Motion-prior training improves robot insertion success with few demonstrations
Dissecting Motion-Prior Regularization for Data-Scarce Robotic Insertion
Robotics
Summary
The study looks at how teaching robots to move smoothly helps them do a tricky task called insertion with very few examples. The researchers tested two ways to encourage smooth motion during training: one that avoids sudden changes in speed and another that links speed to how sharply the robot moves. They found that encouraging smooth speed changes worked best and adding the second method didn't improve things much. This means teaching robots simple smooth movements can help them learn difficult tasks better, even with little practice data.
What this means in practice
- •For robotics engineers: Improve robot insertion skills by training with minimum jerk motion priors to achieve higher success rates from few demonstrations.
- •For industrial automation teams: Develop more reliable robotic assembly systems by applying smooth motion constraints during learning to reduce failures in tight insertion tasks.
Authors
Ning Hu, Shuai Li, Jindong Tan
Abstract
This study asks whether training-time motion-prior regularization can improve insertion success when a diffusion policy is learned from only 15 demonstrations. Minimum jerk discourages abrupt changes in predicted translational acceleration; speed-curvature regularization instead couples movement speed to path geometry. These are candidate mechanisms for task completion, not safety guarantees. We compare the priors individually and jointly, neither prior, and generic smoothness, with 80 real-robot trials per setting pooled over four recorded condition classes. Joint and minimum-jerk-only settings each achieved 70/80 successes (87.5%), versus 69/80 (86.3%) for speed-curvature only, 66/80 (82.5%) for neither prior, and 67/80 (83.8%) for generic smoothness. Success rates and Wilson 95% confidence intervals are visualized for direct comparison. Joint regularization exceeded neither by 5.0 percentage points but provided no observed gain over minimum jerk alone. The results motivate minimum jerk as the simpler candidate for replication, without establishing synergy, biomechanical specificity, improved safety, or distribution-shift robustness.