Francesco Zanlungo

Social force model with explicit collision prediction

We introduce a new specification of the social force model in which pedestrians explicitly predict the place and time of the next collision in order to avoid it. This and other specifications of the social force model are calibrated, using genetic algorithms, on a set of pedestrian trajectories, obtained tracking with laser range finders the movement of pedestrians in controlled experiments, and their performance is compared. The results show that the proposed method has a better performance in describing the trajectory set.

Towards a Socially Acceptable Collision Avoidance for a Mobile Robot Navigating Among Pedestrians Using a Pedestrian Model

Safe navigation is a fundamental capability for robots that move among pedestrians. The traditional approach in robotics to attain such a capability has treated pedestrians as moving obstacles and provides algorithms that assure collision-free motion in the presence of such moving obstacles. In contrast, recent studies have focused on providing the robot not only collision-free motion but also a socially acceptable behavior by planning the robot’s path to maintain a “social distance” from pedestrians and respect their personal space. Such a social behavior is perceived as natural by the pedestrians and thus provides them a comfortable feeling, even if it may be considered a decorative element from a strictly safety oriented perspective. In this work we develop a system that realizes human-like collision avoidance in a mobile robot. In order to achieve this goal, we use a pedestrian model from human science literature, a version of the popular Social Force Model that was specifically designed to reproduce conditions similar to those found in shopping malls and other pedestrians facilities. Our findings show that the proposed system, which we tested in 2-h field trials in a real world environment, not only is perceived as comfortable by pedestrians but also yields safer navigation than traditional collision-free methods, since it better fits the behavior of the other pedestrians in the crowd.

A Microscopic “Social Norm” Model to Obtain Realistic Macroscopic Velocity and Density Pedestrian Distributions

We propose a way to introduce in microscopic pedestrian models a “social norm” in collision avoiding and overtaking, i.e. the tendency, shared by pedestrians belonging to the same culture, to avoid collisions and perform overtaking in a preferred direction. The “social norm” is implemented, regardless of the specific collision avoiding model, as a rotation in the perceived velocity vector of the opponent at the moment of computation of the collision avoiding strategy, and justified as an expectation that the opponent will follow the same “social norm” (for example a tendency to avoid on the left and overtake on the right, as proposed in this work for Japanese pedestrians). By comparing with real world data, we show that the introduction of this norm allows for a better reproduction of macroscopic pedestrian density and velocity patterns.

Deciphering the crowd: modeling and identification of pedestrian group motion.

Associating attributes to pedestrians in a crowd is relevant for various areas like surveillance, customer profiling and service providing. The attributes of interest greatly depend on the application domain and might involve such social relations as friends or family as well as the hierarchy of the group including the leader or subordinates. Nevertheless, the complex social setting inherently complicates this task. We attack this problem by exploiting the small group structures in the crowd. The relations among individuals and their peers within a social group are reliable indicators of social attributes. To that end, this paper identifies social groups based on explicit motion models integrated through a hypothesis testing scheme. We develop two models relating positional and directional relations. A pair of pedestrians is identified as belonging to the same group or not by utilizing the two models in parallel, which defines a compound hypothesis testing scheme. By testing the proposed approach on three datasets with different environmental properties and group characteristics, it is demonstrated that we achieve an identification accuracy of 87% to 99%. The contribution of this study lies in its definition of positional and directional relation models, its description of compound evaluations, and the resolution of ambiguities with our proposed uncertainty measure based on the local and global indicators of group relation.

A framework with a pedestrian simulator for deploying robots into a real environment

We describe a simulation framework aimed to develop and test robots before deploying them in a real environment crowded with pedestrians. In order to use mobile robots in the real world, it is necessary to test whether they are able to navigate well, i.e. without causing safety risks to humans. This task is particular difficult due to the complex behavior pedestrians have towards each other and also towards the robot, that can be perceived either as an obstacle to avoid or as an object of interest to approach for curiosity. To overcome this difficulty, our framework involves a pedestrian simulator, based on a collision avoidance model developed to describe low density conditions as those occurring in shopping malls, to test the robots navigation capability among pedestrians. Furthermore, we analyzed the behavior of pedestrians towards a robot in a shopping mall to build a human-to-robot interaction model that was introduced in the simulator. Our simulator works as a tool to test the level of safety of robot navigation before deploying it in a real environment. We demonstrate our approach showing how we used the simulator, and how the robot finally navigated in a real environment.

A mesoscopic model for the effect of density on pedestrian group dynamics

We introduce a mesoscopic model of pedestrian group behaviour, in which the internal group dynamics is modelled using a microscopic potential, while the effect of the environment is modelled using a harmonic term whose intensity depends on a macroscopic quantity, crowd density. We show that, in order to properly describe the behaviour of 2-person groups, the harmonic term is directed orthogonally to the walking direction, and its intensity grows linearly with density. We also show that, once calibrated on 2-person groups, the model correctly predicts the velocity and spatial extension of 3-person groups in the walking direction, while in order to describe properly also the abreast extension of 3-person groups a modification in the microscopic group dynamics has to be introduced. The model also correctly predicts the presence of a bifurcation phenomenon, namely the emergence of a stable 3-person Λ configuration at high densities, while only the V formation is stable at low densities.

Experimental Study and Modelling of Pedestrian Space Occupation and Motion Pattern in a Real World Environment

In this work we tackle the statistical study and modelling of the usage of space by pedestrians in a real world environment. A large amount of pedestrian trajectories is collected in a corridor used just as a transition place, and the density and velocity distributions are analysed as functions of the distance from the walls. The empirical data are fitted to a model assuming the density and velocity to be determined through a Boltzmann factor by a comfort function depending on the distance from the walls and assuming a maximum on the left side of the corridor (Japanese traffic convention). The empirical data are then compared to numerical simulations using pure collision avoidance models, to better analyse the influence of the environment on the pedestrian distribution and to investigate how to introduce in collision avoiding the bias that makes people walk preferentially on a given side of a corridor.

Intrinsic group behaviour: Dependence of pedestrian dyad dynamics on principal social and personal features

Being determined by human social behaviour, pedestrian group dynamics may depend on “intrinsic properties” such as the purpose of the pedestrians, their personal relation, gender, age, and body size. In this work we investigate the dynamical properties of pedestrian dyads (distance, spatial formation and velocity) by analysing a large data set of automatically tracked pedestrian trajectories in an unconstrained “ecological” setting (a shopping mall), whose apparent physical and social group properties have been analysed by three different human coders. We observed that females walk slower and closer than males, that workers walk faster, at a larger distance and more abreast than leisure oriented people, and that inter-group relation has a strong effect on group structure, with couples walking very close and abreast, colleagues walking at a larger distance, and friends walking more abreast than family members. Pedestrian height (obtained automatically through our tracking system) influences velocity and abreast distance, both growing functions of the average group height. Results regarding pedestrian age show that elderly people walk slowly, while active age adults walk at the maximum velocity. Groups with children have a strong tendency to walk in a non-abreast formation, with a large distance (despite a low abreast distance). A cross-analysis of the interplay between these intrinsic features, taking in account also the effect of an “extrinsic property” such as crowd density, confirms these major results but reveals also a richer structure. An interesting and unexpected result, for example, is that the velocity of groups with children increases with density, at least in the low-medium density range found under normal conditions in shopping malls. Children also appear to behave differently according to the gender of the parent.

Modelling of pedestrian groups and application to group recognition

In analysing the movement and interaction of pedestrians it is very important to take into account the social groups they form. In this paper we describe the work we have done on the modelling of the spatial formations of socially interacting groups of pedestrians. We than explain the application of the obtained statistical models to the automatic detection of pedestrians who are in a group. The results show that a high detection accuracy can be achieved.

Walk the talk: Gestures in mobile interaction

This study aims at describing navigation guidelines and concerning analytic motion models for a mobile interaction robot, which moves together with a human partner. We address particularly the impact of gestures on the coupled motion of this human-robot pair.