Improving Robotic Imitation Learning via Trajectory Standardization
2026-06-22 • Robotics
RoboticsComputer Vision and Pattern Recognition
AI summaryⓘ
The authors focus on improving how robots learn from human demonstrations, which often have uneven speed and pauses that make learning harder. They introduce a new way called Information-Standardized Trajectory Resampling (ISR) that spaces out demonstration points based on the amount of important movement information, rather than just time. This method helps remove repetitive or unimportant data while keeping key moves, leading to better robot learning and task success. Their tests show ISR works well on different tasks and reduces training time compared to simple time-based sampling.
Imitation LearningRobotic ManipulationTrajectory ResamplingRiemannian ManifoldGeodesic ParameterizationInformation DistanceVelocity NormAcceleration NormDownsamplingTrajectory Data Preprocessing
Authors
Licheng Yang, Lingfeng Qian, Fei Zheng, Yonghao He, Wei Sui, Shuangshuang Li, Hu Su
Abstract
Imitation learning for robotic manipulation relies on large sets of human demonstration trajectories, which are often noisy and temporally irregular due to variable operator speed, intermittent pauses, and inconsistent action density. A common preprocessing strategy is time-uniform downsampling to shorten sequences, but it cannot effectively remove speed-induced non-uniformity or redundant pauses. This mismatch degrades data quality and hinders policy learning. To address this issue, we propose Information-Standardized Trajectory Resampling (ISR), an offline preprocessing method for effective imitation learning. ISR resamples each trajectory by enforcing approximately equal information distance between adjacent points. Specifically, we map trajectories onto an information-modulated Riemannian manifold and perform geodesic-equidistant parameterization. We construct an information-intensity field from velocity and acceleration norms: the velocity term removes small-motion redundancy, while the acceleration term preserves high-curvature and fine-manipulation phases. We evaluate ISR on three real-world manipulation tasks with mainstream imitation learning policies. Compared with the baseline time-uniform 3x downsampling, ISR improves task success rates by about 25%, remains robust across datasets collected from different operators, and reduces both dataset size and training cost. The code and videos are publicly available at https://d-robotics-ai-lab.github.io/isr.page.