Incremental Human Motion Map system and human walking behavior representation in indoor environment

Wada, Tetsuya; Wang, Zhidong; Ogawa, Yuji; Hirata, Yasuhisa; Kosuge, Kazuhiro

doi:10.1109/robio.2012.6491057

Cited by 7 publications

(3 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…However, most of the existing models are built offline, as model creation and updating can be computationally expensive and tedious. Wada et al [31] and Kucner et al [25] aim to solve this issue in the spatial domain, while Chenellato et al [32] address the incremental building of a von Mises Mixture model from streaming data to represent multi-modal distributions of human activity.…”

Section: B Human Motion Modellingmentioning

confidence: 99%

Robotic Exploration for Learning Human Motion Patterns

2022

View full text Add to dashboard Cite

Understanding how people are likely to move is key to efficient and safe robot navigation in human environments. However, mobile robots can only observe a fraction of the environment at a time, while the activity patterns of people may also change at different times. This paper introduces a new methodology for mobile robot exploration to maximise the knowledge of human activity patterns by deciding where and when to collect observations. We introduce an exploration policy driven by the entropy levels in a spatio-temporal map of pedestrian flows, and compare multiple spatio-temporal exploration strategies including both informed and uninformed approaches. The evaluation is performed by simulating mobile robot exploration using real sensory data from three long-term pedestrian datasets. The results show that for certain scenarios the models built with proposed exploration system can better predict the flow patterns than uninformed strategies, allowing the robot to move in a more socially compliant way, and that the exploration ratio is a key factor when it comes to the model prediction accuracy.

show abstract

Section: B Human Motion Modellingmentioning

confidence: 99%

Robotic Exploration for Learning Human Motion Patterns

2022

View full text Add to dashboard Cite

show abstract

“…Using Gaussian process-based regression, [21] proposed the use of navigational maps to encode human tendencies when navigating towards a goal, while [2] refined the probability of space occupancy using the human pose traces as training points for fitting the likelihood function. On the same track, the work of Wada et al [31] extracted distinctive walking patterns across different areas by aggregating leg traces while they recently integrated human articulation cues [22] as a means to map the dependence of human motion classes in specific areas. All those works rely on off-line data collection through human observations to build constant map representations, while our higher objective is to develop human interaction-based mapping schemes that improve the local spatio-temporal consistency.…”

Section: Introductionmentioning

confidence: 99%

Binding human spatial interactions with mapping for enhanced mobility in dynamic environments

Papadakis

Rives

2016

Auton Robot

View full text Add to dashboard Cite

To cite this version:Panagiotis Papadakis, Patrick Rives. Binding human spatial interactions with mapping for enhanced mobility in dynamic environments. Autonomous Robots, Springer Verlag, 2017, 41 (5) Abstract For mobile robots to operate in compliance with human presence, interpreting the impact of human activities and responding constructively is a challenging goal. In this paper, we propose a generative approach for enhancing robot mapping and mobility in the presence of humans through a joint, probabilistic treatment of static and dynamic characteristics of indoor environments. Human spatial activity is explicitly exploited for the purpose of passage detection and space occupancy prediction while effectively discarding false positive human detections using prior map information. In turn, this allows the execution of plan trajectories within unexplored areas by using human presence for resolving the uncertainty or ambiguity that is due to dynamic events. A series of experiments with an indoor robot navigating in close human proximity within a multifloor building demonstrate the effectiveness of our approach in realistic conditions.

show abstract

“…Wada et al [5] proposed a concept and an architecture of Human Motion Map by representing extracted human behaviors in the human living space as a map. On building Human Motion Map incrementally, human walking area interpolating algorithm and map update algorithm are developed.…”

Section: Introductionmentioning

confidence: 99%

A method of map updating for global path planning of a robot

Park

Cho

2015

2015 12th International Conference on Ubiquitous Robots and Ambient Intelligence (URAI)

View full text Add to dashboard Cite

A robot should make an adequate global path to offer smooth services to users. For this purpose, accurate environmental information, i.e. map, and continual map updating is needed. In this paper, we suggest a method of map updating for a global path planning of a robot. In this method, we first define the process of creating of map update factors. And then, a step for usage of map update factors is shown. Using this method, a robot can perform its mission with reduction of task load which is needed for collision avoidance in complex environment.

show abstract

Incremental Human Motion Map system and human walking behavior representation in indoor environment

Cited by 7 publications

References 9 publications

Robotic Exploration for Learning Human Motion Patterns

Robotic Exploration for Learning Human Motion Patterns

Binding human spatial interactions with mapping for enhanced mobility in dynamic environments

A method of map updating for global path planning of a robot

Contact Info

Product

Resources

About