Many applications require a robot to accurately track reference end-effector trajectories. Certain trajectories may not be tracked as single, continuous paths due to the robot's kinematic constraints or obstacles elsewhere in the environment. In this situation, it becomes necessary to divide the trajectory into shorter segments. Each such division introduces a reconfiguration, in which the robot deviates from the reference trajectory, repositions itself in configuration space, and then resumes task execution. The occurrence of reconfigurations should be minimized because they increase the time and energy usage. In this paper, we present IKLink, a method for finding joint motions to track reference end-effector trajectories while executing minimal reconfigurations. Our graph-based method generates a diverse set of Inverse Kinematics (IK) solutions for every waypoint on the reference trajectory and utilizes a dynamic programming algorithm to find the globally optimal motion by linking the IK solutions. We demonstrate the effectiveness of IKLink through a simulation experiment and an illustrative demonstration using a physical robot.
This paper presents, for the first time, an image enhancement methodology designed to enhance the clarity of small intestinal villi in Wireless Capsule Endoscopy (WCE) images. This method first separates the low-frequency and high-frequency components of small intestinal villi images using guided filtering. Subsequently, an adaptive light gain factor is generated based on the low-frequency component, and an adaptive gradient gain factor is derived from the convolution results of the Laplacian operator in different regions of small intestinal villi images. The obtained light gain factor and gradient gain factor are then combined to enhance the high-frequency components. Finally, the enhanced high-frequency component is fused with the original image to achieve adaptive sharpening of the edges of WCE small intestinal villi images. The experiments affirm that, compared to established WCE image enhancement methods, our approach not only accentuates the edge details of WCE small intestine villi images but also skillfully suppresses noise amplification, thereby preventing the occurrence of edge overshooting.
We present the Evolving Graph Fourier Transform (EFT), the first invertible spectral transform that captures evolving representations on temporal graphs. We motivate our work by the inadequacy of existing methods for capturing the evolving graph spectra, which are also computationally expensive due to the temporal aspect along with the graph vertex domain. We view the problem as an optimization over the Laplacian of the continuous time dynamic graph. Additionally, we propose pseudo-spectrum relaxations that decompose the transformation process, making it highly computationally efficient. The EFT method adeptly captures the evolving graph's structural and positional properties, making it effective for downstream tasks on evolving graphs. Hence, as a reference implementation, we develop a simple neural model induced with EFT for capturing evolving graph spectra. We empirically validate our theoretical findings on a number of large-scale and standard temporal graph benchmarks and demonstrate that our model achieves state-of-the-art performance.
The next global mobile communication standard 6G strives to push the technological limits of radio frequency (RF) communication even further than its predecessors: Data rates beyond 100 Gbit/s, RF bandwidths above 1 GHz, and sub-millisecond latency necessitate very high performance development tools to enable the extent of innovation required for 6G's likely features. We propose a new SDR firmware and software architecture designed explicitly to meet these challenging requirements. It relies on Ethernet and commercial off-the-shelf network and server components to maximize flexibility and to reduce costs. We analyze state-of-the-art solutions (USRP X440 and other RFSoC-based systems), derive architectural design goals, explain resulting design decision in detail, and exemplify our architecture's implementation on the XCZU48DR RFSoC. Finally, we prove its performance via measurements and outline how the architecture surpasses the state-of-the-art with respect to sustained RF recording while maintaining high Ethernet bandwidth efficiency. Building a micro-Doppler radar example, we demonstrate its real-time and rapid application development capabilities.
In longitudinal observational studies with a time-to-event outcome, a common objective in causal analysis is to estimate the causal survival curve under hypothetical intervention scenarios within the study cohort. The g-formula is a particularly useful tool for this analysis. To enhance the traditional parametric g-formula approach, we developed a more adaptable Bayesian g-formula estimator. This estimator facilitates both longitudinal predictive and causal inference. It incorporates Bayesian additive regression trees in the modeling of the time-evolving generative components, aiming to mitigate bias due to model misspecification. Specifically, we introduce a more general class of g-formulas for discrete survival data. These formulas can incorporate the longitudinal balancing scores, which serve as an effective method for dimension reduction and are vital when dealing with an expanding array of time-varying confounders. The minimum sufficient formulation of these longitudinal balancing scores is linked to the nature of treatment regimes, whether static or dynamic. For each type of treatment regime, we provide posterior sampling algorithms, which are grounded in the Bayesian additive regression trees framework. We have conducted simulation studies to illustrate the empirical performance of our proposed Bayesian g-formula estimators, and to compare them with existing parametric estimators. We further demonstrate the practical utility of our methods in real-world scenarios using data from the Yale New Haven Health System's electronic health records.
Benchmarks play a crucial role in the development and analysis of reinforcement learning (RL) algorithms. We identify that existing benchmarks used for research into open-ended learning fall into one of two categories. Either they are too slow for meaningful research to be performed without enormous computational resources, like Crafter, NetHack and Minecraft, or they are not complex enough to pose a significant challenge, like Minigrid and Procgen. To remedy this, we first present Craftax-Classic: a ground-up rewrite of Crafter in JAX that runs up to 250x faster than the Python-native original. A run of PPO using 1 billion environment interactions finishes in under an hour using only a single GPU and averages 90% of the optimal reward. To provide a more compelling challenge we present the main Craftax benchmark, a significant extension of the Crafter mechanics with elements inspired from NetHack. Solving Craftax requires deep exploration, long term planning and memory, as well as continual adaptation to novel situations as more of the world is discovered. We show that existing methods including global and episodic exploration, as well as unsupervised environment design fail to make material progress on the benchmark. We believe that Craftax can for the first time allow researchers to experiment in a complex, open-ended environment with limited computational resources.
Leaky-integrate-and-fire (LIF) is studied as a non-linear operator that maps an integrable signal $f$ to a sequence $\eta_f$ of discrete events, the spikes. In the case without any Dirac pulses in the input, it makes no difference whether to set the neuron's potential to zero or to subtract the threshold $\vartheta$ immediately after a spike triggering event. However, in the case of superimpose Dirac pulses the situation is different which raises the question of a mathematical justification of each of the proposed reset variants. In the limit case of zero refractory time the standard reset scheme based on threshold subtraction results in a modulo-based reset scheme which allows to characterize LIF as a quantization operator based on a weighted Alexiewicz norm $\|.\|_{A, \alpha}$ with leaky parameter $\alpha$. We prove the quantization formula $\|\eta_f - f\|_{A, \alpha} < \vartheta$ under the general condition of local integrability, almost everywhere boundedness and locally finitely many superimposed weighted Dirac pulses which provides a much larger signal space and more flexible sparse signal representation than manageable by classical signal processing.
Modeling and simulation of autonomous vehicles plays a crucial role in achieving enterprise-scale realization that aligns with technical, business and regulatory requirements. Contemporary trends in digital lifecycle treatment have proven beneficial to support SBD as well as V&V of these complex systems. Although, the development of appropriate fidelity simulation models capable of capturing the intricate real-world physics and graphics (real2sim), while enabling real-time interactivity for decision-making, has remained a challenge. Nevertheless, recent advances in AI-based tools and workflows, such as online deep-learning algorithms leveraging live-streaming data sources, offer the tantalizing potential for real-time system-identification and adaptive modeling to simulate vehicles, environments, as well as their interactions. This transition from virtual prototypes to digital twins not only improves simulation fidelity and real-time factor, but can also support the development of online adaption/augmentation techniques that can help bridge the gap between simulation and reality (sim2real). In such a milieu, this work focuses on developing autonomy-oriented digital twins of vehicles across different scales and configurations to help support the streamlined development and deployment of Autoware stack, using a unified real2sim2real toolchain. Particularly, the core deliverable for this project was to integrate the Autoware stack with AutoDRIVE Ecosystem to demonstrate end-to-end task of map-based autonomous navigation. This work discusses the development of vehicle and environment digital twins using AutoDRIVE Ecosystem, along with various APIs and HMIs to connect with the same, followed by a detailed section on AutoDRIVE-Autoware integration. Furthermore, this study describes the first-ever off-road deployment of the Autoware stack, expanding the ODD beyond on-road autonomous navigation.
Modeling the correlations among errors is closely associated with how accurately the model can quantify predictive uncertainty in probabilistic time series forecasting. Recent multivariate models have made significant progress in accounting for contemporaneous correlations among errors, while a common assumption on these errors is that they are temporally independent for the sake of statistical simplicity. However, real-world observations often deviate from this assumption, since errors usually exhibit substantial autocorrelation due to various factors such as the exclusion of temporally correlated covariates. In this work, we propose an efficient method, based on a low-rank-plus-diagonal parameterization of the covariance matrix, which can effectively characterize the autocorrelation of errors. The proposed method possesses several desirable properties: the complexity does not scale with the number of time series, the resulting covariance can be used for calibrating predictions, and it can seamlessly integrate with any model with Gaussian-distributed errors. We empirically demonstrate these properties using two distinct neural forecasting models -- GPVar and Transformer. Our experimental results confirm the effectiveness of our method in enhancing predictive accuracy and the quality of uncertainty quantification on multiple real-world datasets.
Utilizing administrative data to predict outcomes is an important application area of machine learning, particularly in healthcare. Most administrative data records are timestamped and the pattern of records over time is a key input for machine learning models. This paper explores how best to divide the observation window of a machine learning model into time segments or "bins". A computationally efficient process is presented that identifies which data features benefit most from smaller, higher resolution time segments. Results generated on healthcare and housing/homelessness administrative data demonstrate that optimizing the time bin size of these high priority features while using a single time bin for the other features achieves machine learning models that are simpler and quicker to train. This approach also achieves similar and sometimes better performance than more complex models that default to representing all data features with the same time resolution.