Trajectory Optimization for Collision-Aware Redundant Robotic Multi-Axis Additive Manufacturing by Constrained Gradient Projection

A new gradient-projection method for robotic multi-axis additive manufacturing keeps nozzle placement under 10 μm while cutting max joint jerk by up to 77.6%. For teams working on fabrication pipelines, the interesting part is the collision-aware optimization: it handles changing geometry during deposition and still converges faster than an SQP baseline. The paper also reports successful physical prints of complex shapes with fewer visible artifacts.