AI & ML
Homeward: No Place Like the Training View
arXiv cs.RO0 views
arXiv:2611.24455v1 Announce Type: new Abstract: Vision-language-action (VLA) policies implicitly assume that third-person cameras remain fixed at their data-collection poses; once a camera is bumped, remounted, or swapped at deployment, task success degrades precipitously even though the underlying task and robot remain unchanged. We present Homeward, a training-free, plug-and-play observation adapter that canonicalizes observations from an uncalibrated deployment camera back into the training view for frozen VLA policies. Our design stems from a closed-loop diagnostic paradox in simulation: while re-rendering perturbed views into the training camera with oracle geometry recovers much of the lost performance, substituting an off-the-shelf feed-forward 3D foundation model can leave the policy worse off than applying no correction at all. This degradation concentrates on the thin, articulated robot arm, which feed-forward depth prediction tears and scatters - yet the arm's exact 3D state is already known from robot kinematics. Homeward exploits this asymmetry: it estimates what is unknown - camera parameters and static scene depth - from the live RGB frame and a single training-view reference, and renders what is known - the moving robot links - directly from the kinematic model. Evaluated across $\sim$300,000 closed-loop episodes spanning four frozen VLAs, Homeward boosts success across all 1,599 camera variants of LIBERO-Plus from 62.5%, 76.5%, 68.0%, and 3.6% to 77.6%, 95.1%, 91.2%, and 26.4% for OpenVLA-OFT, $\pi_{0.5}$, $\pi_0$, and OpenVLA, respectively. Without any scene fine-tuning or deployment camera calibration, Homeward extends to 6-DoF random placements, focal-length changes, and, with per-step pose estimation, continuous intra-episode camera drift, while matching or surpassing a calibrated, scene-trained view-synthesis baseline on three of four policies on LIBERO-Plus.
Source:https://arxiv.org/abs/2611.24455PreviousConstructive Infinitely Differentiable Guidance Vector Fields for Robotic ControlNextWhen to Refine: Selective Search for Frozen Visual World Models
Related posts

How to Interpret Logistic Regression and Odds Ratios
0dev.to
Kubernetes Service Account Tokens Do Not Need to Ride Along
0dev.to Kubernetes
Export a calendar day to ICS for your system calendar
0dev.to OpenSource
Comparing Axleta Repository Packer with Gitingest
0dev.to Programming

Animating and rigging by hand is sometimes hard....
0dev.to Programming
Anthropic is bullshitting you about subagents and loops.
0dev.to Programming