.png){kind=icon}
.png){kind=icon}
Return
Nonholonomic Dynamic Movement Primitives
.png){kind=icon}
PRE
AI
G
G
A
DOI：10.1109/tro.2026.3706555.png)
.png){kind=icon}
Original request for help.png){kind=icon}
Share.png){kind=icon}
Save
Abstract
En 中文
We address imitation-based trajectory generalization for robots subject to nonholonomic constraints. Standard dynamic movement primitives (DMPs) are effective for unconstrained systems, but they can generate infeasible trajectories when applied to wheeled robots, such as unicycles or car-like vehicles. We introduce nonholonomic DMPs (NHDMPs), a framework that reformulates the imitation objective in quasi-velocity space and replaces the standard linear attractor with a Lyapunov-stable controller that enforces nonholonomic feasibility, together with two forcing terms learned from demonstrations. We derive a numerical optimization-based reference benchmark and evaluate two NHDMP variants: an optimized version with per-instance parameter optimization and a trained version with fixed parameters learned offline. On 1000 random trajectories, the optimized variant achieves imitation discrepancy close to the numerical optimum while being an order of magnitude faster; the trained variant achieves comparable trajectory quality at lower computational cost, outperforming prior nonholonomic DMP methods on the considered benchmark. Physical experiments on the AlterEgo wheeled platform, together with simulations of sequential primitive chaining for car-like road navigation, demonstrate the approach across systems of increasing complexity.
Keywords:
Dynamic movement primitives (DMPs)
learning from demonstration
nonholonomic motion planning
wheeled robots
Journal
IF:
10.5
Papers:
3.3K
Citations:
2.8W
Organization
Cited Papers