• Corpus ID: 219792667

Robust Unsupervised Learning of Temporal Dynamic Interactions

@article{Guha2020RobustUL,
  title={Robust Unsupervised Learning of Temporal Dynamic Interactions},
  author={Aritra Guha and Rayleigh Lei and Jiacheng Zhu and XuanLong Nguyen and Ding Zhao},
  journal={ArXiv},
  year={2020},
  volume={abs/2006.10241}
}
Robust representation learning of temporal dynamic interactions is an important problem in robotic learning in general and automated unsupervised learning in particular. Temporal dynamic interactions can be described by (multiple) geometric trajectories in a suitable space over which unsupervised learning techniques may be applied to extract useful features from raw and high-dimensional data measurements. Taking a geometric approach to robust representation learning for temporal dynamic… 

Figures and Tables from this paper

References

SHOWING 1-10 OF 46 REFERENCES

A Bayesian nonparametric approach to modeling motion patterns

This work proposes modeling target motion patterns as a mixture of Gaussian processes with a Dirichlet process prior over mixture weights, which provides an adaptive representation for each individual motion pattern and automatically adjusts the complexity of the motion model based on the available data.

Local Robustness in Bayesian Analysis

The use of local analysis to study sensitivity in contexts broader than merely prior uncertainty is discussed, ranging from differentiation of functions to differentiation of functionals (e.g., assessing sensitivity to hyperparameters) and so on.

Bayesian influence analysis: a geometric approach.

A general framework of Bayesian influence analysis for assessing various perturbation schemes to the data, the prior and the sampling distribution for a class of statistical models is developed.

Modeling Multi-Vehicle Interaction Scenarios Using Gaussian Random Field

A method to model multi-vehicle interactions using a stochastic vector field model and apply non-parametric Bayesian learning to extract the underlying motion patterns from a large quantity of naturalistic traffic data is proposed.

Learning V2V interactive driving patterns at signalized intersections

An Unsupervised Approach for Inferring Driver Behavior From Naturalistic Driving Data

Although the method is unsupervised, the clusters produced exhibit high-level patterns that can easily be associated with driving behaviors such as braking, turning, accelerating, and coasting.

Unsupervised Hierarchical Modeling of Driving Behavior and Prediction of Contextual Changing Points

An unsupervised learning method, called double articulation analyzer with temporal prediction (DAA-TP), is proposed on the basis of the original DAA model. The method will enable future advanced

Probabilistic Trajectory Prediction for Autonomous Vehicles with Attentive Recurrent Neural Process

The meta-learning instinct of NPs enables the proposed ARNP model to capture global information of all observations, thereby being able to adapt to new targets efficiently, and outperforms previous counterparts in terms of accuracy and uncertainty expressiveness.

Multi-Vehicle Interaction Scenarios Generation with Interpretable Traffic Primitives and Gaussian Process Regression

The proposed method can generate a bunch of human-like multi-vehicle interaction trajectories that can fit different road conditions remaining the key interaction patterns of agents in the provided scenarios, which is import to the development of autonomous vehicles.

Learning from Multiple Cities: A Meta-Learning Approach for Spatial-Temporal Prediction

This paper is the first to leverage information from multiple cities to increase the stability of transfer and designs a spatial-temporal network with a meta-learning paradigm designed to utilize the long-period data from other cities via transfer learning.