69 Hits in 9.0 sec

Anticipatory Navigation in Crowds by Probabilistic Prediction of Pedestrian Future Movements [article]

Weiming Zhi, Tin Lai, Lionel Ott, Fabio Ramos
2020 arXiv   pre-print
To this end, we learn a predictive model to predict continuous-time stochastic processes to model future movement of pedestrians.  ...  This paper presents Stochastic Process Anticipatory Navigation (SPAN), a framework that enables nonholonomic robots to navigate in environments with crowds, while anticipating and accounting for the motion  ...  SPAN leverages a probabilistic predictive model to predict movements of pedestrians.  ... 
arXiv:2011.06235v1 fatcat:qzxbfsr24nexng6b2ylps7vo2u

Core Challenges of Social Robot Navigation: A Survey [article]

Christoforos Mavrogiannis, Francesca Baldini, Allan Wang, Dapeng Zhao, Pete Trautman, Aaron Steinfeld, Jean Oh
2021 arXiv   pre-print
Robot navigation in crowded public spaces is a complex task that requires addressing a variety of engineering and human factors challenges.  ...  Despite the significant progress and the massive recent interest, we observe a number of significant remaining challenges that prohibit the seamless deployment of autonomous robots in public pedestrian  ...  Army Ground Vehicle Systems Center & Software Engineering Institute at Carnegie Mellon University (PWP 6-652A4 DDCD GVSC), and the Air Force Office of Scientific Research (AFOSR FA2386-17-1-4660).  ... 
arXiv:2103.05668v2 fatcat:qc2mr4ssxbahxj5p4xzqexnhye

Detecting Intentions of Vulnerable Road Users Based on Collective Intelligence [article]

Maarten Bieshaar, Günther Reitberger, Stefan Zernetsch, Bernhard Sick, Erich Fuchs, Konrad Doll
2018 arXiv   pre-print
Vulnerable road users (VRUs, i.e. cyclists and pedestrians) will play an important role in future traffic.  ...  The intention detection consists of basic movement primitive prediction, e.g. standing, moving, turning, and a forecast of the future trajectory.  ...  Acknowledgement This work was funded within the priority program "Cooperatively Interacting Automobiles" of the German Science Foundation DFG.  ... 
arXiv:1809.03916v1 fatcat:gtc4v42cdbgyfjc4ddwgqriiie

Pedestrian simulation as multi-objective reinforcement learning

Naresh Balaji Ravichandran, Fangkai Yang, Christopher Peters, Anders Lansner, Pawel Herman
2018 Proceedings of the 18th International Conference on Intelligent Virtual Agents - IVA '18  
In this work, we model pedestrians in a modular framework integrating navigation and collision-avoidance tasks as separate modules.  ...  Modelling and simulation of pedestrian crowds require agents to reach pre-determined goals and avoid collisions with static obstacles and dynamic pedestrians, while maintaining natural gait behaviour.  ...  [10] proposed a predictive collision avoidance model (PCM), which anticipates future collisions in order to avoid them.  ... 
doi:10.1145/3267851.3267914 dblp:conf/iva/RavichandranYPL18 fatcat:6jjztq4tabaa7dnl46ve53ptre

Crowd against the machine: A simulation-based benchmark tool to evaluate and compare robot capabilities to navigate a human crowd [article]

Fabien Grzeskowiak
2021 arXiv   pre-print
The evaluation of robot capabilities to navigate human crowds is essential to conceive new robots intended to operate in public spaces.  ...  to test robots, to establish standard scenarios and metrics to evaluate navigation techniques in terms of safety and efficiency, and thus, to install new methods to benchmarking robots' crowd navigation  ...  The reason for this choice is that the robot will respectively: i) ignore the crowd agents, ii) consider them as static obstacles, and iii) predict the short term future motion of agents.  ... 
arXiv:2104.14177v1 fatcat:mtvh6qedgbawrpfwls6c7b6duy

Human-robot co-navigation using anticipatory indicators of human walking motion

Vaibhav V. Unhelkar, Claudia Perez-D'Arpino, Leia Stirling, Julie A. Shah
2015 2015 IEEE International Conference on Robotics and Automation (ICRA)  
Human motion capture data is collected with predefined goals to train and test a prediction algorithm. Use of anticipatory features results in improved performance of the prediction algorithm.  ...  Further, we demonstrate the effectiveness of these turn indicators as features in the prediction of human motion trajectories.  ...  The social forces method [25] and its variants have been utilized for the simulation and prediction of pedestrian motion in crowds.  ... 
doi:10.1109/icra.2015.7140067 dblp:conf/icra/UnhelkarPSS15 fatcat:2mkgdgk4f5ff5np3gkrit6cvku

Prevention and Resolution of Conflicts in Social Navigation – a Survey [article]

Reuth Mirsky and Xuesu Xiao and Justin Hart and Peter Stone
2021 arXiv   pre-print
It starts by defining a conflict in social navigation, and offers a detailed taxonomy of its components.  ...  Finally, this paper propose some future directions and problems that are currently in the frontier of social navigation to help focus research efforts.  ...  Foka and Trahanias [32] model hot points of human navigation, a probabilistic prediction of the person's destination.  ... 
arXiv:2106.12113v1 fatcat:nrd4jhi3svhutple2a4uear5lu

Escaping from Children's Abuse of Social Robots

Drazen Brscić, Hiroyuki Kidokoro, Yoshitaka Suehiro, Takayuki Kanda
2015 Proceedings of the Tenth Annual ACM/IEEE International Conference on Human-Robot Interaction - HRI '15  
Using this model together with a simulator of pedestrian behavior, we enabled the robot to predict the possibility of an abuse situation and escape before it happens.  ...  Some actually abused the robot by saying bad things, and at times even kicking or punching the robot. We developed a statistical model of occurrence of children's abuse.  ...  In [21] we used a pedestrian simulator to predict the occurrence of crowding around a robot and used a planner to choose a path to minimize dissatisfaction to people passing by.  ... 
doi:10.1145/2696454.2696468 dblp:conf/hri/BrscicKSK15 fatcat:mub4l35ypvf7xixnuhhuskbleq

ALAN: Adaptive Learning for Multi-Agent Navigation [article]

Julio Godoy, Tiannan Chen, Stephen J. Guy, Ioannis Karamouzas, Maria Gini
2017 arXiv   pre-print
navigation, and a Predictive collision avoidance model.  ...  Existing methods compute motions that are optimal locally but do not account for the aggregated motions of all agents, producing inefficient global behavior especially when agents move in a crowded space  ...  a Predictive model for pedestrian navigation.  ... 
arXiv:1710.04296v1 fatcat:4xsmrhlyurc3nagmgbbe4opiym

Calibrating a Motion Model Based on Reinforcement Learning for Pedestrian Simulation [chapter]

Francisco Martinez-Gil, Miguel Lozano, Fernando Fernández
2012 Lecture Notes in Computer Science  
The results of the experiments are compared with databases of real pedestrians in similar scenarios.  ...  In this paper, the calibration of a framework based in Multiagent Reinforcement Learning (RL) for generating motion simulations of pedestrian groups is presented.  ...  Thus, the simulation of pedestrians groups is an important tool for all these areas. Several approaches exist to simulate crowds and groups of pedestrians in different problem domains.  ... 
doi:10.1007/978-3-642-34710-8_28 fatcat:mfstf3fn6venfc4cc4lwvze5fe

Computational Challenges in Cooperative Intelligent Urban Transport (Dagstuhl Seminar 16091)

Caitlin Doyle Cottrill, Jan Fabian Ehmke, Frankziska Klügl, Sabine Timpf, Marc Herbstritt
2016 Dagstuhl Reports  
This report documents the talks and group work of Dagstuhl Seminar 16091 "Computational Challenges in Cooperative Intelligent Urban Transport".  ...  Furthermore, this seminar consisted of significant amounts of group work that is also documented with short abstracts detailing group discussions and planned outcomes.  ...  Obviously not all pedestrians pose an equal hindrance for future movement.  ... 
doi:10.4230/dagrep.6.2.119 dblp:journals/dagstuhl-reports/CottrillEKT16 fatcat:lphem3bjbrdrvpiusriejjeyzq

Human-robot interface with anticipatory characteristics based on Laban Movement Analysis and Bayesian models

Jorg Rett, Jorge Dias
2007 2007 IEEE 10th International Conference on Rehabilitation Robotics  
We present results through its embodiment in the social robot 'Nicole' in the context of a person performing gestures and 'Nicole' reacting by means of audio output and robot movement.  ...  With this work we define the required qualities and characteristics of future embodied agents in terms of social interaction with humans.  ...  ACKNOWLEDGMENTS The authors would like to thank Juan-Manuel Ahuatzin from ProBayes, Grenoble for his support on the implementation using the ProBT-software, while the work was partially sponsored by by  ... 
doi:10.1109/icorr.2007.4428436 fatcat:7f6ifogckvfqbdrxfb4bx3loqi

Joint Attention in Driver-Pedestrian Interaction: from Theory to Practice [article]

Amir Rasouli, John K. Tsotsos
2018 arXiv   pre-print
In this literature review we aim to address the interaction problem between pedestrians and drivers (or vehicles) from joint attention point of view.  ...  Today, one of the major challenges that autonomous vehicles are facing is the ability to drive in urban environments.  ...  Relying on active sensors for navigation significantly constraints these vehicles, especially in crowded areas.  ... 
arXiv:1802.02522v2 fatcat:nzeq5eleajcktjl32m2kyqu7rq

Person Following by Autonomous Robots: A Categorical Overview [article]

Md Jahidul Islam, Jungseok Hong, Junaed Sattar
2019 arXiv   pre-print
This paper provides a comprehensive overview of the literature by categorizing different aspects of person-following by autonomous robots.  ...  Researchers have addressed these challenges in many ways and contributed to the development of a large body of literature.  ...  The authors are with the Interactive Robotics and Vision Laboratory (IRVLab), University of Minnesota, Twin Cities, MN, USA.  ... 
arXiv:1803.08202v4 fatcat:wrqjbueulramzknpae3kt45kte

Human Action Recognition and Prediction: A Survey [article]

Yu Kong, Yun Fu
2022 arXiv   pre-print
In this paper, we survey the complete state-of-the-art techniques in action recognition and prediction.  ...  Derived from rapid advances in computer vision and machine learning, video analysis tasks have been moving from inferring the present state to predicting the future state.  ...  Future actions are predicted in [172] by learning a distribution of future actions using Variational Auto-Encoder.  ... 
arXiv:1806.11230v3 fatcat:2a2d7fuezbdqzfgrjwkcuqvmbu
« Previous Showing results 1 — 15 out of 69 results