Provides a closed-form safety law for Dynamic Movement Primitives, enabling provably safe robot control without real-time optimization.
April 1, 2026
Original Paper
SafeDMPs: Integrating Formal Safety with DMPs for Adaptive HRI
arXiv · 2603.29708
The Takeaway
It achieves orders-of-magnitude faster performance than optimization-based baselines, allowing high-frequency controllers to guarantee collision avoidance in dynamic human-centric environments without the usual compute overhead.
From the abstract
Robots operating in human-centric environments must be both robust to disturbances and provably safe from collisions. Achieving these properties simultaneously and efficiently remains a central challenge. While Dynamic Movement Primitives (DMPs) offer inherent stability and generalization from single demonstrations, they lack formal safety guarantees. Conversely, formal methods like Control Barrier Functions (CBFs) provide provable safety but often rely on computationally expensive, real-time op