Towards a Predictive Behavioural Model for Service Robots in Shared Environments

Service robots are increasingly applied in real life environments populated with human beings. In such a challenging scenario, the autonomous robots have to avoid collision in a “natural” way, that is to execute trajectories that a human would follow. This challenging goal can be efficiently tackled if a sufficiently descriptive human motion model is available, in order to predict future pedestrian behaviour and hence safely planning the correct route. In this paper, we move a first step towards a motion model that is able to describe to a certain extent the nonverbal negotiation of spaces in shared environments, still preserving its simplicity for ease of computation. The avoidance task is shared among the robot and the pedestrians and thus human-like trajectories can be generated. Simulations and application to actual pedestrian data are presented to validate the model.

[1]  Xiaoping Chen,et al.  Real-time navigation in dynamic human environments using optimal reciprocal collision avoidance , 2015, 2015 IEEE International Conference on Mechatronics and Automation (ICMA).

[2]  Dinesh Manocha,et al.  Reciprocal collision avoidance with acceleration-velocity obstacles , 2011, 2011 IEEE International Conference on Robotics and Automation.

[3]  Thierry Fraichard,et al.  Human robot motion: A shared effort approach , 2017, 2017 European Conference on Mobile Robots (ECMR).

[4]  Luigi Palopoli,et al.  Path planning maximising human comfort for assistive robots , 2016, 2016 IEEE Conference on Control Applications (CCA).

[5]  Stefan Glasauer,et al.  Adjustments of Speed and Path when Avoiding Collisions with Another Pedestrian , 2014, PloS one.

[6]  Helbing,et al.  Social force model for pedestrian dynamics. , 1995, Physical review. E, Statistical physics, plasmas, fluids, and related interdisciplinary topics.

[7]  Luigi Palopoli,et al.  Simulating Passivity for Robotic Walkers via Authority-Sharing , 2018, IEEE Robotics and Automation Letters.

[8]  Axel Legay,et al.  Efficient customisable dynamic motion planning for assistive robots in complex human environments , 2015, J. Ambient Intell. Smart Environ..

[9]  Christian Laugier,et al.  From Proxemics Theory to Socially-Aware Navigation: A Survey , 2014, International Journal of Social Robotics.

[10]  Antonis A. Argyros,et al.  Navigation assistance and guidance of older adults across complex public spaces: the DALi approach , 2015, Intell. Serv. Robotics.

[11]  Dirk Helbing,et al.  How simple rules determine pedestrian behavior and crowd disasters , 2011, Proceedings of the National Academy of Sciences.

[12]  Ning Bin,et al.  A new collision avoidance model for pedestrian dynamics , 2015 .

[13]  P. Molnár.  Social Force Model for Pedestrian Dynamics Typeset Using Revt E X 1 , 1995 .

[14]  E. Hall.  The hidden dimension: an anthropologist examines man's use of space in public and private , 1969 .

[15]  Luigi Palopoli,et al.  Indoor Positioning of a Robotic Walking Assistant for Large Public Environments , 2015, IEEE Transactions on Instrumentation and Measurement.

[16]  Ioannis Karamouzas,et al.  Universal power law governing pedestrian interactions. , 2014, Physical review letters.

[17]  Luigi Palopoli,et al.  Harnessing steering singularities in passive path following for robotic walkers , 2017, 2017 IEEE International Conference on Robotics and Automation (ICRA).

[18]  Luigi Palopoli,et al.  Path Following With Authority Sharing Between Humans and Passive Robotic Walkers Equipped With Low-Cost Actuators , 2017, IEEE Robotics and Automation Letters.

[19]  Valerio Magnago,et al.  A nearly optimal landmark deployment for indoor localisation with limited sensing , 2017, 2017 International Conference on Indoor Positioning and Indoor Navigation (IPIN).

[20]  Daniele Fontanelli,et al.  Walking Ahead: The Headed Social Force Model , 2017, PloS one.

[21]  Andrey V. Savkin,et al.  Seeking a path through the crowd: Robot navigation in unknown dynamic environments with moving obstacles based on an integrated environment representation , 2014, Robotics Auton. Syst..

[22]  Joaquim B. Cavalcante Neto,et al.  Gradient‐based steering for vision‐based crowd simulation algorithms , 2017, Comput. Graph. Forum.

[23]  Luigi Palopoli,et al.  Indoor Localization of Mobile Robots Through QR Code Detection and Dead Reckoning Data Fusion , 2017, IEEE/ASME Transactions on Mechatronics.

[24]  Kai Oliver Arras,et al.  People tracking with human motion predictions from social forces , 2010, 2010 IEEE International Conference on Robotics and Automation.

[25]  Antonios Gasteratos,et al.  Recent trends in social aware robot navigation: A survey , 2017, Robotics Auton. Syst..

[26]  Takayuki Kanda,et al.  Potential for the dynamics of pedestrians in a socially interacting group. , 2014, Physical review. E, Statistical, nonlinear, and soft matter physics.

[27]  Martin Buss,et al.  Safety assessment of trajectories for navigation in uncertain and dynamic environments , 2011, 2011 IEEE International Conference on Robotics and Automation.

[28]  Silvio Savarese,et al.  Learning Social Etiquette: Human Trajectory Understanding In Crowded Scenes , 2016, ECCV.

[29]  Luigi Palopoli,et al.  Reactive Planning for Assistive Robots , 2018, IEEE Robotics and Automation Letters.

[30]  Rachid Alami,et al.  Human-aware robot navigation: A survey , 2013, Robotics Auton. Syst..

[31]  Daniel R Parisi,et al.  Experimental characterization of collision avoidance in pedestrian dynamics. , 2016, Physical review. E.

[32]  Julien Pettré,et al.  Collision avoidance between two walkers: role-dependent strategies. , 2013, Gait & posture.