HumanMPC - Safe and Efficient MAV Navigation among Humans

2025-10-20

AI Summary

This work addresses the challenge of safe and efficient navigation for micro air vehicles (MAVs) in dynamic human crowds—specifically requiring full-body human motion modeling beyond root-joint trajectory tracking. We propose a model predictive control (MPC) framework that integrates formal guarantees with data-driven learning. Our key contributions are: (i) a reachability-based safety constraint mechanism that imposes explicit bounds only on the initial control input, yet rigorously captures its propagated effect over the entire prediction horizon—ensuring strict safety while significantly reducing conservatism; and (ii) tight coupling with a data-driven human motion predictor, trained on real-world pedestrian trajectories, enabling multi-task capabilities including goal-directed navigation and human tracking. Extensive simulations and real-world flight experiments demonstrate superior performance over state-of-the-art baselines in safety compliance, navigation efficiency, and task adaptability.

Technology Category

• Humans and AI: Human-Aware Planning and Behavior Prediction
• Intelligent Robots: Motion and Path Planning
• Computer Vision: Motion & Tracking

Application Category

• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Economics, Online Markets and Human Computation: LLM based quality controls for crowd work
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

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 HumanMPC, a Model Predictive Control (MPC) framework for 3D Micro Air Vehicle (MAV) navigation among humans that combines theoretical safety guarantees with data-driven models for realistic human motion forecasting. Our approach introduces a novel twist to 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 HumanMPC 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 MAVs in this work, it is generic and can be adapted by other platforms. Our results show that the method ensures safety without excessive conservatism and outperforms baseline approaches in both efficiency and reliability.

Problem

• Ensuring safe 3D MAV navigation in human environments
• Overcoming limitations of simplified 2D human motion models
• Combining safety guarantees with realistic human motion prediction

Innovation

• MPC framework for 3D MAV navigation among humans
• Reachability-based safety formulation constraining initial control
• Data-driven models for realistic human motion forecasting