Condition-Invariant Robot Localization Using Global Sequence Alignment of Deep Features

Localization is one of the essential process in robotics, as it plays an important role in autonomous navigation, simultaneous localization, and mapping for mobile robots. As robots perform large-scale and long-term operations, identifying the same locations in a changing environment has become an important problem. In this paper, we describe a robust visual localization system under severe appearance changes. First, a robust feature extraction method based on a deep variational autoencoder is described to calculate the similarity between images. Then, a global sequence alignment is proposed to find the actual trajectory of the robot. To align sequences, local fragments are detected from the similarity matrix and connected using a rectangle chaining algorithm considering the robot’s motion constraint. Since the chained fragments provide reliable clues to find the global path, false matches on featureless structures or partial failures during the alignment could be recovered and perform accurate robot localization in changing environments. The presented experimental results demonstrated the benefits of the proposed method, which outperformed existing algorithms in long-term conditions.

Generalization Ability of Deep Learning Algorithms Trained using SEM Data for Objects Classification

This paper proposes a workflow to efficiently determine the material of spherical objects and the location of the receiving antenna relative to their position in bi-static measurements using supervised learning techniques. From a single observation, we compare classification performances resulting from the application of several classifiers on different data types: the Ultra-Wide Band scattered field in time and frequency domains and pre-processed data from the Singularity Expansion Method (SEM). Indeed, the resonances extracted using the SEM are aspect independent and therefore, are used to discriminate the objects. As for the residues, they depend upon the aspect angle and can hence be exploited to determine the observation angle. We construct 3 datasets to assess which one yields the highest accuracy while using the simplest and fastest classifiers. Hence, 80% of each dataset is used for training and the remaining 20% are used for testing. In a further step, we test with sphere sizes and data with several noisy levels that were not in the training datasets. Although SEM is noise sensitive, associating a robust feature extraction technique with a simple but reliable classifier is promising, particularly when generalizing to data not included in the training set.

Generalization Ability of Deep Learning Algorithms Trained using SEM Data for Objects Classification

This paper proposes a workflow to efficiently determine the material of spherical objects and the location of the receiving antenna relative to their position in bi-static measurements using supervised learning techniques. From a single observation, we compare classification performances resulting from the application of several classifiers on different data types: the Ultra-Wide Band scattered field in time and frequency domains and pre-processed data from the Singularity Expansion Method (SEM). Indeed, the resonances extracted using the SEM are aspect independent and therefore, are used to discriminate the objects. As for the residues, they depend upon the aspect angle and can hence be exploited to determine the observation angle. We construct 3 datasets to assess which one yields the highest accuracy while using the simplest and fastest classifiers. Hence, 80% of each dataset is used for training and the remaining 20% are used for testing. In a further step, we test with sphere sizes and data with several noisy levels that were not in the training datasets. Although SEM is noise sensitive, associating a robust feature extraction technique with a simple but reliable classifier is promising, particularly when generalizing to data not included in the training set.