Contact Windows Are a Model-Error Bottleneck, Not a Decision Bottleneck

Event-based and semi-Markov world models rest on a specific claim: on a fixed 50 Hz time axisstance, flight, impact and recovery share one transition function, so prediction errorconcentrates in the contact window and an explicit event time should improve control. We test iton humanoid landing. The error is real: one-step error at touchdown is 4.7x its pre-contactlevel, 2.4x after removing its ordinary growth with horizon. By physical quantity the jump livesentirely in velocity channels (joint velocity 3.2x), while the pose errors the cost actuallyscores show no extra jump (0.67x, 0.79x). On the decision side the answer is no: overwriting themodel with ground truth for three steps cuts failures by 8.1 pp at contact, by 16.1 pp eightsteps later, 20.3 pp at random steps, and a time-matched control recovers only 1.7 pp---mostlyfrom the touchdown frame (78%). The interface should encode the state jump, not the clock: fourcontact-time estimators are all null, while a post-impact reset head gives +0.016 orderingaccuracy and -1.9 pp of failures, with a placebo built from the model's own increment recoveringnone of it. Both effects scale with base-model accuracy.

Authors

Institutions

Publication Details

Journal
Zenodo (CERN European Organization for Nuclear Research)
Published
2026-11-21
DOI
https://doi.org/10.5281/zenodo.24421074
Primary Topic
Reinforcement Learning in Robotics
Type
preprint
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
preprint

Contact Windows Are a Model-Error Bottleneck, Not a Decision Bottleneck

Haihong Qiu
Zenodo (CERN European Organization for Nuclear Research)
Reinforcement Learning in Robotics
preprint

Contact Windows Are a Model-Error Bottleneck, Not a Decision Bottleneck

Haihong Qiu
preprint en

Abstract

Event-based and semi-Markov world models rest on a specific claim: on a fixed 50 Hz time axisstance, flight, impact and recovery share one transition function, so prediction errorconcentrates in the contact window and an explicit event time should improve control. We test iton humanoid landing. The error is real: one-step error at touchdown is 4.7x its pre-contactlevel, 2.4x after removing its ordinary growth with horizon. By physical quantity the jump livesentirely in velocity channels (joint velocity 3.2x), while the pose errors the cost actuallyscores show no extra jump (0.67x, 0.79x). On the decision side the answer is no: overwriting themodel with ground truth for three steps cuts failures by 8.1 pp at contact, by 16.1 pp eightsteps later, 20.3 pp at random steps, and a time-matched control recovers only 1.7 pp---mostlyfrom the touchdown frame (78%). The interface should encode the state jump, not the clock: fourcontact-time estimators are all null, while a post-impact reset head gives +0.016 orderingaccuracy and -1.9 pp of failures, with a placebo built from the model's own increment recoveringnone of it. Both effects scale with base-model accuracy.

Zenodo (CERN European Organization for Nuclear Research)
Guangdong University of Technology (CN)
Reinforcement Learning in Robotics
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon
Contact Windows Are a Model-Error Bottleneck, Not a Decision Bottleneck — Haihong Qiu · Zenodo (CERN European Organization for Nuclear Research) (2026) | TGRS Research Map | TGRS