Piotr Skrzypczyński

Piotr Kicki, Puze Liu, Davide Tateo et al.

Motion planning is a mature area of research in robotics with many well-established methods based on optimization or sampling the state space, suitable for solving kinematic motion planning. However, when dynamic motions under constraints are needed and computation time is limited, fast kinodynamic planning on the constraint manifold is indispensable. In recent years, learning-based solutions have become alternatives to classical approaches, but they still lack comprehensive handling of complex constraints, such as planning on a lower-dimensional manifold of the task space while considering the robot's dynamics. This paper introduces a novel learning-to-plan framework that exploits the concept of constraint manifold, including dynamics, and neural planning methods. Our approach generates plans satisfying an arbitrary set of constraints and computes them in a short constant time, namely the inference time of a neural network. This allows the robot to plan and replan reactively, making our approach suitable for dynamic environments. We validate our approach on two simulated tasks and in a demanding real-world scenario, where we use a Kuka LBR Iiwa 14 robotic arm to perform the hitting movement in robotic Air Hockey.

Krzysztof Ćwian, Luca Di Giammarino, Simone Ferrari et al.

The joint optimization of sensor poses and 3D structure is fundamental for state estimation in robotics and related fields. Current LiDAR systems often prioritize pose optimization, with structure refinement either omitted or treated separately using implicit representations. This paper introduces a framework for simultaneous optimization of sensor poses and 3D map, represented as surfels. A generalized LiDAR uncertainty model is proposed to address less reliable measurements in varying scenarios. Experimental results on public datasets demonstrate improved performance over most comparable state-of-the-art methods. The system is provided as open-source software to support further research.

Riccardo Albertoni, Sara Colantonio, Piotr Skrzypczyński et al.

Reproducibility is one of the core dimensions that concur to deliver Trustworthy Artificial Intelligence. Broadly speaking, reproducibility can be defined as the possibility to reproduce the same or a similar experiment or method, thereby obtaining the same or similar results as the original scientists. It is an essential ingredient of the scientific method and crucial for gaining trust in relevant claims. A reproducibility crisis has been recently acknowledged by scientists and this seems to affect even more Artificial Intelligence and Machine Learning, due to the complexity of the models at the core of their recent successes. Notwithstanding the recent debate on Artificial Intelligence reproducibility, its practical implementation is still insufficient, also because many technical issues are overlooked. In this survey, we critically review the current literature on the topic and highlight the open issues. Our contribution is three-fold. We propose a concise terminological review of the terms coming into play. We collect and systematize existing recommendations for achieving reproducibility, putting forth the means to comply with them. We identify key elements often overlooked in modern Machine Learning and provide novel recommendations for them. We further specialize these for two critical application domains, namely the biomedical and physical artificial intelligence fields.

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

Piotr Kicki, Piotr Skrzypczyński

This paper demonstrates how an efficient representation of the planned path using B-splines, and a construction procedure that takes advantage of the neural network's inductive bias, speed up both the inference and training of a DNN-based motion planner. We build upon our recent work on learning local car maneuvers from past experience using a DNN architecture, introducing a novel B-spline path construction method, making it possible to generate local maneuvers in almost constant time of about 11 ms, respecting a number of constraints imposed by the environment map and the kinematics of a car-like vehicle. We evaluate thoroughly the new planner employing the recent Bench-MR framework to obtain quantitative results showing that our method outperforms state-of-the-art planners by a large margin in the considered task.

Jan Wietrzykowski, Piotr Skrzypczyński

We propose an extension to the segment-based global localization method for LiDAR SLAM using descriptors learned considering the visual context of the segments. A new architecture of the deep neural network is presented that learns the visual context acquired from synthetic LiDAR intensity images. This approach allows a single multi-beam LiDAR to produce rich and highly descriptive location signatures. The method is tested on two public datasets, demonstrating an improved descriptiveness of the new descriptors, and more reliable loop closure detection in SLAM. Attention analysis of the network is used to show the importance of focusing on the broader context rather than only on the 3-D segment.

Piotr Kicki, Mete Ozay, Piotr Skrzypczyński

We propose a computationally efficient $G$-invariant neural network that approximates functions invariant to the action of a given permutation subgroup $G \leq S_n$ of the symmetric group on input data. The key element of the proposed network architecture is a new $G$-invariant transformation module, which produces a $G$-invariant latent representation of the input data. Theoretical considerations are supported by numerical experiments, which demonstrate the effectiveness and strong generalization properties of the proposed method in comparison to other $G$-invariant neural networks.

Piotr Kicki, Tomasz Gawron, Krzysztof Ćwian et al.

Being able to rapidly respond to the changing scenes and traffic situations by generating feasible local paths is of pivotal importance for car autonomy. We propose to train a deep neural network (DNN) to plan feasible and nearly-optimal paths for kinematically constrained vehicles in small constant time. Our DNN model is trained using a novel weakly supervised approach and a gradient-based policy search. On real and simulated scenes and a large set of local planning problems, we demonstrate that our approach outperforms the existing planners with respect to the number of successfully completed tasks. While the path generation time is about 40 ms, the generated paths are smooth and comparable to those obtained from conventional path planners.

Piotr Kicki, Tomasz Gawron, Piotr Skrzypczyński

An efficient path planner for autonomous car-like vehicles should handle the strong kinematic constraints, particularly in confined spaces commonly encountered while maneuvering in city traffic, and should enable rapid planning, as the city traffic scenarios are highly dynamic. State-of-the-art planning algorithms handle such difficult cases at high computational cost, often yielding non-deterministic results. However, feasible local paths can be quickly generated leveraging the past planning experience gained in the same or similar environment. While learning through supervised training is problematic for real traffic scenarios, we introduce in this paper a novel neural network-based method for path planning, which employs a gradient-based self-supervised learning algorithm to predict feasible paths. This approach strongly exploits the experience gained in the past and rapidly yields feasible maneuver plans for car-like vehicles with limited steering-angle. The effectiveness of such an approach has been confirmed by computational experiments.

Piotr Kicki, Mete Ozay, Piotr Skrzypczyński

We introduce a method to design a computationally efficient $G$-invariant neural network that approximates functions invariant to the action of a given permutation subgroup $G \leq S_n$ of the symmetric group on input data. The key element of the proposed network architecture is a new $G$-invariant transformation module, which produces a $G$-invariant latent representation of the input data. This latent representation is then processed with a multi-layer perceptron in the network. We prove the universality of the proposed architecture, discuss its properties and highlight its computational and memory efficiency. Theoretical considerations are supported by numerical experiments involving different network configurations, which demonstrate the effectiveness and strong generalization properties of the proposed method in comparison to other $G$-invariant neural networks.

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.

Jan Wietrzykowski, Michał Nowicki, Piotr Skrzypczyński

Personal indoor localization is usually accomplished by fusing information from various sensors. A common choice is to use the WiFi adapter that provides information about Access Points that can be found in the vicinity. Unfortunately, state-of-the-art approaches to WiFi-based localization often employ very dense maps of the WiFi signal distribution, and require a time-consuming process of parameter selection. On the other hand, camera images are commonly used for visual place recognition, detecting whenever the user observes a scene similar to the one already recorded in a database. Visual place recognition algorithms can work with sparse databases of recorded scenes and are in general simple to parametrize. Therefore, we propose a WiFi-based global localization method employing the structure of the well-known FAB-MAP visual place recognition algorithm. Similarly to FAB-MAP our method uses Chow-Liu trees to estimate a joint probability distribution of re-observation of a place given a set of features extracted at places visited so far. However, we are the first who apply this idea to recorded WiFi scans instead of visual words. The new method is evaluated on the UJIIndoorLoc dataset used in the EvAAL competition, allowing fair comparison with other solutions.