Marcelo Contreras

A high-definition (HD) map development framework providing real-time visualization of multimodal perception data for state estimation, motion planning, and decision-making in autonomous navigation is presented and experimentally validated. The proposed framework integrates synchronized visual and LiDAR data and generates consistent frame transformations to construct accurate and interpretable HD maps suitable for navigation in dynamic environments. In addition, the framework enables flexible customization of essential map elements, including road features and static landmarks, facilitating efficient map generation and visualization. Building upon the developed HD map visualizer, a semantic-aware visual odometry (VO)-based pose estimation module is designed and verified through extensive evaluations and under perceptually degraded conditions. To ensure the reliability of synchronized multimodal data used by downstream perception and pose estimation modules, a sensor health monitoring system is also developed and validated in urban canyon scenarios with intermittent or unavailable global navigation satellite system (GNSS) measurements. Experimental results demonstrate that the proposed HD map visualizer and associated perception modules are transferable for autonomous navigation and can be effectively employed as benchmarking tools for state estimation and motion planning algorithms in autonomous driving.

Machine learning and deep learning advancements have boosted Brain-Computer Interface (BCI) performance, but their wide-scale applicability is limited due to factors like individual health, hardware variations, and cultural differences affecting neural data. Studies often focus on uniform single-site experiments in uniform settings, leading to high performance that may not translate well to real-world diversity. Deep learning models aim to enhance BCI classification accuracy, and transfer learning has been suggested to adapt models to individual neural patterns using a base model trained on others’ data. This approach promises better generalizability and reduced overfitting, yet challenges remain in handling diverse and imbalanced datasets from different equipment, subjects, multiple centres in different countries, and both healthy and patient populations for effective model transfer and tuning. In a setting characterized by maximal heterogeneity, we proposed P300 wave detection in BCIs employing a convolutional neural network fitted with adaptive transfer learning based on Poison Sampling Disk (PDS) called Active Sampling (AS), which flexibly adjusts the transition from source data to the target domain. Our results reported for subject adaptive with 40% of adaptive fine-tuning that the averaged classification accuracy improved by 5.36% and standard deviation reduced by 12.22% using two distinct, internationally replicated datasets. These results outperformed in classification accuracy, computational time, and training efficiency, mainly due to the proposed Active Sampling (AS) method for transfer learning.

Conventional visual navigation methods presume scene stability and encounter challenges due to moving objects in highly dynamic environments. We propose DynaNav-SVO, a stereo visual odometry (VO) framework, which semantically detects and constructs a region-of-interest (ROI) by focusing on a-priori urban fixed elements for reliable feature extraction and subsequently estimates vehicle pose. The outcome is a static map with minimal outliers and is used for state estimation in dynamic scenes and perceptually degraded conditions. This map enhances computational efficiency due to the reduced size of the new static mask (as confirmed in several experiments), compared to the existing visual simultaneous localization and mapping (vSLAM) solutions. To refine the estimated pose, a back-end module selects a moving horizon of frames, generates a covisibility graph for data association, and optimizes a structure-from-motion program using local bundle adjustment. Finally, the performance of the framework is experimentally evaluated using a test vehicle in highly-dynamic urban settings and under adverse weather conditions with degraded visual perception with varying sequence lengths. The experiments confirm excellent performance in terms of estimation accuracy and computational efficiency for autonomous navigation compared to existing vSLAM methods.