Risk-Aware and Scalable Hierarchical Motion Planning for Large-Scale Robotic Swarms Via CVaR-Constrained MPC
Xuru Yang, Yuqiao Zhao, Yunze Hu, Zongru Yang, Pingping Zhu, Ying Sun, Chang Liu
AI summary
Problem
Large-scale swarm motion planning struggles to balance computational scalability with rigorous safety guarantees in cluttered environments, as microscopic methods become intractable and macroscopic methods often ignore collision avoidance or robot dynamics.
Approach
The proposed C-ROVER framework uses a closed-loop hierarchical structure where a macroscopic planner models the swarm as a Gaussian Mixture Model and optimizes trajectories using CVaR-constrained MPC, while a microscopic controller handles individual robot tracking and collision avoidance via distributed MPC.
Key results
- Analytical CVaR expression derived from a proven stochastic Signed Distance Function for GMMs
- Risk-aware space discretization optimizing Gaussian covariances to mitigate collision risk
- Provably convergent sequential convex programming algorithm for efficient online planning
- Validation through simulations and real-world experiments confirming scalability, safety, and real-time performance
Why it matters
Provides a practical, risk-aware planning framework that enables safe and efficient large-scale swarm deployment in complex, obstacle-rich environments for applications like search and rescue.
Abstract
Motion planning for large-scale robotic swarms presents significant challenges in terms of scalability and safety assurance in cluttered environments. To address these issues, this manuscript proposes a Closed-loop hierarchical Risk- aware swarm mOtion planner using Conditional ValuE at Risk (C-ROVER) that enables safe and efficient navigation for swarm robotic systems. The hierarchical structure of C-ROVER comprises a macroscopic planning stage that models the swarm state with Gaussian Mixture Models (GMMs) and generates trajectories for the swarm GMM, followed by a microscopic control stage that computes individual robot control using dis- tributed model predictive control to track the GMM trajectories while achieving robot-level collision avoidance. Robot positions are periodically used to update the swarm GMM, closing the hierarchical planning and control loop. To achieve collision risk-awareness between the swarm and environmental obstacles at the macroscopic stage, C-ROVER leverages the stochastic Signed Distance Function to characterize the distance between the swarm GMM and obstacles, which is proven to follow a GMM. Then C-ROVER proposes an analytical expression of Conditional Value-at-Risk (CVaR) of a GMM to enable the swarm collision risk mitigation. Furthermore, C-ROVER designs a novel risk-aware space discretization approach to enhance the ability to navigate constrained spaces. To achieve efficient online motion planning, C-ROVER develops a conver- gent sequential convex programming approach for macroscopic planning, leveraging the concavity of CVaR constraints. C- ROVER has been evaluated through various simulations and real-world experiments, demonstrating its capability to ensure safe, scalable, and real-time swarm navigation in cluttered scenarios.