The Curse of Precision: A Data Scaling Law for High-Precision Robotic Manipulation

2026-07-25

AI Summary

This study investigates the relationship between demonstration data volume and task success rate in high-precision robotic manipulation, revealing that the required data grows super-exponentially as the target precision approaches the system’s fundamental limit. Through imitation learning experiments, multi-component system evaluations, and logarithmic-scale analysis, the work introduces the first precision-oriented data scaling law: log(N) ∝ 1/(P−c), where the limiting precision c emerges as a system-level property determined jointly by sensors, actuators, and the expert policy—rather than being an intrinsic constant of the task itself. This model not only quantifies the data cost of achieving higher precision but also demonstrates that optimizing system components can effectively reduce c, thereby raising the achievable precision ceiling and providing a quantitative framework for evaluating robotic system capabilities.

Abstract

While scaling laws for imitation learning have primarily focused on generalization in open-world settings, the relationship between data and precision in closed-world tasks like robotic assembly remains largely unexplored. This paper systematically investigates this relationship and introduces a novel scaling law. We find that to achieve a fixed success rate, the required number of demonstrations $N$ grows super-exponentially as the target precision $P$ approaches a limit $c$. This relationship is accurately captured by the model $\log(N) \propto 1/(P-c)$. Crucially, we reveal that the limit precision $c$ is not a static physical constant of the task but an emergent property of the entire agent system, including its sensors and expert policy. Through experiments on canonical manipulation tasks, we validate this law and demonstrate that improving system components, such as adding a wrist camera or using a more effective expert, measurably lowers $c$, thus expanding the system's achievable precision. Our work provides a new theoretical framework for precision in robotics and a quantitative metric to evaluate system capabilities. Furthermore, these findings provide a practical methodology for guiding the development and debugging of high-precision manipulation systems.

Problem

• precision
• robotic manipulation
• scaling law
• data efficiency
• imitation learning

Innovation

• scaling law
• high-precision manipulation
• imitation learning
• emergent precision limit
• robotic assembly