Modeling and Prediction of Pedestrian Behavior based on the Sub-goal Concept

Ikeda, Teruyuki; Chigodo, Yoshihiro; Rea, Daniel J.; Zanlungo, Francesco; Shiomi, Masahiro; Kanda, Takayuki

doi:10.15607/rss.2012.viii.018

Cited by 49 publications

(49 citation statements)

References 25 publications

(46 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In our approach, we do not require manual labels for such beliefs. Ikeda et.al [40] models paths by first determining sub-goals and then learning transitions between sub-goals. However, their model of the crowd is solely based on the social-force model, and sub-goals are defined as points towards which many velocities converge.…”

Section: Related Workmentioning

confidence: 99%

Trending Paths: A New Semantic-Level Metric for Comparing Simulated and Real Crowd Data

Wang

Ondřej

O’Sullivan

2017

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

Abstract-We propose a new semantic-level crowd evaluation metric in this paper. Crowd simulation has been an active and important area for several decades. However, only recently has there been an increased focus on evaluating the fidelity of the results with respect to real-world situations. The focus to date has been on analyzing the properties of low-level features such as pedestrian trajectories, or global features such as crowd densities. We propose the first approach based on finding semantic information represented by latent Path Patterns in both real and simulated data in order to analyze and compare them. Unsupervised clustering by non-parametric Bayesian inference is used to learn the patterns, which themselves provide a rich visualization of the crowd behavior. To this end, we present a new Stochastic Variational Dual Hierarchical Dirichlet Process (SV-DHDP) model. The fidelity of the patterns is computed with respect to a reference, thus allowing the outputs of different algorithms to be compared with each other and/or with real data accordingly. Detailed evaluations and comparisons with existing metrics show that our method is a good alternative for comparing crowd data at a different level and also works with more types of data, holds fewer assumptions and is more robust to noise.

show abstract

Section: Related Workmentioning

confidence: 99%

Trending Paths: A New Semantic-Level Metric for Comparing Simulated and Real Crowd Data

Wang

Ondřej

O’Sullivan

2017

IEEE Trans. Visual. Comput. Graphics

View full text Add to dashboard Cite

show abstract

“…The work [13] addresses the problem of vision-based future action inference by using a semantic scene understanding technique and optimal control theory. Ikeda et al [14] propose a method to predict the long-term behavior of pedestrians by estimating the final goal using the concept of sub-goal. The locations of sub-goals and the transitions among them are learned and the future positions are predicted based on initial observations.…”

Section: Related Workmentioning

confidence: 99%

Multi-scale conditional transition map: Modeling spatial-temporal dynamics of human movements with local and long-term correlations

Wang

Folkesson

2015

2015 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS)

View full text Add to dashboard Cite

Abstract-This paper presents a novel approach to modeling the dynamics of human movements with a grid-based representation. The model we propose, termed as Multi-scale Conditional Transition Map (MCTMap), is an inhomogeneous HMM process that describes transitions of human location state in spatial and temporal space. Unlike existing work, our method is able to capture both local correlations and longterm dependencies on faraway initiating events. This enables the learned model to incorporate more information and to generate an informative representation of human existence probabilities across the grid map and along the temporal axis for intelligent interaction of the robot, such as avoiding or meeting the human. Our model consists of two levels. For each grid cell, we formulate the local dynamics using a variant of the left-toright HMM, and thus explicitly model the exiting direction from the current cell. The dependency of this process on the entry direction is captured by employing the Input-Output HMM (IOHMM). On the higher level, we introduce the place where the whole trajectory originated into the IOHMM framework forming a hierarchical input structure to capture long-term dependencies. The capabilities of our method are verified by experimental results from 10 hours of data collected in an office corridor environment.

show abstract

“…None of these approaches, however, take into account the robot's influence in estimating and modifying current human trajectories. Among the solutions that have considered explicitly the effect of a robot's action on human motion behaviours, the "social force model" proposed by [6] is often used to provide a quantitative description of pedestrian behaviours [7]. This model describes human motion according to forces driven by internal objectives, such as the desire of reaching a target or avoiding an obstacle, although some recent work suggests the model is not suitable for dealing with individual pedestrians during evasive manoeuvres [8].…”

Section: Rfldo 5rerwlfv /Hfwxuh 1rwhv Lq Andrpsxwhu 6flhqfh 9roxph Ss mentioning

confidence: 99%

Qualitative Design and Implementation of Human-Robot Spatial Interactions

2013

View full text Add to dashboard Cite

Abstract. Despite the large number of navigation algorithms available for mobile robots, in many social contexts they often exhibit inopportune motion behaviours in proximity of people, often with very "unnatural" movements due to the execution of segmented trajectories or the sudden activation of safety mechanisms (e.g., for obstacle avoidance). We argue that the reason of the problem is not only the difficulty of modelling human behaviours and generating opportune robot control policies, but also the way human-robot spatial interactions are represented and implemented. In this paper we propose a new methodology based on a qualitative representation of spatial interactions, which is both flexible and compact, adopting the well-defined and coherent formalization of Qualitative Trajectory Calculus (QTC). We show the potential of a QTC-based approach to abstract and design complex robot behaviours, where the desired robot's motion is represented together with its actual performance in one coherent approach, focusing on spatial interactions rather than pure navigation problems.

show abstract

Modeling and Prediction of Pedestrian Behavior based on the Sub-goal Concept

Cited by 49 publications

References 25 publications

Trending Paths: A New Semantic-Level Metric for Comparing Simulated and Real Crowd Data

Trending Paths: A New Semantic-Level Metric for Comparing Simulated and Real Crowd Data

Multi-scale conditional transition map: Modeling spatial-temporal dynamics of human movements with local and long-term correlations

Qualitative Design and Implementation of Human-Robot Spatial Interactions

Contact Info

Product

Resources

About