sensors-logo

Journal Browser

Journal Browser

Sensing, Modelling and Using Spatial Motion Patterns for Dynamics-Aware Mobile Robots

A special issue of Sensors (ISSN 1424-8220). This special issue belongs to the section "Sensors and Robotics".

Deadline for manuscript submissions: closed (14 May 2021) | Viewed by 2306

Special Issue Editors

AASS Mobile Robotics and Olfaction Lab, Örebro University, 702 81 Örebro, Sweden
Interests: mapping and localization for mobile robots; maps of dynamics; heterogeneous map merging; perception in low visibility; robotic introspection
AASS Mobile Robotics and Olfaction Lab, Örebro University, 702 81 Örebro, Sweden
Interests: mobile robots; maps of dynamics; chronorobotics; robotic introspection; robot perception; mapping
AASS Mobile Robotics and Olfaction Lab, Örebro University, 702 81 Örebro, Sweden
Interests: robot perception; human–robot interaction; maps of dynamics; long-term human motion prediction; mobile robot olfaction
Special Issues, Collections and Topics in MDPI journals

Special Issue Information

Mobile robots are increasingly being deployed outside of labs and in real-world applications. This makes it ever more important to explicitly account for the dynamics present in real-world environments over longer timescales. The dynamic nature of the world faced by robots notably includes flows and activity patterns of people, vehicles, and other robots, as well as dynamic and semi-static objects; but also flows of air and water currents, e.g., in applications of air and surface vessels. Constructing, and making use of, representations that explicitly model dynamics can facilitate both safer and more efficient robots, and also better understanding and predictions of flows and other spatiotemporal patterns.

There are several open research questions related to dynamics awareness for mobile robots. These involve, among many other things, studying representations of dynamics in terms of efficiency, accuracy, expressiveness, and usability; exploring how these representations can be used to facilitate dynamics-aware planning and human–robot spatial interaction; active perception and other measures for improving and maintaining the learned representations during long-term operation; as well as using robots, possibly integrated into stationary sensor networks, for building models of flow for, e.g., ventilation monitoring and surveillance.

The aim of this Special Issue is to bring out and highlight contributions in modeling, exploring, and exploiting information about the spatiotemporal patterns that govern dynamics, especially with applications in mobile robotics.

Therefore, prospective authors are invited to submit original research contributions or survey articles for review and publication in the Sensors open access journal. Topics of interest include (but are not limited to) the following:

  • Maps of dynamics and flow;
  • Perception of spatial dynamics;
  • Dynamics-aware localization;
  • Dynamics-aware motion planning;
  • Dynamics-aware coordination;
  • Dynamics-aware reasoning;
  • Planning for dynamics perception;
  • Active perception and exploration for dynamics;
  • Dynamics-awareness for human–robot spatial interaction;
  • Dynamics-awareness for motion prediction;
  • Surveillance and crowd analysis.
Dr. Martin Magnusson
Dr. Tomasz Piotr Kucner
Prof. Dr. Achim J. Lilienthal
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the special issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 100 words) can be sent to the Editorial Office for announcement on this website.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-blind peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Sensors is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.

Keywords

  • Maps of dynamics and flow
  • Perception of spatial dynamics
  • Dynamics-aware localization
  • Dynamics-aware motion planning
  • Dynamics-aware coordination
  • Dynamics-aware reasoning
  • Planning for dynamics perception
  • Active perception and exploration for dynamics
  • Dynamics-awareness for human–robot spatial interaction
  • Dynamics-awareness for motion prediction
  • Surveillance and crowd analysis

Published Papers (1 paper)

Order results
Result details
Select all
Export citation of selected articles as:

Research

17 pages, 5902 KiB  
Article
A Probabilistic Model for Real-Time Semantic Prediction of Human Motion Intentions from RGBD-Data
by Wouter Houtman, Gosse Bijlenga, Elena Torta and René van de Molengraft
Sensors 2021, 21(12), 4141; https://doi.org/10.3390/s21124141 - 16 Jun 2021
Cited by 1 | Viewed by 1586
Abstract
For robots to execute their navigation tasks both fast and safely in the presence of humans, it is necessary to make predictions about the route those humans intend to follow. Within this work, a model-based method is proposed that relates human motion behavior [...] Read more.
For robots to execute their navigation tasks both fast and safely in the presence of humans, it is necessary to make predictions about the route those humans intend to follow. Within this work, a model-based method is proposed that relates human motion behavior perceived from RGBD input to the constraints imposed by the environment by considering typical human routing alternatives. Multiple hypotheses about routing options of a human towards local semantic goal locations are created and validated, including explicit collision avoidance routes. It is demonstrated, with real-time, real-life experiments, that a coarse discretization based on the semantics of the environment suffices to make a proper distinction between a person going, for example, to the left or the right on an intersection. As such, a scalable and explainable solution is presented, which is suitable for incorporation within navigation algorithms. Full article
Show Figures

Figure 1

Back to TopTop