Search for: All records

Lack of high‐resolution observations in the inner‐core of tropical cyclones remains a key issue when constructing an accurate initial state of the storm structure. The major implication of an improper initial state is the poor predictability of the future state of the storm. The size and associated hazard from strong winds at the inner‐core make it impossible to sample this region entirely. However, targeting regions of the inner‐core where forecasted atmospheric measurements have high uncertainty can significantly improve the accuracy of measurements for the initial state of the storm. This study provides a scheme for targeted high‐resolution observations for small Unmanned Aircraft Systems (sUAS) platforms (e.g., Coyote sUAS) to improve the estimates of the atmospheric measurement in the inner‐core structure. The benefit of observation is calculated based on the high‐fidelity state‐of‐the‐art hurricane ensemble data assimilation system. Potential locations with the mostinformativemeasurements are identified through exploration of various simulation‐based solutions depending on the state variables (e.g., pressure, temperature, wind speed, relative humidity) and a combined representation of those variables. A sampling‐based sUAS path planning algorithm considers energy usage when locating the regions of highly uncertain prediction of measurements, allowing sUAS to maximize the benefit of observation. Robustness analysis of our algorithm for multiple scenarios of sUAS drop and goal locations shows satisfactory performance against benchmark similar to current NOAA field campaign. With optimized sUAS observations, a data assimilation analysis shows significant improvements of up to 4% in the tropical cyclone structure estimates after resolving uncertainties at targeted locations.

 

Recent advances in computer vision for space exploration have handled prediction uncertainties well by approximating multimodal output distribution rather than averaging the distribution. While those advanced multimodal deep learning models could enhance the scientific and engineering value of autonomous systems by making the optimal decisions in uncertain environments, sequential learning of those approximated information has depended on unimodal or bimodal probability distribution. In a sequence of information learning and transfer decisions, the traditional reinforcement learning cannot accommodate the noise in the data that could be useful for gaining information from other locations, thus cannot handle multimodal and multivariate gains in their transition function. Still, there is a lack of interest in learning and transferring multimodal space information effectively to maximally remove the uncertainty. In this study, a new information theory overcomes the traditional entropy approach by actively sensing and learning information in a sequence. Particularly, the autonomous navigation of a team of heterogeneous unmanned ground and aerial vehicle systems in Mars outperforms benchmarks through indirect learning. 

Recent advances in computer vision for space exploration have handled prediction uncertainties well by approximating multimodal output distribution rather than averaging the distribution. While those advanced multimodal deep learning models could enhance the scientific and engineering value of autonomous systems by making the optimal decisions in uncertain environments, sequential learning of those approximated information has depended on unimodal or bimodal probability distribution. In a sequence of information learning and transfer decisions, the traditional reinforcement learning cannot accommodate the noise in the data that could be useful for gaining information from other locations, thus cannot handle multimodal and multivariate gains in their transition function. Still, there is a lack of interest in learning and transferring multimodal space information effectively to maximally remove the uncertainty. In this study, a new information theory overcomes the traditional entropy approach by actively sensing and learning information in a sequence. Particularly, the autonomous navigation of a team of heterogeneous unmanned ground and aerial vehicle systems in Mars outperforms benchmarks through indirect learning. 

Current free and subscription-based trip planners have heavily focused on providing available transit options to improve the first and last-mile connectivity to the destination. However, those trip planners may not truly be multimodal to vulnerable road users (VRU)s since those selected side walk routes may not be accessible or feasible for people with disability. Depending on the level of availability of digital twin of travelers behaviors and sidewalk inventory, providing the personalized suggestion about the sidewalk with route features coupled with transit service reliability could be useful and happier transit riders may boost public transit demand/funding and reduce rush hour congestion. In this paper, the adaptive trip planner considers the real-time impact of environment changes on pedestrian route choice preferences (e.g., fatigue, weather conditions, unexpected construction, road congestion) and tolerance level in response to transit service uncertainty. Side walk inventory is integrated in directed hypergraph on the General Transit Feed Specification to specify traveler utilities as weights on the hyperedge. A realistic assessment of the effect of the user-defined preferences on a traveler’s path choice is presented for a section of the Boston transit network, with schedule data from the Massachusetts Bay Transportation Authority. Different maximum utility values are presented as a function of varying traveler’s risk-tolerance levels. In response to unprecedented climate change, poverty, and inflation, this new trip planner can be adopted by state agencies to boost their existing public transit demand without extra efforts 

Estimating multimodal distributions of travel times (TT) from real-world data is critical for understanding and managing congestion. Mixture models can estimate the overall distribution when distinct peaks exist in the probability density function, but no transfer of mixture information under epistemic uncertainty across different spatiotemporal scales has been considered for capturing unobserved heterogeneity. In this paper, a physics-informed and -regularized (PIR) prediction model is developed that shares observations across similarly distributed network segments over time and space. By grouping similar mixture models, the model uses a particular sample distribution at distant non-contiguous unexplored locations and improves TT prediction. The model includes hierarchical Kalman filtering (KF) updates using the traffic fundamental diagram to regulate any spurious correlation and estimates the mixture of TT distributions from observations at the current location and time sampled from the multimodal and multivariate TT distributions at other locations and times. In order to overcome the limitations of KF, this study developed dynamic graph neural network (GCN) model which uses time evolving spatial correlations. The KF model with PIR predicts traffic state with 19% more accuracy than TMML model in Park et al.(2022) and GCN model will further reduce the uncertainty in prediction. This study uses information gain from explored correlated links to obtain accurate predictions for unexplored ones. 

Paratransit services are indispensable for vulnerable road users, especially for the elderly and the disabled who lack other available mobility options or face lower accessibility to public transit systems. There are some recurrent disturbances that would be simpler to predict and, it is reasonable suspicion that there exists a significant relationship between the spatiotemporal characteristics of a location and the amount of potential delay. Therefore, this study proposes the incorporation of dwell time uncertainty in paratransit operation systems. It will use temporal multimodal multivariate learning (TMML) and the contextual bandit (CB) to estimate the impact of features on loading time. 

Drivers traveling on the road usually choose the route which will reduce their own travel time without giving a thought about how this decision will affect other users in the traffic network. Their behaviours leads to problem of oscillating congestion on the roads in the event of traffic disruption. This paper addresses this issue by adopting a competing optimal approach for informed and uninformed drivers. Informed drivers are proposed with alternate routes that reduce the system cost while uninformed drivers continue their journey on originally proposed routes. This strategy of dispersing traffic can reduce congestion significantly. The framework is implemented using Transmodeler, a traffic simulation by experimenting with varying percentage of informed drivers in the network. 

Traffic systems exhibit supply-side uncertainty which is alleviated through real-time information. This article explores subscription models for a private agency sharing data at a fixed rate. A multiclass strategy-based equilibrium model is developed for two classes of subscribed and unsubscribed travelers, whose optimal strategy given the link-state costs is modeled as a Markov decision process (MDP) and a partially-observable MDP, respectively. A utility-based subscription choice model is formulated to study the impacts of subscription rates on the percentage of travelers choosing to subscribe. Solutions to the fixed-point formulation are determined using iterative algorithms. The proposed subscription model can be used for designing optimal subscription rates in various settings where real-time information can be a valuable routing tool such as express lanes, parking systems, roadside delivery, and routing of vulnerable road users. 

Estimating multimodal distributions of travel times from real-world data is critical for understanding and managing congestion. Mixture models can estimate the overall distribution when distinct peaks exist in the probability density function, but no transfer of mixture information under epistemic uncertainty across different spatiotemporal scales has been considered for capturing unobserved heterogeneity. In this paper, a physics-informed and -regularized prediction model is developed that shares observations across similarly distributed network segments across time and space. By grouping similar mixture models, the model uses a particular sample distribution at distant non-contiguous unexplored locations and improves TT prediction. Compared to traditional prediction without those updates, the proposed model's 19% of performance show the benefit of indirect learning. Different from traditional travel time prediction tools, the developed model can be used by traffic and planning agencies in knowing how far back in history and what sample size of historic data would be useful for current prediction. 

Predictive routing is effective in knowledge transfer. However, it ignores information gained from probability distributions with more than one peak. We introduce traffic multimodal information learning, a new class of transportation decision-making models that can learn and transfer online information from multiple simultaneous observations of a probability distribution with multiple peaks or multiple outcome variables from one time stage to the next. Multimodal learning improves the scientific and engineering value of autonomous vehicles by determining the best routes based on the intended level of exploration, risk, and limits.