HumanHalo: Safe and Efficient 3D Navigation Among Humans via Minimally Conservative MPC

Simon Schaefer; Helen Oleynikova; Sandra Hirche; Stefan Leutenegger

cs.ROOct 20, 2025

HumanHalo: Safe and Efficient 3D Navigation Among Humans via Minimally Conservative MPC

Authors: Simon Schaefer, Helen Oleynikova, Sandra Hirche, Stefan Leutenegger

Organizations: Technical University of Munich · ETH Zurich

Abstract

Safe and efficient robotic navigation among humans is essential for integrating robots into everyday environments. Most existing approaches focus on simplified 2D crowd navigation and fail to account for the full complexity of human body dynamics beyond root motion. We present HumanHalo, an MPC framework for 3D MAV navigation among humans that combines theoretical safety guarantees with data-driven models for realistic human motion forecasting. Our approach introduces a novel reachability-based safety formulation that constrains only the initial control input for safety while modeling its effects over the entire planning horizon, enabling safe yet efficient navigation. We validate HumanHalo in both simulated experiments using real human trajectories and in the real world, demonstrating its effectiveness across tasks ranging from goal-directed navigation to visual servoing for human tracking. While we apply our method to MAV in this work, it is generic and can be adapted to other platforms. Our results show that the method preserves safety without excessive conservatism, even under imperfect human prediction and in constrained workspaces, while remaining efficient enough for real-time onboard execution.

Figures & tables

Fig. 1 : HumanHalo: A control framework for safe and efficient MAV navigation among humans. Our method combines reachability-based safety constraints with state-of-the-art data-driven human motion forecasting, ensuring recursive safety guarantees without overly conservative behavior.

Fig. 2 : Based on the current MAV state $\mathbf{x}_{0}$ and the tracked 3D positions of human body joints, we first compute both the MAV ’s and the human’s reachable sets over the entire horizon. We then optimize the control inputs $\mathbf{u}_{k}$ with the requirement that the initial control input $\mathbf{u}_{0}$ must not lead to a situation where the MAV ’s reachable set becomes a subset of the human’s reachable set at any time. While partial overlap between the two sets is safe, as it can be resolved by future control actions, full containment of the MAV ’s set within the human’s would imply inevitable collision regardless of future control inputs. To run on an MAV , our method is augmented with a real-time perception and forecasting stack (dashed boxes) that provides the current human and MAV state and informs the objective about future human motion.

Fig. 3 : Example evaluation of our safety constraint for three different initial control input choices. While the left choice leads to unsafe behavior, both the middle and the right choices for the initial control input are regarded safe as they leave options to avoid collision later on.

Panel of Figure 4 — Fig. 4 : Example constructions of the human reachable set for discretization steps $\Delta t=0.025s$ and $\Delta t=0.500s$ . The black dots represent the 3D body joints at $t=0s$ .

Parameter	Value	Parameter	Value	Parameter	Value
$\rho_{Head}$	0.2	$\rho_{Torso}$	0.3	$\rho_{Arm}$	0.205
$\rho_{Hand}$	0.1	$v_{i,\max}$	1.0	$a_{i,\max}$	1.0
$\lambda$	1000	$R_{\text{MAV}}$	0.5	$\tau_{\min}$	-0.5
$\tau_{\max}$	0.25	$\theta_{\min}$	$-$$$	$\theta_{\max}$	15 °
$\phi_{\min}$	$-$$$	$\phi_{\max}$	15 °	$b_{1}$	1.0
$b_{2}$	0.1	$b_{3}$	1.0	$b_{4}$	0.1

TABLE I : Parameters for reachable sets, box constraints, and MAV model in simulation.

Method	1 Human				2 Humans
	Coll. Avoid. $\uparrow$ [%]	SR $\uparrow$ [%]	TTG $\downarrow$ [s]	Solver $\downarrow$ [ms]	Coll. Avoid. $\uparrow$ [%]	SR $\uparrow$ [%]	TTG $\downarrow$ [s]	Solver $\downarrow$ [ms]
No Constraint	94/92	94/92	3.96/3.96	0.05	89/91	89/91	3.56/3.56	0.07
3D-ORCA [ 18 ]	98/96	84/80	4.98/4.87	0.05	100/93	91/87	4.74/4.74	0.07
CBF-QP [ 15 ]	100/100	100/98	4.43/4.51	0.06	100/98	98/91	4.11/3.99	0.11
MPC-CBF [ 16 ]	100/96	100/96	4.17/4.14	0.57	100/91	100/91	3.94/3.82	1.39
Salazar et al. [ 9 ]	96/90	82/78	4.91/5.03	0.06	98/98	91/89	4.72/4.61	0.08

TABLE II : Simulation evaluation. Each cell reports det/noisy , i.e. under a perfect forecast and under an imperfect one where the executed human motion deviates from the prediction by a seeded per-sequence velocity drift (std

0.6\text{\,}\mathrm{m}\text{\,}{\mathrm{s}}^{-1}

). SR is success rate and TTG time-to-goal. With a perfect forecast all safety-aware methods are comparable, but under prediction error only the reachability variants stay fully collision-free while also reaching the goal faster than the external safe baselines, carrying a formal guarantee (Proposition 1) and, unlike prior baselines, extending to static obstacles ( Table III ).

Method	Human Avoid. $\uparrow$	Obstacle Avoid. $\uparrow$	Success Rate $\uparrow$	Min. Dist. $\uparrow$	Solver Time $\downarrow$
	[%]	[%]	[%]	[m]	[ms]
No Constraint	14	100	14	0.21	0.18
3D-ORCA [ 18 ]	72	100	26	0.75	0.06
CBF-QP [ 15 ]	94	94	50	1.09	0.08
MPC-CBF [ 16 ]	62	96	56	0.77	0.76
Complex HRS	84	100	64	0.97	3.40

TABLE III : Constrained-workspace evaluation: a

2\text{\,}\mathrm{m}

-wide corridor with a low ceiling below the human’s vertical reach, so a flyover is impossible. Only our method stays simultaneously safe w.r.t. humans and obstacles (both

100\text{\,}\mathrm{\%}

) while completing the task most often.

Horizon	Coll. Avoid. $\uparrow$ [%]	Success Rate $\uparrow$ [%]	Time To Goal $\downarrow$ [s]	Solver Time $\downarrow$ [ms]
20	100	84	7.53	1.09
40	100	98	4.17	3.90
60	100	98	3.52	9.05

TABLE IV : Effect of horizon length in the single-human scene. Safety holds at every horizon. A short horizon yields slow, conservative trajectories, while extending the horizon reduces time-to-goal only up to a point, after which it mainly adds computation. A horizon of 40 balances goal-reaching speed and solver time.

Explore similar work

HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control
May 25, 2026Simon Schaefer, Joshua Näf, Stefan LeuteneggerHuman Motion Generation Motion Estimation
Technical University of Munich · MCML · MIRMI +1
Navigating the Crowd: Non-linear MPC with Social Forces Dynamics for Human-Aware Robot Navigation
Jul 11, 2026Stefano Trepella, Andrea Ostuni, Mauro Martini +5Social Robot Navigation Model Predictive Control
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
CoCoNav: Conformal Control for Safe Robot Navigation in Crowds
Aug 7, 2026Cheng Guo, Mingzhe Ni, Zheng Liang +5Social Robot Navigation Model Predictive Control
Department of Computer Science, The University of Manchester, Manchester, UK. · Human-Robot Interfaces and Interaction Laboratory, Italian Institute of Technology, Genoa, Italy. · Genisom AI, Shanghai, China. +3

May 25, 2026, cs.ROJ/K move · Enter open · S save

HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control

Simon Schaefer, Joshua Näf, Stefan Leutenegger

Technical University of Munich · MCML · MIRMI+1

Human Motion Generation Motion Estimation Model Predictive Control Latent Space

Open paper AskPDF arXiv

Robust and accurate perception of humans in their 3D scene context is essential for integrating robots into everyday environments. Existing approaches, however, often fail to predict plausible and accurate human motion estimates that are consistent with the surrounding scene, especially in the presence of heavy occlusions or partial visibility. This can limit both safety and efficiency for robotic operations. We introduce HumanFlow, a latent diffusion model that unifies human motion tracking and forecasting, conditioned on the 3D scene context. We show that our human motion model produces smooth and accurate predictions under challenging conditions, including heavy occlusions, and outperforms state-of-the-art methods in tracking accuracy while being significantly more efficient. Furthermore, we show how HumanFlow's latent space can be tightly coupled with control by conditioning a flow-matching-based, approximate MPC policy on these representations. We validate our policy in simulation with real human trajectories for MAV social navigation, demonstrating superior navigation performance and remaining collision-free, even under partial observability of the human.

Abstract

Explore similar work

HumanFlow -- Diffusion-Driven MAV Navigation Among Humans via Tightly-Coupled Motion Tracking, Forecasting, and Control

Navigating the Crowd: Non-linear MPC with Social Forces Dynamics for Human-Aware Robot Navigation

CoCoNav: Conformal Control for Safe Robot Navigation in Crowds