AI & ML
Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation
arXiv cs.RO0 views
arXiv:2606.20118v3 Announce Type: replace Abstract: Vision-language-action (VLA) policies have shown strong potential for general-purpose manipulation, yet they often fail on novel, out-of-distribution objects whose appearance or geometry deviates from the training distribution. The standard remedy is to collect multi-view teleoperation data for every failure case, but this scales poorly in both cost and time. We introduce Pose6DAug, a failure-driven data augmentation framework that turns existing successful episodes into targeted demonstrations for a policy's failure modes, without any new data collection. Our key insight is that each successful episode already encodes a physically valid action trajectory together with calibrated multi-view observations. By swapping only the manipulated object while preserving this trajectory, we obtain new and physically grounded demonstrations. However, the challenge lies in synthesizing object swaps, e.g., naive 2D video editing breaks multi-view consistency and physical plausibility, particularly under heavy occlusion and egocentric viewpoints. Our method instead operates directly in 3D, anchoring the target object with an explicit mesh driven by a temporally coherent 6D pose trajectory. This ensures geometrically consistent renderings across all camera views. Fine-tuning a VLA on data augmented by our method improves success rates by 16.5% relative to the state-of-the-art baseline on novel objects, while preserving in-distribution performance. On a real robot, it more than doubles the success rate of the base policy. These results show that multi-view and physically consistent augmentation is a practical path to scalable VLA generalization.
Source:https://arxiv.org/abs/2606.20118PreviousWorldComposer: Generative High-Fidelity Simulation with Digital Cousins for Generalizable Robot Learning and EvaluationNextNeural LiDAR Bundle Adjustment
Related posts
How I use my bots to plan, and a dedicated spare MacBook to write the code
0dev.to
How to Speed Up Qwen3.8-27B in llama.cpp (NVIDIA's Draft Model May Lose to MTP)
0dev.to
How to Make the Ink Used to Write Hamlet and the Declaration of Independence
0Hacker News
Why AI Wants to Be Local – With Pete Warden (Creator of Moonshine Voice)
0Hacker News
A Voice License Must Fit the Product It Authorizes
0dev.to Machine Learning

How I Made a 90-Second AI Short Film With One Consistent Character (and Fixed Its Glitches With ffmpeg)
0dev.to Tutorial