Environmental Map Building to Describe Walking Dynamics for Determination of Spatial Feature of Walking Activity

Path planning in a dynamic environment is required not only efficiently but also with high safety. To achieve this, it is necessary to understand people’s walking activity in the space, and studies of planning paths focused on walking paths of pedestrian have been widely done. In these studies, information getting from walking paths does not include spatial features of people’s walking activity such as dynamics of their walking. A walking behavior is not always smooth from the viewpoints of changes of walking speed and moving directions. For example, people should accelerate or decelerate their walking speed according to environmental settings or their purposes of walking. In addition, moving directions of people’s walking also depend on the environmental structures and settings. Therefore, people’s walking activity should be understood including walking dynamics. To apply the information of the walking activity to the path planning for mobile robot navigation, there are two requirements; one is that the information should be described in form that a robot system is able to use, and another one is that it should be described without lacking spatial information. To realize these, we propose that an environmental map describing the walking activity of people including walking dynamics. More specifically, we build the environmental map as a grid map that is one of the often-used maps for a mobile robot. From the results of the experiment, it was shown that the proposed environmental map was possible to determine spatial features.

[1]  Xiaogang Wang,et al.  Understanding pedestrian behaviors from stationary crowd groups , 2015, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR).

[2]  Tomomasa Sato,et al.  Mobile robot path planning using human prediction model based on massive trajectories , 2012, 2012 Ninth International Conference on Networked Sensing (INSS).

[3]  Mihoko Niitsuma,et al.  Temporal segmentation of environmental map based on changing rate of activity areas and improvement of tracking method using LRF , 2015, 2015 IEEE/SICE International Symposium on System Integration (SII).

[4]  Hiroshi Mizoguchi,et al.  Path Planning Using Pedestrian Information Map for Mobile Robots in a Human Environment , 2015, 2015 IEEE International Conference on Systems, Man, and Cybernetics.

[5]  A. Okabe,et al.  An experimental analysis of direction judgment in a curved corridor , 2002 .

[6]  K. Watanabe,et al.  Proposal of path planning for a mobile robot to respect human movements in dynamic environments by using a Human Frequency Map , 2012, 2012 Proceedings of SICE Annual Conference (SICE).

[7]  Atsuyuki Okabe,et al.  Qualitative spatial reasoning about directions in a corridor containing a single turn , 2002 .

[8]  Takayuki Itoh,et al.  Feature Extraction and Visualization for Symbolic People Flow Data , 2016, 2016 20th International Conference Information Visualisation (IV).

[9]  Mark Reynolds,et al.  Bi-Prediction: Pedestrian Trajectory Prediction Based on Bidirectional LSTM Classification , 2017, 2017 International Conference on Digital Image Computing: Techniques and Applications (DICTA).

[10]  Mahbub Hassan,et al.  Adaptive pedestrian activity classification for indoor dead reckoning systems , 2013, International Conference on Indoor Positioning and Indoor Navigation.

[11]  Yuka Kato,et al.  Predicting a Pedestrian Trajectory Using Seq2Seq for Mobile Robot Navigation , 2018, IECON 2018 - 44th Annual Conference of the IEEE Industrial Electronics Society.

[12]  Zhi Yan,et al.  3DOF Pedestrian Trajectory Prediction Learned from Long-Term Autonomous Mobile Robot Deployment Data , 2017, 2018 IEEE International Conference on Robotics and Automation (ICRA).

[13]  Matthias Althoff,et al.  Provably safe motion of mobile robots in human environments , 2017, 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS).