Marco Antonio Meggiolaro

Accurate state estimation is crucial for legged robot locomotion, as it provides the necessary information to allow control and navigation. However, it is also challenging, especially in scenarios with uneven and slippery terrain. This paper presents a new Invariant Extended Kalman filter for legged robot state estimation using only proprioceptive sensors. We formulate the methodology by combining recent advances in state estimation theory with the use of robust cost functions in the measurement update. We tested our methodology on quadruped robots through experiments and public datasets, showing that we can obtain a pose drift up to 40% lower in trajectories covering a distance of over 450m, in comparison with a state-of-the-art Invariant Extended Kalman filter.

The majority of visual SLAM systems are not robust in dynamic scenarios. The ones that deal with dynamic objects in the scenes usually rely on deep-learning-based methods to detect and filter these objects. However, these methods cannot deal with unknown moving objects. This work presents Panoptic-SLAM, an open-source visual SLAM system robust to dynamic environments, even in the presence of unknown objects. It uses panoptic segmentation to filter dynamic objects from the scene during the state estimation process. Panoptic-SLAM is based on ORB-SLAM3, a state-of-the-art SLAM system for static environments. The implementation was tested using real-world datasets and compared with several state-of-the-art systems from the literature, including DynaSLAM, DS-SLAM, SaD-SLAM, PVO and FusingPanoptic. For example, Panoptic-SLAM is on average four times more accurate than PVO, the most recent panoptic-based approach for visual SLAM. Also, experiments were performed using a quadruped robot with an RGB-D camera to test the applicability of our method in real-world scenarios. The tests were validated by a ground-truth created with a motion capture system.

The real-world deployment of fully autonomous mobile robots depends on a robust simultaneous localization and mapping (SLAM) system, capable of handling dynamic environments, where objects are moving in front of the robot, and changing environments, where objects are moved or replaced after the robot has already mapped the scene. This paper proposes Changing-SLAM, a method for robust Visual SLAM in both dynamic and changing environments. This is achieved by using a Bayesian filter combined with a long-term data association algorithm. Also, it employs an efficient algorithm for dynamic keypoints filtering based on object detection that correctly identifies features inside the bounding box that are not dynamic, preventing a depletion of features that could cause lost tracks. Furthermore, a new dataset was developed with RGB-D data specially designed for the evaluation of changing environments on an object level, called PUC-USP dataset. Six sequences were created using a mobile robot, an RGB-D camera and a motion capture system. The sequences were designed to capture different scenarios that could lead to a tracking failure or map corruption. Changing-SLAM does not assume a given camera pose or a known map, being also able to operate in real time. The proposed method was evaluated using benchmark datasets and compared with other state-of-the-art methods, proving to be highly accurate.

A maioria dos sistemas de SLAM visual não é robusta em cenários dinâmicos. Aqueles que lidam com conteúdo dinâmico nas cenas geralmente dependem de métodos baseados em aprendizado profundo para detectar e filtrar objetos dinâmicos. No entanto, esses métodos não conseguem lidar com objetos desconhecidos. Este trabalho apresenta o Panoptic-SLAM, um sistema de SLAM visual robusto para ambientes dinâmicos, mesmo na presença de objetos desconhecidos. Ele utiliza a Segmentação Panóptica para filtrar objetos dinâmicos da cena durante o processo de estimativa de estado. A metodologia proposta é baseada no ORB-SLAM3, um sistema SLAM estado-da-arte para ambientes estáticos. A implementação foi testada usando conjuntos de dados do mundo real e comparada com vários sistemas da literatura, incluindo DynaSLAM, DS-SLAM e SaD-SLAM e PVO.

Localização e Mapeamento Simultâneos é um problema fundamental em robótica móvel. No entanto, a maioria dos algoritmos de SLAM Visual assume um cenário estático, limitando sua aplicabilidade em ambientes do mundo real. Lidar com conteúdo dinâmico em SLAM visual ainda é um problema em aberto. Este trabalho apresenta o primeiro método de SLAM visual feito para ambientes humanos lotados usando detecção de pessoas.

The use of digital manufacturing for the construction of orthosis and prostheses has become common since the popularization of 3D printers and the advent of Industry 4.0. Furthermore, due to the fact that the manufacture of orthosis is interactive and for personal use, generic production is difficult. In this sense, the large-scale production of these products lacks of improvements, standardization of processes and production optimization. An aggravation of this is the recent social distance due to the COVID-19 pandemic, which makes the use of temporary orthosis made in 3D printers to have a recent growth. Parallel to this, the use of multi-lattice inner structures for internal structuring of prints has also been increasing and taking on a more consolidated form. This article aims to present the multi-lattice optimization as a solution to this problem, in order to reduce material waste while maintaining the mechanical behavior of printed parts.