RoboPocket: Improve Robot Policies Instantly with Your Phone
Junjie Fang, Wendi Chen, Han Xue, Fangyuan Zhou, Tian Le, Yi Wang, Yuting Zhang, Jun Lv, Chuan Wen, Cewu Lu

TL;DR
RoboPocket enables instant robot policy improvement using smartphones and AR visualization, significantly increasing data and sample efficiency without physical robot use, thus accelerating imitation learning.
Contribution
It introduces RoboPocket, a portable system that combines remote inference, AR visualization, and online finetuning for scalable, robot-free policy iteration.
Findings
Doubles data efficiency over offline methods
Achieves up to 2x sample efficiency in distributed settings
Enables rapid policy updates within minutes
Abstract
Scaling imitation learning is fundamentally constrained by the efficiency of data collection. While handheld interfaces have emerged as a scalable solution for in-the-wild data acquisition, they predominantly operate in an open-loop manner: operators blindly collect demonstrations without knowing the underlying policy's weaknesses, leading to inefficient coverage of critical state distributions. Conversely, interactive methods like DAgger effectively address covariate shift but rely on physical robot execution, which is costly and difficult to scale. To reconcile this trade-off, we introduce RoboPocket, a portable system that enables Robot-Free Instant Policy Iteration using single consumer smartphones. Its core innovation is a Remote Inference framework that visualizes the policy's predicted trajectory via Augmented Reality (AR) Visual Foresight. This immersive feedback allows…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Videos
No videos yet. Explain this paper in a talk, walkthrough, or lecture? Add one.
Taxonomy
TopicsReinforcement Learning in Robotics · Social Robot Interaction and HRI · Robot Manipulation and Learning
