In autonomous driving, a prior LiDAR map(PLM) is used as a powerful tool for correcting SLAM drift, but finding robust and accurate correspondences between cross modal sensors is a challenging problem. To address this cross-modality issue, this paper proposes a real-time plane-based stereo localization system with a PLM. In the proposed system, drift in visual pose estimation is eliminated through plane-based joint optimization and the registration module. Two types of planes are employed in this system: surfel, ensuring accuracy in a narrow domain, and global plane, providing robustness in a wide area. For accurate and robust matching between the visual map point and PLM, surfels and global planes in PLM are utilized collaboratively based on point-to-PLM distance. To reduce the computational cost of the registration module, a plane-to-plane drift estimation module is proposed. The performance of the proposed system is extensively validated across synthetic simulation and real-world indoor and outdoor datasets. We validate the effectiveness of each module through ablation studies and also assess the robustness against error that may exist in PLM and initial pose. In most of the validation, the proposed system shows more accurate and robust performance compared to the state-of-the-art methods.

This article presents an online distributed trajectory planning algorithm for a quadrotor swarm in a maze-like dynamic environment. We utilize a dynamic linear safe corridor to construct the feasible collision constraints that can ensure interagent collision avoidance and consider the uncertainty of moving obstacles. We introduce mode-based subgoal planning to resolve deadlock faster in a complex environment using only previously shared information. For dynamic obstacle avoidance, we adopt heuristic methods such as collision alert propagation and escape point planning to deal with the situation where dynamic obstacles approach the agents clustered in a narrow corridor. We prove that the proposed algorithm guarantees the feasibility of the optimization problem for every replanning step. In an obstacle-free space, the proposed method can compute the trajectories for 60 agents on average 7.66 ms per agent with an Intel i7 laptop and shows the perfect success rate. Also, our method shows 64.5 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> shorter flight time than buffered Voronoi cell and 34.6 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> shorter than with our previous work. We conduct the simulation in a random forest and maze with four dynamic obstacles, and the proposed algorithm shows the highest success rate and shortest flight time compared to state-of-the-art baseline algorithms. In particular, the proposed algorithm shows over 97 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> success rate when the velocity of moving obstacles is below the agent's maximum speed. We validate the safety and robustness of the proposed algorithm through a hardware demonstration with ten quadrotors and two pedestrians in a maze-like environment.

In autonomous driving, a prior LiDAR map(PLM) is used as a powerful tool for correcting SLAM drift, but finding robust and accurate correspondences between cross modal sensors is a challenging problem. To address this cross-modality issue, this paper proposes a real-time plane-based stereo localization system with a PLM. In the proposed system, drift in visual pose estimation is eliminated through plane-based joint optimization and the registration module. Two types of planes are employed in this system: surfel, ensuring accuracy in a narrow domain, and global plane, providing robustness in a wide area. For accurate and robust matching between the visual map point and PLM, surfels and global planes in PLM are utilized collaboratively based on point-to-PLM distance. To reduce the computational cost of the registration module, a plane-to-plane drift estimation module is proposed. The performance of the proposed system is extensively validated across synthetic simulation and real-world indoor and outdoor datasets. We validate the effectiveness of each module through ablation studies and also assess the robustness against error that may exist in PLM and initial pose. In most of the validation, the proposed system shows more accurate and robust performance compared to the state-of-the-art methods.

This article presents an online distributed trajectory planning algorithm for a quadrotor swarm in a maze-like dynamic environment. We utilize a dynamic linear safe corridor to construct the feasible collision constraints that can ensure interagent collision avoidance and consider the uncertainty of moving obstacles. We introduce mode-based subgoal planning to resolve deadlock faster in a complex environment using only previously shared information. For dynamic obstacle avoidance, we adopt heuristic methods such as collision alert propagation and escape point planning to deal with the situation where dynamic obstacles approach the agents clustered in a narrow corridor. We prove that the proposed algorithm guarantees the feasibility of the optimization problem for every replanning step. In an obstacle-free space, the proposed method can compute the trajectories for 60 agents on average 7.66 ms per agent with an Intel i7 laptop and shows the perfect success rate. Also, our method shows 64.5 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> shorter flight time than buffered Voronoi cell and 34.6 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> shorter than with our previous work. We conduct the simulation in a random forest and maze with four dynamic obstacles, and the proposed algorithm shows the highest success rate and shortest flight time compared to state-of-the-art baseline algorithms. In particular, the proposed algorithm shows over 97 <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"><tex-math notation="LaTeX">$\%$</tex-math></inline-formula> success rate when the velocity of moving obstacles is below the agent's maximum speed. We validate the safety and robustness of the proposed algorithm through a hardware demonstration with ten quadrotors and two pedestrians in a maze-like environment.

Safety guarantee prior to the deployment of robots can be difficult due to unexpected disturbances in runtime. This article presents a real-time receding-horizon robust trajectory planning algorithm for nonlinear closed-loop systems, which guarantees the safety of the system under unknown but bounded disturbances. We characterize the forward reachable sets (FRSs) of the system based on the Hamilton–Jacobi reachability analysis as a means for safety verification. For the online computation of the FRSs, we approximate nonlinear systems as LTV systems with linearization errors and compute ellipsoids that encompass the FRSs in continuous time. Using the proposed ellipsoidal approximation of the FRSs, we formulate a computationally tractable robust planning problem that can be solved online. Consequently, the proposed method enables real-time replanning of a reference trajectory with safety guarantees even when the system encounters unexpected disturbances in runtime. The flight experiment of obstacle avoidance in a windy environment validates the proposed robust planning algorithm.

Conventional object detectors represent each object by a deterministic bounding box, regressing its center and size from RGB images. However, such discrete parameterization ignores the inherent uncertainty in object appearance and geometric projection, which can be more naturally modeled as a probabilistic density field. Recent works have introduced Gaussian-based formulations that treat objects as distributions rather than boxes, yet they remain limited to 2D images or require late fusion between image and depth modalities. In this paper, we propose a unified Gaussian-based framework for direct 3D object detection from RGB-D inputs. Our method is built upon a vision transformer backbone to effectively capture global context. Instead of separately embedding RGB and depth features or refining depth within region proposals, our method takes a full four-channel RGB-D tensor and predicts the mean and covariance of a 3D Gaussian distribution for each object in a single forward pass. We extend a pretrained vision transformer to accept four-channel inputs by augmenting the patch embedding layer while preserving ImageNet-learned representations. This formulation allows the detector to represent both object location and geometric uncertainty in 3D space. By optimizing divergence metrics such as the Kullback–Leibler or Bhattacharyya distances between predicted and target distributions, the network learns a physically consistent probabilistic representation of objects. Experimental results on the SUN RGB-D benchmark demonstrate that our approach achieves competitive performance compared to state-of-the-art point-cloud-based methods while offering uncertainty-aware and geometrically interpretable 3D detections.

This study aims to develop and validate an enhanced early prediction model for diabetes utilizing machine learning and ensemble techniques, aimed at addressing the rapid increase in diabetes prevalence and the associated healthcare burden. Leveraging diverse datasets, including the Pima Indian Diabetes Dataset, electronic health records from local hospitals, and wearable device data, this research employs a variety of innovative methods. Generative Adversarial Networks (GAN) are used for data augmentation to address class imbalances, while SHAP (Shapley Additive exPlanations) provides interpretability for machine learning predictions, enhancing trust and understanding in clinical applications. The methodology integrates several machine learning algorithms—Support Vector Machine (SVM), Random Forest, XGBoost, Artificial Neural Networks (ANN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) networks—comparing their efficacy in diabetes prediction. Ensemble methods further refine the predictive accuracy, reliability, and applicability of the models. The study evaluates these models based on standard performance metrics such as accuracy, precision, recall, and F1-score across different configurations and combined approaches. Results indicate that ensemble methods significantly enhance predictive performance, achieving higher accuracy and precision compared to individual models. Particularly, the integration of deep learning techniques with traditional machine learning models provides substantial improvements in detecting early signs of Type 1 and Type 2 diabetes, utilizing insights from insulin and C-peptide data. The application of XAI techniques like SHAP not only clarifies model decisions but also assists in tailoring interventions and management strategies in clinical setting.

Urban Air Mobility (UAM) has emerged as a promising solution to urban challenges such as population concentration and traffic congestion. While previous research has predominantly focused on technological and regulatory aspects, educational approaches to enhance pilot competencies critical for safe and reliable early-stage UAM operations remain limited. This study investigates flight trainees’ perceptions of UAM education to propose strategies for pilot training and competency development. Results show that 36.5% of respondents prioritized establishing appropriate UAM training facilities, followed by pilot qualification training (29.8%), training for adverse weather and emergency situations (27.6%), and obstacle avoidance training (6.1%). Furthermore, 90.6% expressed interest in UAM, 91.7% in information exchange, and 89.5% in exhibitions or flight demonstrations. The findings highlight the necessity of shifting from theory-centered instruction to hands-on, experience-based training, supported by infrastructure expansion. This study provides practical insights to inform the development of UAM curricula and policy frameworks aimed at enhancing pilot preparedness and operational safety in future UAM environments.

Autonomous vehicles are increasingly utilized in diverse industries, relying heavily on perception systems to interpret their surroundings for decision-making and control. While Line-of-Sight perception technologies have advanced significantly, Non-Line-of-Sight (NLoS) perception remains a critical challenge. Current systems struggle to detect objects in NLoS scenarios, such as pedestrians or vehicles suddenly appearing from behind obstacles, leading to accidents, particularly at narrow T-junctions in urban environments. To address this, mmWave radar has emerged as a promising sensor for NLoS perception due to its ability to capture reflections and estimate the location of dynamic objects in occluded areas. However, previous researches are limited to controlled settings or single objects, with challenges like multipath reflections requiring precise spatial analysis for real-world use. In this paper, we propose a localization method for multi-dynamic NLoS pedestrians using ray tracing on 2D radar point clouds obtained from mm Wave radar in outdoor environments. The approach involves inferring spatial information from static points, performing ray tracing for dynamic points, and applying noise filtering and clustering to estimate pedestrian locations. Validation on a custom-built test bed demonstrates the effectiveness of the method, establishing a foundation for advanced NLoS perception technologies in real-world driving.

We present EigenSafe, an operator-theoretic framework for safety assessment of learning-enabled stochastic systems. In many robotic applications, the dynamics are inherently stochastic due to factors such as sensing noise and environmental disturbances, and it is challenging for conventional methods such as Hamilton-Jacobi reachability and control barrier functions to provide a well-calibrated safety critic that is tied to the actual safety probability. We derive a linear operator that governs the dynamic programming principle for safety probability, and find that its dominant eigenpair provides critical safety information for both individual state-action pairs and the overall closed-loop system. The proposed framework learns this dominant eigenpair, which can be used to either inform or constrain policy updates. We demonstrate that the learned eigenpair effectively facilitates safe reinforcement learning. Further, we validate its applicability in enhancing the safety of learned policies from imitation learning through robot manipulation experiments using a UR3 robotic arm in a food preparation task.

Local planning is an essential module for Autonomous Driving Systems (ADS), in order for a vehicle to safely reach its destination by adapting to rapidly changing road conditions. Although some simple heuristic approaches may satisfy the real-time requirements of the local planning module, they tend to struggle in complex and dynamic scenarios. While a variety of approaches—including reachability-based, optimization-based, sampling-based, and learning-based methods—are capable of handling more complex scenarios in simulation, their practical effectiveness remains uncertain due to long computation time or limited experimental validation. In this paper, we propose an efficient and adaptable sampling-based local trajectory planning method to handle diverse scenarios while ensuring computational efficiency and robust performance in real-world environments. The proposed method leverages the Lateral Recursive Feasible Set (LRFS) to define the control input range based on road boundary constraints, ensuring sampled trajectories within the boundary. To further enhance trajectory sampling efficiency, we introduce a truncated normal distribution for control input sampling, allowing trajectories to remain within safe regions. The effectiveness of our method, <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">LRFS-MPPI</i>, is demonstrated through comparisons with existing sampling-based methods in terms of execution time, sampling efficiency, the quality of the determined trajectory in simulation, and validation through hardware experiments. The results show that LRFS-MPPI efficiently generates collision-free trajectories suitable for real-time autonomous driving.