Precise progress estimation improves robotic high precision tasks

Not All Actions Contribute Equally: Learning Precise Progress Estimation from Imprecise Demonstrations

Robotics

Summary

Progress estimation helps robots know how close they are to completing a task, which is especially tricky in tasks requiring high precision. The authors found that not all actions during human demonstrations contribute equally: some actions might be mistakes, confusing the robot’s learning. They created PRIME, a method that looks across multiple demonstrations and connects similar states to better estimate progress by understanding real advancement versus errors. This approach is more accurate for difficult manipulation tasks and works well even when demonstrations are imperfect.

What this means in practice

  • For robotics engineers: Improve robot learning in precise assembly tasks by more accurately assessing task progress from imperfect human demonstrations.
  • For industrial automation teams: Develop more reliable robotic insertion and manipulation systems for manufacturing by distinguishing meaningful progress from human errors in training data.

Authors

Huanqian Wang, Boshi Tang, Botong Xiao, Jie Zhang, Yang Yue, Danhua Tao, Shiji Song, Gao Huang

Abstract

Progress estimators play an essential role in providing dense reward signals for reinforcement learning in robotic manipulation, but accurately assessing task progress can be much challenging. Existing methods heavily rely on expert data and naively assume that all actions within a demonstration contribute to task success. This assumption often breaks down in real-world scenarios, especially in high-precision manipulation, where subtle geometric errors can lead to task failure. Therefore, these methods can erroneously interpret human mistakes as meaningful progress, further corrupting progress learning. We argue that a key limitation is the lack of a global prior regarding task evaluation criteria, which is crucial for distinguishing meaningful progress from human mistakes. To this end, we propose PRIME, a novel progress estimator capable of learning precise progress estimation from imprecise demonstrations by aggregating experience across trajectories. PRIME constructs a weighted graph over observed states, connecting states across trajectories based on spatial proximity and visual consistency. Edge weights encode spatial distances as transition costs, and shortest-path search approximates the geodesic distance to success. Changes in this distance naturally distinguish advancement, stagnation, and setbacks without assuming monotonic progress over time. Extensive experiments in both simulation and real world on precise manipulation tasks show that PRIME is consistently effective across diverse tasks, and robust to data with varying degrees of suboptimality. Notably, the advantage of PRIME gets more pronounced in higher-precision scenarios, yielding up to a \(5\times\) improvement in policy success rate over the SFT baselines on charger insertion.