Designing reward functions for agile robotic maneuvers in reinforcement learning remains difficult, and demonstration-based approaches often require reference motions that are unavailable for novel platforms or extreme stunts. We present LineRides, a line-guided learning framework that enables a custom bicycle robot to acquire diverse, commandable stunt behaviors from a user-provided spatial guideline and sparse key-orientations, without demonstrations or explicit timing. LineRides handles physically infeasible guidelines using a tracking margin that permits controlled deviation, resolves temporal ambiguity by measuring progress via traveled distance along the guideline, and disambiguates motion details through position- and sequence-based key-orientations. We evaluate LineRides on the Ultra Mobility Vehicle (UMV) and show that the policy trained with our methods supports seamless transitions between normal driving and stunt execution, enabling five distinct stunts on command: MiniHop, LargeHop, ThreePointTurn, Backflip, and DriftTurn.
Stunting detection is a significant issue in Indonesian healthcare, causing lower cognitive function, lower productivity, a weakened immunity, delayed neuro-development, and degenerative diseases. In regions with a high prevalence of stunting and limited welfare resources, identifying children in need of treatment is critical. The diagnostic process often raises challenges, such as the lack of experience in medical workers, incompatible anthropometric equipment, and inefficient medical bureaucracy. To counteract the issues, the use of load cell sensor and ultrasonic sensor can provide suitable anthropometric equipment and streamline the medical bureaucracy for stunting detection. This paper also employs machine learning for stunting detection based on sensor readings. The experiment results show that the sensitivity of the load cell sensor and the ultrasonic sensor is 0.9919 and 0.9986, respectively. Also, the machine learning test results have three classification classes, which are normal, stunted, and stunting with an accuracy rate of 98\%.
This work demonstrates a front-flip on bicycle robots via reinforcement learning, particularly by imitating reference motions that are infeasible and imperfect. To address this, we propose Iterative Motion Imitation(IMI), a method that iteratively imitates trajectories generated by prior policy rollouts. Starting from an initial reference that is kinematically or dynamically infeasible, IMI helps train policies that lead to feasible and agile behaviors. We demonstrate our method on Ultra-Mobility Vehicle (UMV), a bicycle robot that is designed to enable agile behaviors. From a self-colliding table-to-ground flip reference generated by a model-based controller, we are able to train policies that enable ground-to-ground and ground-to-table front-flips. We show that compared to a single-shot motion imitation, IMI results in policies with higher success rates and can transfer robustly to the real world. To our knowledge, this is the first unassisted acrobatic flip behavior on such a platform.
The next generation of active safety features in autonomous vehicles should be capable of safely executing evasive hazard-avoidance maneuvers akin to those performed by professional stunt drivers to achieve high-agility motion at the limits of vehicle handling. This paper presents a novel framework, ManeuverGPT, for generating and executing high-dynamic stunt maneuvers in autonomous vehicles using large language model (LLM)-based agents as controllers. We target aggressive maneuvers, such as J-turns, within the CARLA simulation environment and demonstrate an iterative, prompt-based approach to refine vehicle control parameters, starting tabula rasa without retraining model weights. We propose an agentic architecture comprised of three specialized agents (1) a Query Enricher Agent for contextualizing user commands, (2) a Driver Agent for generating maneuver parameters, and (3) a Parameter Validator Agent that enforces physics-based and safety constraints. Experimental results demonstrate successful J-turn execution across multiple vehicle models through textual prompts that adapt to differing vehicle dynamics. We evaluate performance via established success criteria and discuss limi
Novalike variables are a subgroup of cataclysmic variables (CVs) that -- unlike dwarf novae -- do not exhibit strong brightenings in their long-term light curves. Variations over time scales of weeks, months or years are mostly restricted to irregular low-amplitude modulations. However, some of them occasionally suffer from so-called stunted outbursts, that is, small-scale brightenings of less than a magnitude lasting for a couple of days to weeks. There is no consensus about the physical mechanisms behind these outbursts. Here I discuss the common properties of a group of novalike variables (which I call AH~Pictoris stars after its most prominent member) that exhibit a continuous train of successive stunted outbursts over their entire observational history, or at least for several years. The outburst amplitudes are stable in a given system, always ranging between 0.5 and 1~mag in the visual band. The outburst intervals, at an overall range between 12 and 30 days, and the outburst profiles can gradually evolve, but no sudden changes are observed. On shorter time scales the orbital waveforms are not only surprisingly similar, but also evolve in the same way over the outburst cycle.
In this article, we introduce the notion of $\mathcal P$-triviality of topological manifolds and give a complete description of the $\mathcal P$-triviality of stunted real and complex projective spaces.
Disease detection in sugarcane, particularly the identification of asymptomatic infectious diseases such as Ratoon Stunting Disease (RSD), is critical for effective crop management. This study employed various machine learning techniques to detect the presence of RSD in different sugarcane varieties, using vegetation indices derived from freely available satellite-based spectral data. Our results show that the Support Vector Machine with a Radial Basis Function Kernel (SVM-RBF) was the most effective algorithm, achieving classification accuracy between 85.64% and 96.55%, depending on the variety. Gradient Boosting and Random Forest also demonstrated high performance achieving accuracy between 83.33% to 96.55%, while Logistic Regression and Quadratic Discriminant Analysis showed variable results across different varieties. The inclusion of sugarcane variety and vegetation indices was important in the detection of RSD. This agreed with what was identified in the current literature. Our study highlights the potential of satellite-based remote sensing as a cost-effective and efficient method for large-scale sugarcane disease detection alternative to traditional manual laboratory testin
Learning with few labeled tabular samples is often an essential requirement for industrial machine learning applications as varieties of tabular data suffer from high annotation costs or have difficulties in collecting new samples for novel tasks. Despite the utter importance, such a problem is quite under-explored in the field of tabular learning, and existing few-shot learning schemes from other domains are not straightforward to apply, mainly due to the heterogeneous characteristics of tabular data. In this paper, we propose a simple yet effective framework for few-shot semi-supervised tabular learning, coined Self-generated Tasks from UNlabeled Tables (STUNT). Our key idea is to self-generate diverse few-shot tasks by treating randomly chosen columns as a target label. We then employ a meta-learning scheme to learn generalizable knowledge with the constructed tasks. Moreover, we introduce an unsupervised validation scheme for hyperparameter search (and early stopping) by generating a pseudo-validation set using STUNT from unlabeled data. Our experimental results demonstrate that our simple framework brings significant performance gain under various tabular few-shot learning ben
In this article we describe and apply the Fay-Herriot model with spatially correlated random area effects (Pratesi, M., & Salvati, N. (2008)), in order to predict the prevalence of anemia and childhood stunting in Peruvian districts, based on the data from the Demographic and Family Health Survey of the year 2019, which collects data about anemia and childhood stunting for children under the age of 12 years, and the National Census carried out in 2017. Our main objective is to produce reliable predictions for the districts, where sample sizes are too small to provide good direct estimates, and for the districts, which were not included in the sample. The basic Fay-Herriot model (Fay & Herriot, 1979) tackles this problem by incorporating auxiliary information, which is generally available from administrative or census records. The Fay-Herriot model with spatially correlated random area effects, in addition to auxiliary information, incorporates geographic information about the areas, such as latitude and longitude. This permits modeling spatial autocorrelations, which are not unusual in socioeconomic and health surveys. To evaluate the mean square error of the above-mentione
Based on early Kepler data, Ostensen et al. (2010) found that KIC 9202990 showed a 4 hr and a two-week photometric period. They suggested the 4 hr period was a signature of an orbital period; the longer period was possibly due to precession of an accretion disk and KIC 9202990 was a cataclysmic variable with an accretion disk which is always in a bright state (a nova-like system). Using the full Kepler dataset on KIC 9202990 which covers 1421 d (Quarter 2--17), and includes 1 min cadence data from the whole of Quarters 5 and 16, we find that the 4 hr period is stable and therefore a signature of the binary orbital period. In contrast, the 10--12 d period is not stable and shows an amplitude between 20--50 percent. This longer period modulation is similar to those nova-like systems which show `stunted' outbursts. We discuss the problems that a precessing disk model has in explaining the observed characteristics and indicate why we favour a stunted outburst model. Although such stunted events are considered to be related to the standard disk instability mechanism, their origin is not well understood. KIC 9202990 shows the lowest amplitude and shortest period of continuous stunted out
We describe two observations of the nova-like cataclysmic variable AC Cnc obtained with {\it Kepler} during its revamped second mission ({\it K2}). Using the {\it K2} 1-minute cadence mode, the data were obtained during Campaigns 5 and 18. Campaign 5 (C05) lasted from ${\sim}$2015 Apr 27 to ${\sim}$2015 July 10, a total of 74.8 days, and yielded ${\sim}$106,000 measurements. Campaign 18 (C18) lasted from ${\sim}$2018 May 13 to ${\sim}$2018 July 2, a total of 50.7 days, yielding $\sim$72,000 measurements. The C05 light curve reveals two `stunted outbursts' having properties consistent with stunted bursts observed from the ground; a stunted burst was underway during the C18 observation when it ended. During a stunted outburst, the primary eclipse is found to increase in depth but the residual brightness at mid-primary-eclipse remains nearly constant. By contrast, the secondary eclipse retains the same depth but the brightness at mid-secondary eclipse increases during outburst, following the orbital variations of the out-of-eclipse light. The eclipse ephemeris is statistically consistent with historical ephemerides and shows only marginal evidence for a period change. On the basis of
This paper presents a safety guaranteed control method for an autonomous vehicle ski-stunt maneuver, that is, a vehicle moving with two one-side wheels. To capture the vehicle dynamics precisely, a Gaussian process model is used as additional correction to the nominal model that is obtained from physical principles. We construct a probabilistic control barrier function (CBF) to guarantee the planar motion safety. The CBF and the balance equilibrium manifold are enforced as the constraints into a safety critical control form. Under the proposed control method, the vehicle avoids the obstacle collision and safely maintain the balance for autonomous ski-stunt maneuvers. We conduct numerical simulation validation to demonstrate the control design. Preliminary experiment results are also presented to confirm the learning-based motion control using a scaled RC truck for autonomous ski-stunt maneuvers.
Let $E\mathbb{R}$ be an even-periodic Real Landweber exact $C_2$-spectrum, and $ER$ its spectrum of fixed points. We compute the $ER$-cohomology of the infinite stunted projective spectra $P_j$. These cohomology groups combine to form the $RO(C_2)$-graded coefficient ring of the $C_2$-spectrum $b(ER) = F(EC_{2+},i_\ast ER)$, which we show is related to $E\mathbb{R}$ by a cofiber sequence $Σ^σb(ER)\rightarrow b(ER)\rightarrow E\mathbb{R}$. We illustrate our description of $π_\star b(ER)$ with the computation of some $ER$-based Mahowald invariants.
We report a time-lapse eclipse mapping analysis of B-band time-series of the nova-like variable UU Aqr along a typical stunted outburst in 2002 August. Disc asymmetries rotating in the prograde sense in the eclipse maps are interpreted as a precessing elliptical disc with enhanced emission at periastron. From the disc expansion velocity a disc viscosity alpha_{hot}= 0.2 is inferred. The outburst starts with a 10-fold increase in uneclipsed light, probably arising in an enhanced disc wind; the disc response is delayed by 2 d. The results are inconsistent with the disc instability model and suggest that the stunted outburst of UU Aqr are the response of its viscous accretion disc to enhanced mass-transfer events.
Most previous studies of the causal relationship between malaria and stunting have been studies where potential confounders are controlled via regression-based methods, but these studies may have been biased by unobserved confounders. Instrumental variables (IV) regression offers a way to control for unmeasured confounders where, in our case, the sickle cell trait can be used as an instrument. However, for the instrument to be valid, it may still be important to account for measured confounders. The most commonly used instrumental variable regression method, two-stage least squares, relies on parametric assumptions on the effects of measured confounders to account for them. Additionally, two-stage least squares lacks transparency with respect to covariate balance and weighing of subjects and does not blind the researcher to the outcome data. To address these drawbacks, we propose an alternative method for IV estimation based on full matching. We evaluate our new procedure on simulated data and real data concerning the causal effect of malaria on stunting among children. We estimate that the risk of stunting among children with the sickle cell trait decrease by 0.22 times the averag
Malaria, childhood acute respiratory infection, and child undernutrition together account for over two million deaths annually in children under five, with the burden concentrated in low and middle-income countries where climate variability modulates transmission, exposure, and nutritional outcomes. Routine health surveillance in these settings remains sparse and reactive. Satellite-derived representations of the Earth's surface offer a scalable, low-cost complement to traditional covariates, yet their utility as predictors of population health outcomes is poorly characterised. We summarise findings from three studies evaluating AlphaEarth Foundations 64-dimensional satellite embeddings as predictors of population health outcomes, focusing on vulnerable populations. The studies span infectious disease (malaria, respiratory infection) and stunting. In each study, embeddings provide predictive value at sufficient spatial granularity: (i) malaria prediction across Nigeria shows consistent per-region R^2 gains; (ii) childhood acute respiratory infection prediction across 11 DHS countries increases pooled R^2 from 0.157 to 0.206 across three tree-based estimators; (iii) stunting predict
We introduce and solve from first principles a continuous-time quantum walk with absorption generated by a Lindblad boundary sink of arbitrary strength. Tracing out the sink maps the problem onto a non-Hermitian tight-binding Hamiltonian with a rank-one imaginary defect on the semi infinite line. We obtain closed-form expressions for the exact propagator and first-passage statistics. Weak coupling limits absorption through inefficient transfer into the sink, whereas for strong dissipation, boundary occupation is stunted by the emergence of a localized non-Hermitian mode. Despite the different physical origin of these suppression mechanisms, we show their respective asymptotic absorption probabilities exhibits an exact duality. The evolution is conveniently visualized in phase-space, where the non-Hermitian mode produces a Wigner droplet exponentially confined near the edge site.
Econometrics in general, and Panel Data methods in particular, are becoming crucial in Public Health Economics and Social Policy analysis. In this discussion paper, we employ a helpful approach of Feasible Generalized Least Squares (FGLS) to assess if there are statistically relevant relationships between hemoglobin (adjusted to sea-level), weight, and height from 2007 to 2022 in children up to five years of age in Peru. By using this method, we may find a tool that allows us to confirm if the relationships considered between the target variables by the Peruvian agencies and authorities are in the right direction to fight against chronic malnutrition and stunting.
The potato is a widely grown crop in many regions of the world. In recent decades, potato farming has gained incredible traction in the world. Potatoes are susceptible to several illnesses that stunt their development. This plant seems to have significant leaf disease. Early Blight and Late Blight are two prevalent leaf diseases that affect potato plants. The early detection of these diseases would be beneficial for enhancing the yield of this crop. The ideal solution is to use image processing to identify and analyze these disorders. Here, we present an autonomous method based on image processing and machine learning to detect late blight disease affecting potato leaves. The proposed method comprises four different phases: (1) Histogram Equalization is used to improve the quality of the input image; (2) feature extraction is performed using a Deep CNN model, then these extracted features are concatenated; (3) feature selection is performed using wrapper-based feature selection; (4) classification is performed using an SVM classifier and its variants. This proposed method achieves the highest accuracy of 99% using SVM by selecting 550 features.
The promise of Large Language Model (LLM) agents is to perform complex, stateful tasks. This promise is stunted by significant risks - policy violations, process corruption, and security flaws - that stem from the lack of visibility and mechanisms to manage undesirable data flows produced by agent actions. Today, agent workflows are responsible for enforcing these policies in ad hoc ways. Just as data validation and access controls shifted from the application to the DBMS, freeing application developers from these concerns, we argue that systems should support Data Flow Controls (DFCs) and enforce DFC policies natively. This paper describes early work developing a portable instance of DFC for DBMSes and outlines a broader research agenda toward DFC for agent ecosystems.