Sequence Prediction of Driving Behavior Using Double Articulation Analyzer

Taniguchi, Tadahiro; Nagasaka, Shogo; Hitomi, Kentarou; Chandrasiri, Naiwala P.; Bando, Takashi; Takenaka, Kazuhito

doi:10.1109/tsmc.2015.2465933

Cited by 47 publications

(17 citation statements)

References 30 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In this study, a Neural Network (NN) is applied for simplicity after considering various learning techniques. Note that there have also been some other interesting developments on reference driving pattern generation by Bayesian nonparametric approaches in recent years, for examples Hierarchical Dirichlet Process-Hidden Markov Model (HDP-HMM) [43], [44] and Hierarchical Dirichlet Process-Hidden Semi Markov Model (HDP-HSMM) [45]. With careful craft, those approaches can be also applied.…”

Section: B Learning-based Reference Patternsmentioning

confidence: 99%

Behavior Monitoring Using Learning Techniques and Regular-Expressions-Based Pattern Matching

Shin

Turchi

et al. 2019

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

This paper addresses the problem of manoeuvre recognition and behaviour anomaly detection for generic targets by means of pattern matching techniques. The problem analysis is performed making specific reference to moving vehicles in a multi-lane road scenario, but the proposed technique can be easily extended to significantly different monitoring contexts. The potential extensions include, but are not limited to, public surveillance in train station or airport, road incidents and relative precursors detection and vehicle trajectories monitoring. The overall proposed solution consists of a trajectory analysis tool and a string-matching method. This allows integration of two different approaches, to detect both a-priori defined patterns of interest and generic manoeuvre/behaviour standing out from those regularly exhibited. This paper develops a new string matching method based on Regular Expressions. For generating reference patterns, a technique for the automatic definition of a dictionary of regular expressions matching the commonly observed target manoeuvres is presented. The advantages of the proposed approach are extensively analysed and tested by means of numerical simulations and experiments.

show abstract

Section: B Learning-based Reference Patternsmentioning

confidence: 99%

Behavior Monitoring Using Learning Techniques and Regular-Expressions-Based Pattern Matching

Shin

Turchi

et al. 2019

IEEE Trans. Intell. Transport. Syst.

View full text Add to dashboard Cite

show abstract

“…How to build a unified motion planning algorithm for heterogeneous vehicle platforms and use the driving experience to guide and accelerate the completion of planning tasks is one of the fundamental tasks for the further development of unmanned vehicle motion planning algorithms. In both the motion planning algorithm and the driving behavior representation algorithm, the decomposition of complex motion into motion primitives (MPs) can effectively improve the efficiency of the algorithm [7][8][9][10].…”

Section: Introductionmentioning

confidence: 99%

Generation and Selection of Driver-behavior-based Transferable Motion Primitives

Guan

Wang

Wei

et al. 2020

Preprint

View full text Add to dashboard Cite

In order to achieve the integration of driver experience and heterogeneous vehicle platform characteristics in the motion planning algorithm, based on the driver-behavior-based transferable motion primitives, a general motion planning framework for oine generation and online selection of motion primitives (MPs) is proposed. The optimal control theory is applied to solve the boundary value problems in the process of generating MPs, where the driver behaviors and the vehicle motion characteristics are integrated into the optimization in the form of constraints. Moreover, this paper proposes a layered, unequal-weighted MPs selection framework and utilizes the combination of environmental constraints, nonholonomic vehicle constraints, trajectory smoothness, and collision risk as the single-step extension evaluation index. The library of MPs generated oine demonstrates that the proposed generation method realizes the eective expansion of the MP types and achieves the diverse generation of MPs with various velocity attributes and platform types. We also present how the MP selection algorithm utilizes the unique MP library to achieve the online extension of MP sequences. The results show that the proposed motion planning framework can not only improve the eciency and rationality of the algorithm based on driving experience but also can transfer between heterogeneous vehicle platforms and highlight the unique motion characteristics of the platform.

show abstract

“…For example, Bender et al [9] developed an unsupervised method, Bayesian multivariate linear model, to segment a time-series inertial data into finite amounts of linear portions for inferring driver behaviors, but only for a two-dimensional data sequence of one vehicle. Taniguchi et al [10] introduced a double articulation analyzer based on nonparametric Bayesian theory to predict driver behaviors with a six-dimensional data sequence, consisting of gas pedal position, brake pressure, steering angle, velocity, acceleration, and steering angle rate. They also developed an unsupervised approach to segment and predict driver's upcoming behavior by detecting and learning contextual changing points [11].…”

Section: Introductionmentioning

confidence: 99%

Extracting Traffic Primitives Directly From Naturalistically Logged Data for Self-Driving Applications

Wang

Zhao

2018

IEEE Robot. Autom. Lett.

View full text Add to dashboard Cite

Developing an automated vehicle, that can handle complicated driving scenarios and appropriately interact with other road users, requires the ability to semantically learn and understand driving environment, oftentimes, based on analyzing massive amounts of naturalistic driving data. An important paradigm that allows automated vehicles to both learn from human drivers and gain insights is understanding the principal compositions of the entire traffic, termed as traffic primitives. However, the exploding data growth presents a great challenge in extracting primitives from highdimensional time-series traffic data with various types of road users engaged. Therefore, automatically extracting primitives is becoming one of the cost-efficient ways to help autonomous vehicles understand and predict the complex traffic scenarios. In addition, the extracted primitives from raw data should 1) be appropriate for automated driving applications and also 2) be easily used to generate new traffic scenarios. However, existing literature does not provide a method to automatically learn these primitives from large-scale traffic data. The contribution of this paper has two manifolds. The first one is that we proposed a new framework to generate new traffic scenarios from a handful of limited traffic data. The second one is that we introduce a nonparametric Bayesian learning method -a sticky hierarchical Dirichlet process hidden Markov model -to automatically extract primitives from multidimensional traffic data without prior knowledge of the primitive settings. The developed method is then validated using one day of naturalistic driving data. Experiment results show that the nonparametric Bayesian learning method is able to extract primitives from traffic scenarios where both the binary and continuous events coexist.

show abstract

Sequence Prediction of Driving Behavior Using Double Articulation Analyzer

Cited by 47 publications

References 30 publications

Behavior Monitoring Using Learning Techniques and Regular-Expressions-Based Pattern Matching

Behavior Monitoring Using Learning Techniques and Regular-Expressions-Based Pattern Matching

Generation and Selection of Driver-behavior-based Transferable Motion Primitives

Extracting Traffic Primitives Directly From Naturalistically Logged Data for Self-Driving Applications

Contact Info

Product

Resources

About