Dynamic Movement Primitives With Control Barrier Functions for Constrained Trajectory Planning

• Published in: IEEE robotics and automation letters Vol. 10; no. 9; pp. 9416 - 9421
• Main Authors: Vesentini, Federico, Meli, Daniele, Sansonetto, Nicola, Persio, Luca Di, Muradore, Riccardo
• Format: Journal Article
• Language: English
• Published: IEEE 01.09.2025
• Subjects: Collision avoidance; const- rained motion planning; Control systems; Convergence; Imitation learning; nonholonomic motion planning; Planning; Robot kinematics; Safety; Shape; Trajectory; Trajectory planning; Vectors

Dynamic Movement Primitives (DMPs) form a robust framework for trajectory generation based on imitation learning, aiming to replicate the shape of reference trajectories from demonstrations closely. DMPs have been extensively employed for trajectory planning in robotic systems. However, they cannot...