As social and service robots increasingly share interaction spaces in public, they may form groups while coordinating tasks or interacting with humans. Initial group formation alone is insufficient in dynamic settings, because it can be disrupted when a person or another agent joins, leaves, or passes through the group. Although group dynamics and repositioning have been widely studied in swarm robotics and virtual-agent settings, little attention has been given to socially appropriate repositioning behaviors in groups of humanoid robots. Existing social-force-based approaches provide a useful foundation for group behavior, but they have limited obstacle handling, and can produce unsafe behavior as environmental complexity increases. We propose a novel framework that modulates traditional Social Force, guided by Model Predictive Control (MPC) to plan ahead, bounded by Control Barrier Functions (CBF) to increase safety for robot groups repositioning behaviors. This approach aims to produce safer and socially aware group repositioning behaviors under various group formation disturbance. We evaluate the method in simulation through an ablation study and an online user study. The results show that our proposed method can produce smoother and safer repositioning behaviors in complex environments while preserving social appropriateness.
Figures & tables
Fig. 1: Snapshots of four Gazebo Fortress layouts: empty space, crowded room, elevator, and hallway. The white robot groups reposition themselves as the yellow robot approaches along the dashed trajectory.
Fig. 2: Overview of our proposed robot-group repositioning framework. ESFFM generates nominal accelerations from observed robot and environment states, which are refined by MPC and filtered by CBF. Safe accelerations are applied only to autonomous robots, and the teleoperated robot acts as an external disturbance.
Controller
Mean collision rate (%) ↓
Mean jerk (m/s 3 ) ↓
Mean personal- space violation (%) ↓
Mean O- space violation (%) ↓
SFFM
57.23
18.46
21.64
1.53
E
1.99
21.34
33.72
1.33
E+C
0.23
16.27
33.53
1.61
E+M
1.15
18.65
33.33
0.74
E+M+C
0.18
14.63
32.83
1.76
TABLE I: Quantitative analysis on ablation study. Collision, jerk, and personal-space means cover eight setups; O-space covers seven eligible setups, excluding the two-agent elevator. E: ESFFM; M: MPC; C: CBF.
Condition
SFFM
E
E+M
E+C
E+M+C
Robot-Obstacle Collision
2 robots, elevator
31.98
–
–
–
–
3 robots, elevator
100.00
8.03
5.20
–
–
5 robots, hallway
59.74
–
2.30
–
–
5 robots, crowded
83.20
–
–
–
–
7 robots, crowded
100.00
3.44
–
–
–
TABLE II: Non-zero collision rates (%) by condition and collision type. “–” indicates no detected collision. E: ESFFM; M: MPC; C: CBF.
Fig. 3: Robot trajectories in the 7-robot crowded room layout. The orange trajectory corresponds to the teleoperated robot, while the teal trajectories correspond to the 6 autonomous robots controlled by the respective controller. Circles (•) mark each robot’s initial position and crosses ( x ) mark its final position.
Fig. 4: Model preference by condition. Ratings were made on a 7-point comparative scale with 4 indicating no preference. For negatively framed questions (orange), ratings below 4 favor our framework, whereas positively framed questions (teal), ratings above 4 favor our proposed framework (ESFFM+MPC+CBF). Within each condition, statistically significant deviations from the neutral midpoint after corrected one-sample t -tests are marked with “*” ( p<0.05 ).
Social robotics studies robots that interact with people through social communication, assistance, collaboration, and behavior adapted to human contexts.
Safe and socially compliant navigation remains a fundamental challenge for autonomous robots operating in human-populated environments. Beyond collision avoidance, robots must anticipate human motion and respect personal space to ensure human comfort. Model Predictive Control (MPC) offers a robust alternative to classical and data-driven methods, although its effectiveness strongly depends on accurate human motion prediction and efficient computation. This paper introduces SFM-NMPC, a Social Force Model-based Non-linear Model Predictive Control framework that embeds human motion prediction directly within the optimization loop. By incorporating the Social Force Model into the dynamic model of surrounding agents, the controller jointly predicts the trajectories of humans and robots over the prediction horizon, thereby enabling socially-aware planning. A tailored set of social cost functions guides the optimization toward human-compliant behaviors. Despite the increased model complexity, the proposed formulation runs in real time at 20 Hz. Extensive simulated testing in crowded environments demonstrates that SFM-NMPC outperforms state-of-the-art baselines in social compliance metrics while maintaining efficient and smooth navigation. Visual trajectory analysis and an ablation study further highlight the contribution of the embedded SFM dynamics and social cost terms, confirming the effectiveness of the proposed approach for real-world social navigation.
Stefano Trepella, Andrea Ostuni, Mauro Martini +5
Department of Electronics and Telecommunications, Politecnico di Torino, 10129, Torino, Italy. · School of Engineering, Pablo de Olavide University, Crta. Utr-era km 1, Seville, Spain
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.
Cong-Thanh Vu, Yen-Chen Liu
Department of Mechanical Engineering, National Cheng Kung University, Tainan 70101, Taiwan.
Social navigation typically assumes a specified goal and focuses on reaching it while respecting social conventions, whereas robot group joining requires predicting where to join based on the group's real-time activity and formation. This is a highly semantic task, yet an important capability for applications such as robotic guide dogs and autonomous mobility scooters. We formulate language-grounded robot group joining: given an observation and a natural-language description of a target group, the robot identifies the relevant group members and predicts socially compliant joining poses. For grounding, we generate structured candidate subsets through recursive spectral partitioning and rank them with a language-conditioned image--geometry model. Given the grounded group, a goal predictor leverages human-formation priors to produce a multimodal energy--orientation map over feasible robot poses. Experiments on conversations, queues, and audiences across varying group sizes, crowd densities, and visual ambiguities show that our method achieves competitive grounding accuracy with sub-second inference and outperforms all baselines in joining-pose prediction. Real-robot experiments further demonstrate group joining in both static and dynamically changing interactions.
Zilin Fang, Zishuo Wang, Gim Hee Lee +1
School of Computing, Smart Systems Institute, National University of Singapore, Singapore. · Smart Systems Institute, National University of Singapore, Singapore.