Search papers, labs, and topics across Lattice.
This paper addresses the underexplored challenge of robotic table tennis serves by developing a novel method that combines motion primitives, Model Predictive Control, and Bayesian Optimization. The approach enables the robot to generate serves that comply with official rules while achieving spins of up to 550 rad/s and speeds of 6.7 m/s, surpassing elite human players. This advancement not only enhances the capabilities of robotic systems in sports but also pushes the boundaries of physics modeling and control in dynamic environments.
Robotic serves can now exceed elite human performance, achieving spins of 550 rad/s and speeds of 6.7 m/s.
Table tennis, a dynamic, compact, and popular sport, has received significant attention as a robotics benchmark over the last decades. Most of the research has focused on the rally aspect - returning an incoming ball - requiring high-speed vision, agile motion planning, and tight closed-loop control. However, the other component of table tennis gameplay - the serve - is comparatively a quite unexplored research problem, that in fact requires pushing physics modeling and control to the extremes. Achieving competitive serves with a robot presents domain-specific challenges, such as high-spin generation from a spinless ball, precise aiming, or multi-objective optimization. In this work, we present a novel approach for generating official rule-compliant serves by combining motion primitives, Model Predictive Control, and Bayesian Optimization. Serves generated in this way offer a wide and controllable variation of spins of up to 550 rad/s, and speeds of up to 6.7 m/s, matching and even surpassing those of elite table tennis players.
