cs.RONov 9, 2026

Flip Anything with Agentic Robotics Self-Learning

Authors: Shuangyu Xie, Kaiyuan Chen, Ken Goldberg

Organizations: University of California, Berkeley

Abstract

Flipping is a fundamental robotic manipulation skill that requires reorienting a target object in a stable pose on a planar support surface by rotating it 180∘^\circ about an axis parallel to the support surface -- think of flipping a coin from heads to tails. Although flipping is a common objective in industrial tasks such as parts inspection, mechanical assembly, and tool use, coding a bimanual robot with grippers to flip diverse objects is a significant challenge. In this paper, we show that a coding agent can autonomously develop and refine object-flipping strategies through iterative learning in physics simulations across diverse object geometries. Progressive skill acquisition, from basic handover to toppling and pushing, robust grasping and sensing, and thin-object manipulation with recovery, improves task success from 24.7% to 95.0%. The resulting graph-based code integrates high-level strategy selection with reactive control, enabling multi-stage flipping on physical robots.

Figures & tables

Explore similar work

CardsList
  1. Flip Stunts on Bicycle Robots using Iterative Motion Imitation

    Mar 30, 2026Jeonghwan Kim, Shamel Fahmi, Seungeun Rho +2Robot Imitation LearningImitation Learning

  2. ReSkill: Selective Self-Improvement for Robot Manipulation

    Nov 7, 2026Zheng Sun, Zhihao Li, Zhuo Li +3Robot Skill LearningSelf-Improving Agents

  3. FlipItRight: Stable Pose-Targeted Throw-Flip Across Diverse Objects

    Jun 1, 2026Axel Dawne, Shinkyu ParkNon-Prehensile ManipulationRobot Motion Generation