisting of a neural network under varying weather conditions using the newly available USyd dataset. The experiments performed on the same trajectories in diverse weather conditions over 50 weeks prove that a 16-line 3D LiDAR can be used to supplement image-based loop closure to increase loop closure performance. This proves that there is a need for more research into loop closures performed with multi-sensory setups.

Michał Nowicki, Jan Wietrzykowski, Piotr Skrzypczyński

The paper presents an approach to indoor personal localization on a mobile device based on visual place recognition. We implemented on a smartphone two state-of-the-art algorithms that are representative to two different approaches to visual place recognition: FAB-MAP that recognizes places using individual images, and ABLE-M that utilizes sequences of images. These algorithms are evaluated in environments of different structure, focusing on problems commonly encountered when a mobile device camera is used. The conclusions drawn from this evaluation are guidelines to design the FastABLE system, which is based on the ABLE-M algorithm, but introduces major modifications to the concept of image matching. The improvements radically cut down the processing time and improve scalability, making it possible to localize the user in long image sequences with the limited computing power of a mobile device. The resulting place recognition system compares favorably to both the ABLE-M and the FAB-MAP solutions in the context of real-time personal localization.

Michał Nowicki, Jan Wietrzykowski

Using WiFi signals for indoor localization is the main localization modality of the existing personal indoor localization systems operating on mobile devices. WiFi fingerprinting is also used for mobile robots, as WiFi signals are usually available indoors and can provide rough initial position estimate or can be used together with other positioning systems. Currently, the best solutions rely on filtering, manual data analysis, and time-consuming parameter tuning to achieve reliable and accurate localization. In this work, we propose to use deep neural networks to significantly lower the work-force burden of the localization system design, while still achieving satisfactory results. Assuming the state-of-the-art hierarchical approach, we employ the DNN system for building/floor classification. We show that stacked autoencoders allow to efficiently reduce the feature space in order to achieve robust and precise classification. The proposed architecture is verified on the publicly available UJIIndoorLoc dataset and the results are compared with other solutions.