Backend
SHAPE: Discrete Supervision and Parallel Continuous Streams for Learning Dexterous Manipulation from Egocentric Human Data
arXiv cs.RO0 views
arXiv:2611.24585v1 Announce Type: new Abstract: Egocentric human recordings are far cheaper than dexterous robot demonstrations, promising stronger pretraining and direct skill learning without task-specific robot data. Yet humans and robots differ in morphology and kinematics, so human recordings lack the joint positions and actuator commands that supervise robot policies, providing only retargeted end-effector (EEF) actions. This raises two questions: how human data should supervise the policy, and how a dexterous robot should read out actions at deployment. We address both in SHAPE (Supervision from Human Action tokens with Parallel Executable streams), a vision-language-action (VLA) model whose backbone predicts discrete action tokens of EEF chunks as an auxiliary task, while a shared flow-matching expert outputs two executable streams, EEF and joint. On a bimanual robot with 22-DoF hands, a matched study shows that discrete supervision helps learn from human data, driving backbone gradients and shaping action-informative representations across domains. Under standard control pipelines at deployment, direct joint readout excels at fine-grained control with robot demonstrations, scoring 0.80 across six tasks against 0.63 for {\pi}0.5, whereas IK-based EEF readout excels at human-to-robot transfer. Pretrained with human data and discrete tokens, SHAPE learns new tasks from human demonstrations without task-specific robot data.
Source:https://arxiv.org/abs/2611.24585PreviousTinyARM-X: A Series of Open-Source, Configurable, and Transparent Torque-Controlled Desktop-Scale Robotic ManipulatorsNextHydrodynamics of robotic micro-swimmers in confinement
Related posts
Attackers Are Already Knocking: 150+ Break-In Attempts in a Day. Is Your Site's Java Patched?
0dev.to Java
Java4Shell (CVE-2026-114938): OpenJDK corrigido no RHEL 8, 9 e 10
0dev.to Java
Five git log commands that show where a codebase actually changes
0dev.to Git
Hyperliquid JavaScript QuickStart for Node.js & TypeScript
0dev.to TypeScript

No Transition Without a Receipt: an Operator's Control Room for Agent Money
0dev.to TypeScript
A solver froze our Node server for 8 seconds in CI — moving it off the request path
0dev.to TypeScript