Game-theoretical trajectory planning enhances social acceptability for humans

TL;DR

This paper introduces a game-theoretical navigation system for robots that improves social acceptability in human environments, validated through a large-scale survey comparing robot and human trajectories.

Contribution

It presents a novel game-theoretic trajectory planner that enhances social acceptance of robots, bridging the gap between safety and human-like social behavior.

Findings

Participants distinguished VFH trajectories from humans

Game-theoretic trajectories were often perceived as human-like

The approach marks progress toward socially integrated robots

Abstract

Since humans and robots are increasingly sharing portions of their operational spaces, experimental evidence is needed to ascertain the safety and social acceptability of robots in human-populated environments. Although several studies have aimed at devising strategies for robot trajectory planning to perform \emph{safe} motion in populated environments, a few efforts have \emph{measured} to what extent a robot trajectory is \emph{accepted} by humans. Here, we present a navigation system for autonomous robotics that ensures safety and social acceptability of robotic trajectories. We overcome the typical reactive nature of state-of-the-art trajectory planners by leveraging non-cooperative game theory to design a planner that encapsulates human-like features of preservation of a vital space, recognition of groups, sequential and strategized decision making, and smooth obstacle avoidance. Social acceptability is measured through a variation of the Turing test administered in the form of a survey questionnaire to a pool of 691 participants. Comparison terms for our tests are a state-of-the-art navigation algorithm (Enhanced Vector Field Histogram, VFH) and purely human trajectories. While all participants easily recognized the non-human nature of VFH-generated trajectories, the distinction between game-theoretical trajectories and human ones were hardly revealed. These results mark a strong milestone toward the full integration of robots in social environments.