Adaptive Companionship for Group-Following Robots: Handling Dynamically Changing Group Formations

2026-07-01

AI Summary

Existing robotic systems struggle to adapt to dynamic group formations during social accompaniment, often resulting in unnatural or unsafe behaviors. This work proposes a vision-language model (VLM)-based adaptive group accompaniment approach, introducing VLMs to this task for the first time. By leveraging semantic reasoning, the method identifies companion identities, interprets group structure, and maintains appropriate social distances, while an MPPI controller generates stable and safe following trajectories. The system integrates modules for group member detection and interaction space awareness. Evaluated across five diverse scenarios, it achieves a 15% increase in success rate and a 25% reduction in collision rate compared to prior methods. User studies further demonstrate that the robot’s behavior is perceived as more natural and socially compliant.

Abstract

Accompanying a group of humans is an essential aspect of developing human-like social cognition in robots. However, human groups typically do not follow fixed formations, which poses significant challenges for robots in maintaining natural companionship behaviors. In this paper, we propose an adaptive group-accompaniment method for social robots based on Vision-Language Models (VLMs), leveraging their semantic reasoning capabilities to infer companion positions, maintain social distances, and understand group dynamics. The members of the group are first detected, and a perceptual module generates visual representations of the interaction group space as input to the VLM, which is then combined with a Model Predictive Path Integral (MPPI) controller to ensure stability and safety. Experimental evaluations across five scenarios show that the proposed method enables robots to accompany the group effectively, demonstrating a 15\% improvement in success rate and a 25\% reduction in collision rate compared to baseline approaches. Additionally, a user study indicates that the generated companionship behaviors are perceived as natural and socially appropriate.

Problem

• group-following
• dynamic formations
• social robots
• companionship
• human-robot interaction

Innovation

• Vision-Language Models
• adaptive group accompaniment
• social robotics
• group dynamics
• Model Predictive Path Integral