Data-driven trajectory prediction with weather uncertainties: A Bayesian deep learning approach

Pang, Yutian; Zhao, Xinyu; Yan, Hao; Liu, Yongming

doi:10.1016/j.trc.2021.103326

Cited by 64 publications

(13 citation statements)

References 23 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…There exists randomness in almost every aspect of UTM (e.g., UAS operation, environment). Thus, uncertainty quantification of aircraft operations is critical for future safety analysis (e.g., the deviation from a trajectory plan due to wind, true speed, positioning error) [52], [54]- [58]. Thus, to model the uncertainties in UAS operation, we form a circle, the center of which is the predicted UAS position without uncertainty.…”

Section: ) Circular Obstacle Avoidance With Uncertaintymentioning

confidence: 99%

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

Yang

Wang

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

Obstacle avoidance for small unmanned aircraft is vital for the safety of future urban air mobility (UAM) and Unmanned Aircraft System (UAS) Traffic Management (UTM). There are a variety of techniques for real-time robust drone guidance, but numerous of them solve in discretized airspace and control, which would require an additional path smoothing step to provide flexible commands for UAS. To deliver safe and computationally efficient guidance for UAS operations, we explore the use of a deep reinforcement learning algorithm based on Proximal Policy Optimization (PPO) to lead autonomous UAS to their destinations while bypassing obstacles through continuous control. The proposed scenario state representation and reward function can map the continuous state space to continuous control for both heading angle and speed. To verify the effectiveness of the proposed learning framework, we conducted numerical experiments with static and moving obstacles. Uncertainties associated with the environments and safety operation bounds are investigated in detail. Results show that the proposed model is able to provide accurate and robust guidance and resolve conflict with a success rate of over 99%.INDEX TERMS continuous control, deep reinforcement learning, UAS obstacle avoidance, uncertainty.

show abstract

Section: ) Circular Obstacle Avoidance With Uncertaintymentioning

confidence: 99%

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

Yang

Wang

et al. 2022

IEEE Access

Self Cite

View full text Add to dashboard Cite

show abstract

“…UAS operation is stochastic and randomness exists in almost every aspect of UTM. Inclusion of uncertainty quantification of aircraft operation is critical for future safety analysis (e.g., deviation from a trajectory plan due to wind, true speed, positioning error) Liu & Goebel, 2018;Pang et al, 2019bPang et al, ,a, 2021. Thus, to model the uncertainties in UAS operation, we form a circle, the center of which is the predicted UAS position without uncertainty.…”

Section: Circular Obstacle Avoidance With Uncertaintymentioning

confidence: 99%

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

Hu¹,

Yang²,

Wang³

et al. 2021

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…[3,–5]). However, there is a high level of epistemic uncertainty inherent in this approach due to: the simplifications necessarily made by the model; an uncertain knowledge of the aircraft’s state; lack of knowledge of the pilot’s intentions [6]; and the unknown influence of environmental effects on the aircraft trajectory [7]. As a consequence, a mismatch between the predictions of physics-based TP methods and the actual path followed by aircraft can be observed, especially during climbs and descents [8,9].…”

Section: Introductionmentioning

confidence: 99%

“…Firstly, given that high levels of epistemic uncertainty contribute so significantly to model-mismatch in state-of-the-art equations-based models, a probabilistic approach would appear to be essential. Next generation TP models must be able to efficiently handle uncertainties and to clearly express the uncertainty in the model predictions [7,16]. This is the motivation for approaches based on sequential Monte Carlo sampling [17] and Gaussian mixture models in the TP literature [1,18].…”

Section: Introductionmentioning

confidence: 99%

A probabilistic model for aircraft in climb using monotonic functional Gaussian process emulators

et al. 2023

View full text Add to dashboard Cite

Ensuring vertical separation is a key means of maintaining safe separation between aircraft in congested airspace. Aircraft trajectories are modelled in the presence of significant epistemic uncertainty, leading to discrepancies between observed trajectories and the predictions of deterministic models, hampering the task of planning to ensure safe separation. In this paper, a probabilistic model is presented, for the purpose of emulating the trajectories of aircraft in climb and bounding the uncertainty of the predicted trajectory. A monotonic, functional representation exploits the spatio-temporal correlations in the radar observations. Through the use of Gaussian process emulators, features that parameterize the climb are mapped directly to functional outputs, providing a fast approximation, while ensuring that the resulting trajectory is monotonic. The model was applied as a probabilistic digital twin for aircraft in climb and baselined against the base of aircraft data, a deterministic model widely used in industry. When applied to an unseen test dataset, the probabilistic model was found to provide a mean prediction that was 20.56% more accurate, as measured by the mean absolute error, with data-driven credible intervals that were9.54% sharper.

show abstract

Data-driven trajectory prediction with weather uncertainties: A Bayesian deep learning approach

Cited by 64 publications

References 23 publications

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

Obstacle Avoidance for UAS in Continuous Action Space Using Deep Reinforcement Learning

A probabilistic model for aircraft in climb using monotonic functional Gaussian process emulators

Contact Info

Product

Resources

About