Nak Young Chong

Thanh Nguyen Canh, Haolan Zhang, Xiem HoangVan et al.

Probabilistic data association (PDA) improves semantic SLAM in perceptually aliased scenes, but existing methods often assume a fixed landmark set, recompute association weights as the map grows, or rely on hand-tuned null-hypothesis weights. To address these limitations, we propose \textbf{BPDA-GMM}, an online Bayesian PDA framework for semantic SLAM with a growing object-level map. BPDA-GMM uses a Dirichlet-process prior to induce a Chinese Restaurant Process (CRP) association model, where accumulated evidence favors existing landmarks, and the concentration parameter assigns probability mass to new landmarks. For each semantic detection, plausible candidates are selected by a joint semantic-geometric gate, CRP-weighted association probabilities are computed, and object landmarks are updated as semantic Gaussians in closed form. The resulting landmark set forms a Gaussian mixture model, and its dominant component is passed to the back-end as a max-mixture semantic factor. When association weights are inconclusive, an ambiguity-triggered $α$-divergence tempering step improves discrimination. Finally, a decoupled back-end zeroes the pose Jacobian of semantic factors, allowing noisy detections to refine landmarks without directly perturbing the trajectory. Experiments in simulation and on a real indoor dataset demonstrate improved trajectory accuracy, semantic mapping quality, and robustness to perceptual aliasing and classifier errors over state-of-the-art baselines. Code and video are publicly available at https://github.com/thanhnguyencanh/BPDA-SLAM.

Thanh-Tuan Tran, Thanh Nguyen Canh, Nak Young Chong et al.

Reinforcement learning in discrete-continuous hybrid action spaces presents fundamental challenges for robotic manipulation, where high-level task decisions and low-level joint-space execution must be jointly optimized. Existing approaches either discretize continuous components or relax discrete choices into continuous approximations, which suffer from scalability limitations and training instability in high-dimensional action spaces and under domain randomization. In this paper, we propose Hybrid TD3, an extension of Twin Delayed Deep Deterministic Policy Gradient (TD3) that natively handles parameterized hybrid action spaces in a principled manner. We conduct a rigorous theoretical analysis of overestimation bias in hybrid action settings, deriving formal bounds under twin-critic architectures and establishing a complete bias ordering across five algorithmic variants under synchronized Gaussian error assumptions. Building on this analysis, we introduce a weighted clipped Q-learning target that marginalizes over the discrete action distribution, achieving equivalent bias reduction to standard clipped minimization while improving policy smoothness. Experimental results demonstrate that Hybrid TD3 achieves superior training stability and competitive performance against state-of-the-art hybrid action baselines.

Haolan Zhang, Thanh Nguyen Canh, Chenghao Li et al.

Visual odometry (VO) is a fundamental component in robotics and augmented reality. RGB-D direct VO benefits from metric depth measurements, but it can degrade in challenging environments, where dynamic objects, occlusions, illumination changes, and unreliable depth violate the short-horizon photometric and depth-geometric consistency assumptions used by direct alignment. Existing approaches mitigate these issues through semantic filtering, explicit occlusion reasoning, illumination adaptation, or hand-crafted geometric criteria, but often rely on external modules or fixed assumptions tailored to individual failure modes, limiting their flexibility and ability to handle diverse challenges in a unified manner. In this work, we propose Con-DSO, a consistency-aware RGB-D direct sparse odometry framework that predicts dense photometric and depth-geometric consistency uncertainty from temporally adjacent RGB-D frame pairs. The consistency network is trained using flow-guided photometric errors and projective depth-consistency errors, allowing consistency violations to be represented as pixel-level uncertainty. These pairwise uncertainty predictions are converted into a host-side quality prior for keyframe-based tracking. The prior is then applied to VO through quality-aware support-pixel selection and decoupled photometric-geometric weighting during pose estimation, enabling continuous attenuation of unreliable observations rather than hard rejection or threshold-based gating. Experiments on five public RGB-D benchmarks show substantial gains over direct RGB-D VO baselines, with over 20\% absolute trajectory error reduction on ICL-NUIM and 50\%--80\% reductions on RGB-D Scenes V2, TUM/Bonn Dynamic, and OpenLORIS sequences.

Ke Liao, Wei Wang, Armagan Elibol et al.

Machine learning has been widely used in healthcare applications to approximate complex models, for clinical diagnosis, prognosis, and treatment. As deep learning has the outstanding ability to extract information from time series, its true capabilities on sparse, irregularly sampled, multivariate, and imbalanced physiological data are not yet fully explored. In this paper, we systematically examine the performance of machine learning models for the clinical prediction task based on the EHR, especially physiological time series. We choose Physionet 2019 challenge public dataset to predict Sepsis outcomes in ICU units. Ten baseline machine learning models are compared, including 3 deep learning methods and 7 non-deep learning methods, commonly used in the clinical prediction domain. Nine evaluation metrics with specific clinical implications are used to assess the performance of models. Besides, we sub-sample training dataset sizes and use learning curve fit to investigate the impact of the training dataset size on the performance of the machine learning models. We also propose the general pre-processing method for the physiology time-series data and use Dice Loss to deal with the dataset imbalanced problem. The results show that deep learning indeed outperforms non-deep learning, but with certain conditions: firstly, evaluating with some particular evaluation metrics (AUROC, AUPRC, Sensitivity, and FNR), but not others; secondly, the training dataset size is large enough (with an estimation of a magnitude of thousands).

Yuhan Song, Armagan Elibol, Nak Young Chong

As recent advances in AI are causing the decline of conventional diagnostic methods, the realization of end-to-end diagnosis is fast approaching. Ultrasound image segmentation is an important step in the diagnostic process. An accurate and robust segmentation model accelerates the process and reduces the burden of sonographers. In contrast to previous research, we take two inherent features of ultrasound images into consideration: (1) different organs and tissues vary in spatial sizes, (2) the anatomical structures inside human body form a relatively constant spatial relationship. Based on those two ideas, we propose a new image segmentation model combining Feature Pyramid Network (FPN) and Spatial Recurrent Neural Network (SRNN). We discuss why we use FPN to extract anatomical structures of different scales and how SRNN is implemented to extract the spatial context features in abdominal ultrasound images.

Yuhan Song, Nak Young Chong

Ultrasound imaging is pivotal in various medical diagnoses due to its non-invasive nature and safety. In clinical practice, the accuracy and precision of ultrasound image analysis are critical. Recent advancements in deep learning are showing great capacity of processing medical images. However, the data hungry nature of deep learning and the shortage of high-quality ultrasound image training data suppress the development of deep learning based ultrasound analysis methods. To address these challenges, we introduce an advanced deep learning model, dubbed S-CycleGAN, which generates high-quality synthetic ultrasound images from computed tomography (CT) data. This model incorporates semantic discriminators within a CycleGAN framework to ensure that critical anatomical details are preserved during the style transfer process. The synthetic images are utilized to enhance various aspects of our development of the robot-assisted ultrasound scanning system. The data and code will be available at https://github.com/yhsong98/ct-us-i2i-translation.

Anand Krishnamoorthy Subramanian, Nak Young Chong

Deep Neural Networks (DNNs) have begun to thrive in the field of automation systems, owing to the recent advancements in standardising various aspects such as architecture, optimization techniques, and regularization. In this paper, we take a step towards a better understanding of Spectral Normalization (SN) and its potential for standardizing regularization of a wider range of Deep Learning models, following an empirical approach. We conduct several experiments to study their training dynamics, in comparison with the ubiquitous Batch Normalization (BN) and show that SN increases the gradient sparsity and controls the gradient variance. Furthermore, we show that SN suffers from a phenomenon, we call the mean-drift effect, which mitigates its performance. We, then, propose a weight reparameterization called as the Mean Spectral Normalization (MSN) to resolve the mean drift, thereby significantly improving the network's performance. Our model performs ~16% faster as compared to BN in practice, and has fewer trainable parameters. We also show the performance of our MSN for small, medium, and large CNNs - 3-layer CNN, VGG7 and DenseNet-BC, respectively - and unsupervised image generation tasks using Generative Adversarial Networks (GANs) to evaluate its applicability for a broad range of embedded automation tasks.

Kshitij Tiwari, Xuesu Xiao, Ville Kyrki et al.

This paper presents an approach for estimating the operational range for mobile robot exploration on a single battery discharge. Deploying robots in the wild usually requires uninterrupted energy sources to maintain the robot's mobility throughout the entire mission. However, for most endeavors into the unknown environments, recharging is usually not an option, due to the lack of pre-installed recharging stations or other mission constraints. In these cases, the ability to model the on-board energy consumption and estimate the operational range is crucial to prevent running out of battery in the wild. To this end, this work describes our recent findings that quantitatively break down the robot's on-board energy consumption and predict the operational range to guarantee safe mission completion on a single battery discharge cycle. Two range estimators with different levels of generality and model fidelity are presented, whose performances were validated on physical robot platforms in both indoor and outdoor environments. Model performance metrics are also presented as benchmarks.

Kshitij Tiwari, Xuesu Xiao, Nak Young Chong

Mobile robots are increasingly being used to assist with active pursuit and law enforcement. One major limitation for such missions is the resource (battery) allocated to the robot. Factors like nature and agility of evader, terrain over which pursuit is being carried out, plausible traversal velocity and the amount of necessary data to be collected all influence how long the robot can last in the field and how far it can travel. In this paper, we develop an analytical model that analyzes the energy utilization for a variety of components mounted on a robot to estimate the maximum operational range achievable by the robot operating on a single battery discharge. We categorize the major consumers of energy as: 1.) ancillary robotic functions such as computation, communication, sensing etc., and 2.) maneuvering which involves propulsion, steering etc. Both these consumers draw power from the common power source but the achievable range is largely affected by the proportion of power available for maneuvering. For this case study, we performed experiments with real robots on planar and graded surfaces and evaluated the estimation error for each case.

Barbara Bruno, Nak Young Chong, Hiroko Kamide et al.

Cultural competence is a well known requirement for an effective healthcare, widely investigated in the nursing literature. We claim that personal assistive robots should likewise be culturally competent, aware of general cultural characteristics and of the different forms they take in different individuals, and sensitive to cultural differences while perceiving, reasoning, and acting. Drawing inspiration from existing guidelines for culturally competent healthcare and the state-of-the-art in culturally competent robotics, we identify the key robot capabilities which enable culturally competent behaviours and discuss methodologies for their development and evaluation.

Barbara Bruno, Nak Young Chong, Hiroko Kamide et al.

The nursing literature shows that cultural competence is an important requirement for effective healthcare. We claim that personal assistive robots should likewise be culturally competent, that is, they should be aware of general cultural characteristics and of the different forms they take in different individuals, and take these into account while perceiving, reasoning, and acting. The CARESSES project is an Europe-Japan collaborative effort that aims at designing, developing and evaluating culturally competent assistive robots. These robots will be able to adapt the way they behave, speak and interact to the cultural identity of the person they assist. This paper describes the approach taken in the CARESSES project, its initial steps, and its future plans.