Smoothness Ranks Skill, Not Success: An Audit of Published Trajectory-Smoothness Curation Metrics Under Episode-Length Controls

cs.RO

Submitted: 2026-10-12

Updated: 2026-10-12

Comments: 13 pages, 4 figures. Accepted (poster) at the NeurIPS 2026 RoboPAD Workshop. Code: https://github.com/imjbassi/smoothness-metric-audit

Code: https://github.com/imjbassi/smoothness-metric-audit

License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/

Sources

• Learning from the Best: Smoothness-Driven Metrics for Data Quality in Imitation Learning
• Auditing Demonstration Curation Metrics: Action-Only Scorers Fail on the Structural Defects That Degrade Imitation Policies
• What Demonstration Curation Metrics Do to Your Policy
• Phase-Localized Curation Does Not Help: A Negative Result on Per-Phase Metric Selection for Demonstration Filtering
• An Efficient Metric for Data Quality Measurement in Imitation Learning
• Robot Learning as an Empirical Science: Best Practices for Policy Evaluation
• RoboEval: Where Robotic Manipulation Meets Structured and Scalable Evaluation
• What Are We Actually Benchmarking in Robot Manipulation?
• Diffusion Policy: Visuomotor Policy Learning via Action Diffusion
• DROID: A Large-Scale In-The-Wild Robot Manipulation Dataset
• REASSEMBLE: A Multimodal Dataset for Contact-rich Robotic Assembly and Disassembly

Related papers

• FMT x: An Efficient and Asymptotically Optimal Extension of the Fast Marching Tree for Dynamic Replanning
• MPCFormer: A physics-informed data-driven approach for explainable socially-aware autonomous driving
• RoboLab: A High-Fidelity Simulation Benchmark for Analysis of Task Generalist Policies
• ARC: A Reasoning Recipe for Robot Foundation Models
• HRDexDB: A 4D Dexterous Grasping Dataset Across Human and Multiple Robot Embodiments
• APT: Action Expert Pretraining Improves Instruction Generalization of Vision-Language-Action Policies