Mobile manipulation policies trained on data from a single robot pose fail when the robot moves even a few centimeters. The paper introduces MobileVISTA, a data generation framework that creates diverse training examples from one demonstration. It works by removing the robot from the camera image, reprojecting the scene as if from a different base pose, and then compositing a re-rendered robot performing a retargeted action. Policies trained on this augmented data generalize to previously unseen base poses without additional data collection or a trained generative model. The method is particularly effective for humanoid robots, where the camera moves with the body and the robot’s own arms fill much of the view. Experiments in simulation and on a real Galaxea R1 Pro show improved robustness over baselines that use 3D representations or large pretrained policies.
Synthetic views make robot policies more tolerant of pose errors
MobileVISTA jointly modifies egocentric images and robot actions to train manipulation policies for base poses absent from demonstrations.
Big Tech
Suzannah Wistreich · Stephen Tian · Isabella Huang · Vitor Campagnolo Guizilini · Sergey Zakharov · Katherine Liu · +1 more
Stanford University · Toyota Research Institute
Research Digest··3 min read
Thread:Robot Manipulation Policies
In one line
MobileVISTA generates pose-perturbed training data from single-pose demonstrations to improve mobile manipulation policy robustness.
Before you read this
An idea this paper builds onRead it as
Wistreich and colleagues introduce an offline augmentation framework that converts demonstrations recorded at one canonical robot pose into physically consistent examples at perturbed poses.
MobileVISTA perturbs a robot's base pose and then updates both parts of an imitation-learning example: what the onboard camera should see and what actions the robot should execute.
How it works
before and afterThe Daily Edition
The front page in your inbox each weekday morning: the lead, the picks, and why each one earned its place.