On-line adaptive side-by-side human robot companion in dynamic urban environments

Abstract

This paper presents an adaptive side-by-side human-robot companion approach for navigation in urban dynamic environments, based on the anticipative kinodynamic planning. The adaptive means that the robot is capable of adjusting its motion to the behavior of the person being accompanied. Our main objective is to optimize in real time the path performed by the pair human-robot, by modifying dynamically the angle and distance between both throughout different locations of the path. We have defined a new cost function for finding the best planned path that takes into account the cost of the geometrical configuration between the human and the robot. Moreover, we have modified the Extended Social Force Model (SFM) to include the required forces to maintain the angle and distance between the robot and human while the human-robot pair is moving towards the shared goal. The method has been validated throughout a large set of simulations and real-live experiments.

People’s V-Formation and Side-by-Side Model Adapted to Accompany Groups of People by Social Robots

“…Once the final destination of the group is obtained, all possible paths are computed by the Anticipative Kinodynamic Planner (AKP) [24], and extended to accompany people [20]. This extension includes a force for the accompaniment task and a cost to evaluate the accompaniment task during each path.…”

“…Authors in [14] proposed a model of people walking sideby-side which could predict the partners future position, and subsequently generate a plan. In Repiso et al [19] the authors proposed a method for on-line adaptive side-by-side for human robot companion in dynamic urban environments and in [20] the authors extended the method to also approach a moving person to interact. In [21], researchers implemented a robot that follows people to obtain a more realistic and human-like navigation in crowded scenarios.…”

Robot Approaching and Engaging People in a Human-Robot Companion Framework

“…We assume that the person of the group knows the target person (it is the person to be approached by the group). The accompany task follows the same procedure that was explained in our previous work [14].…”

“…The attractive force to maintain the formation between the robot and the accompanied person, f goal r,p (D f n ), introduced in our previous work [14], has been split in two forces, the first one is f goal r,d (D dg n ) which manages the dynamic goal and the second one is f goal r,p (D f n ) which manages the formation of the group.…”

“…The best performance has value of 1. The graphs of the performance metrics for distance and angle are described in [14].…”