Kentarou Hitomi

Semiotic prediction of driving behavior using unsupervised double articulation analyzer

In this paper, we propose a novel semiotic prediction method for driving behavior based on double articulation structure. It has been reported that predicting driving behavior from its multivariate time series behavior data by using machine learning methods, e.g., hybrid dynamical system, hidden Markov model and Gaussian mixture model, is difficult because a drivers behavior is affected by various contextual information. To overcome this problem, we assume that contextual information has a double articulation structure and develop a novel semiotic prediction method by extending nonparametric Bayesian unsupervised morphological analyzer. Effectiveness of our prediction method was evaluated using synthetic data and real driving data. In these experiments, the proposed method achieved long-term prediction 2-6 times longer than some conventional methods.

Reinforcement learning for quasi-passive dynamic walking of an unstable biped robot

A class of biped locomotion called Passive Dynamic Walking (PDW) has been recognized to be efficient in energy consumption and a key to understand human walking. Although PDW is sensitive to the initial condition and disturbances, studies of Quasi-PDW which incorporates supplemental actuators have been reported to overcome this sensitivity. In this article, we propose a reinforcement learning method designed particularly for Quasi-PDW of a biped robot whose possession of knees makes the system unstable. Simulations show that the learning is quickly accomplished after 1000 episodes, and the obtained controller is robust against variations in the slope gradient and sudden perturbations.

Contextual scene segmentation of driving behavior based on double articulation analyzer

Various advanced driver assistance systems (ADASs) have recently been developed, such as Adaptive Cruise Control and Precrash Safety System. However, most ADASs can operate in only some driving situations because of the difficulty of recognizing contextual information. For closer cooperation between a driver and vehicle, the vehicle should recognize a wider range of situations, similar to that recognized by the driver, and assist the driver with appropriate timing. In this paper, we assumed a double articulation structure in driving behavior data and segmented driving behavior into meaningful chunks for driving scene recognition in a similar manner to natural language processing (NLP). A double articulation analyzer translated the driving behavior into meaningless manemes, which are the smallest units of the driving behavior just like phonemes in NLP, and from them it constructed navemes, which are meaningful chunks of driving behavior just like morphemes. As a result of this two-phase analysis, we found that driving chunks equivalent to language words were closer to the complicated or contextual driving scene segmentation produced by human recognition.

Development of pedestrian behavior model taking account of intention

In order for robots to safely move in human-robot coexisting environment, they must be able to predict their surrounding peoples behavior. In this study, a pedestrian behavior model that produces humanlike behavior was developed. The model takes into account the pedestrians intention. Based on the intention, the model pedestrian sets its subgoal and moves toward the subgoal according to virtual forces affected by other pedestrian and environment. The proposed model was verified through pedestrian observation experiments.

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 driving assistance systems to determine driving context and predict possible scenarios of driving behavior by segmenting and modeling incoming driving-behavior time series data. In previous studies, we applied the DAA model to driving-behavior data and argued that contextual changing points can be estimated as changing points of chunks. A sequence prediction method, which predicts the next hidden state sequence, was also proposed in a previous study. However, the original DAA model does not model the duration of chunks of driving behavior and is not able to do a temporal prediction of the scenarios. Our DAA-TP method explicitly models the duration of chunks of driving behavior on the assumption that driving-behavior data have a two-layered hierarchical structure, i.e., double articulation structure. For this purpose, the hierarchical Dirichlet process hidden semi-Markov model is used for explicitly modeling the duration of segments of driving-behavior data. A Poisson distribution is also used to model the duration distribution of driving-behavior segments. The duration distribution of chunks of driving-behavior data is also theoretically calculated using the reproductive property of the Poisson distribution. We also propose a calculation method for obtaining the probability distribution of the remaining duration of current driving words as a mixture of Poisson distribution with a theoretical approximation for unobserved driving words. This method can calculate the posterior probability distribution of the next termination time of chunks by explicitly modeling all probable chunking results for observed data. The DAA-TP was applied to a synthetic data set having a double articulation structure to evaluate its model consistency. To evaluate the effectiveness of DAA-TP, we applied it to a driving-behavior data set recorded at actual factory circuits. The DAA-TP could predict the next termination time of chunks more accurately than the compared methods. We also report the qualitative results for understanding the potential capability of DAA-TP.

Estimation of Driving Phase by Modeling Brake Pressure Signals

It is important for a driver-assist system to know the phase of the driver, that is, safety or danger. This paper proposes two methods for estimating the drivers phase by applying machine learning techniques to the sequences of brake signals. One method models the signal set with a mixture of Gaussians, where a Gaussian corresponds to a phase. The other method classifies a segment of the brake sequence to one of the hidden Markov models, each of which represents a phase. These methods are validated with experimental data, and are shown to be consistent with each other for the collected data from an unconstrained drive.

Sequence Prediction of Driving Behavior Using Double Articulation Analyzer

A sequence prediction method for driving behavior data is proposed in this paper. The proposed method can predict a longer latent state sequence of driving behavior data than conventional sequence prediction methods. The proposed method is derived by focusing on the double articulation structure latently embedded in driving behavior data. The double articulation structure is a two-layer hierarchical structure originally found in spoken language, i.e., a sentence is a sequence of words and a word is a sequence of letters. Analogously, we assume that driving behavior data comprise a sequence of driving words and a driving word is a sequence of driving letters. The sequence prediction method is obtained by extending a nonparametric Bayesian unsupervised morphological analyzer using a nested Pitman-Yor language model (NPYLM), which was originally proposed in the natural language processing field. This extension allows the proposed method to analyze incomplete sequences of latent states of driving behavior and to predict subsequent latent states on the basis of a maximum a posteriori criterion. The extension requires a marginalization technique over an infinite number of possible driving words. We derived such a technique on the basis of several characteristics of the NPYLM. We evaluated this proposed sequence prediction method using three types of data: 1) synthetic data; 2) data from test drives around a driving course at a factory; and 3) data from drives on a public thoroughfare. The results showed that the proposed method made better long-term predictions than did the previous methods.

On-line learning of a feedback controller for quasi-passive-dynamic walking by a stochastic policy gradient method

A class of biped locomotion called passive dynamic walking (PDW) has been recognized to be efficient in energy consumption and a key to understand human walking. Although PDW is sensitive to the initial condition and disturbances, some studies of quasi-PDW, which introduces supplementary actuators, are reported to overcome the sensitivity. In this article, for realization of the quasi-PDW, an on-line learning scheme of a feedback controller based on a policy gradient reinforcement learning method is proposed. Computer simulations show that the parameter in a quasi-PDW controller is automatically tuned by our method utilizing the passivity of the robot dynamics. The obtained controller is robust against variations in the slope gradient to some extent.

Prediction of Next Contextual Changing Point of Driving Behavior Using Unsupervised Bayesian Double Articulation Analyzer

Future advanced driver assistance systems (ADASs) should observe a driving behavior and detect contextual changing points of driving behaviors. In this paper, we propose a novel method for predicting the next contextual changing point of driving behavior on the basis of a Bayesian double articulation analyzer. To develop the method, we extended a previously proposed semiotic predictor using an unsupervised double articulation analyzer that can extract a two-layered hierarchical structure from driving-behavior data. We employ the hierarchical Dirichlet process hidden semi-Markov model [4] to model duration time of a segment of driving behavior explicitly instead of the sticky hierarchical Dirichlet process hidden Markov model (HDP-HMM) employed in the previous model [13]. Then, to recover the hierarchical structure of contextual driving behavior as a sequence of chunks, we use the Nested Pitman-Yor Language model [6], which can extract latent words from sequences of latent letters. On the basis of the extension, we develop a method for calculating posterior probability distribution of the next contextual changing point by marginalizing potentially possible results of the chunking method and potentially successive words theoretically. To evaluate the proposed method, we applied the method to synthetic data and driving behavior data that was recorded in a real environment. The results showed that the proposed method can predict the next contextual changing point more accurately and in a longer-term manner than the compared methods: linear regression and Recurrent Neural Networks, which were trained through a supervised learning scheme.

Finding meaningful robust chunks from driving behavior based on double articulation analyzer

The estimation of human intention is essential to realize intelligent vehicle systems which interact and assist humans to accomplish their tasks. In this paper, we propose a novel method for finding meaningful segments from driving behavior which are important for intelligent vehicle systems that act on human intentions. We assume that contextual information of driving behavior has a double articulation structure and develop a novel method to find meaningful segments. The double articulation analyzer consists of the sticky HDP-HMM which can encode multivariate time series data into sequence of labels and the nested Pitman-Yor language model which analyze sentences written in unknown language morphologically. Effectiveness of our method was evaluated based on real driving data by comparing robust chunks with outside environmental information. It was observed that the extracted robust chunks reflected outside information influential for driving intentions.