Social Robot Navigation Tasks: Combining Machine Learning Techniques and Social Force Model

Abstract

Social robot navigation in public spaces, buildings or private houses is a difficult problem that is not well solved due to environmental constraints (buildings, static objects etc.), pedestrians and other mobile vehicles. Moreover, robots have to move in a human-aware manner—that is, robots have to navigate in such a way that people feel safe and comfortable. In this work, we present two navigation tasks, social robot navigation and robot accompaniment, which combine machine learning techniques with the Social Force Model (SFM) allowing human-aware social navigation. The robots in both approaches use data from different sensors to capture the environment knowledge as well as information from pedestrian motion. The two navigation tasks make use of the SFM, which is a general framework in which human motion behaviors can be expressed through a set of functions depending on the pedestrians’ relative and absolute positions and velocities. Additionally, in both social navigation tasks, the robot’s motion behavior is learned using machine learning techniques: in the first case using supervised deep learning techniques and, in the second case, using Reinforcement Learning (RL). The machine learning techniques are combined with the SFM to create navigation models that behave in a social manner when the robot is navigating in an environment with pedestrians or accompanying a person. The validation of the systems was performed with a large set of simulations and real-life experiments with a new humanoid robot denominated IVO and with an aerial robot. The experiments show that the combination of SFM and machine learning can solve human-aware robot navigation in complex dynamic environments.

Robot Navigation Anticipative Strategies in Deep Reinforcement Motion Planning

“…This subsection explains the hybrid model proposed in [11] resulting from a DDPG training and the SFM with collision prediction (CP) [23].…”

“…Second, in the evaluation phase, the people velocities obtained using a tracker [22,16] are used in the SFM with CP to compute velocity changes (∆v) rep = (∆v l , ∆v φ ) as is explained in [11]. These velocity changes are added to the DDPG actions to calculate the actions provided by the hybrid model:…”

“…The training and evaluation in simulation are executed in maps (refer to Fig. 3), which are the same floor maps used in [11]. A new empty scenario has been added to evaluate the performance in presence of only moving obstacles.…”

“…These are some of the floor maps with their sizes in meters. Building 1 and Building 3 maps used for this work are the ones used in[11].…”

Review of Pedestrian Trajectory Prediction Methods: Comparing Deep Learning and Knowledge-based Approaches

“…The output of the KB models can be used to feed the DL algorithm and vice versa [259]. Gil et al [264] calculate the repulsive forces produced by the environment and the pedestrians with the social force model and after that they use them as input for a neural network.…”