Push Anything: Single- and Multi-Object Pushing From First Sight with Contact-Implicit MPC

TL;DR

This paper demonstrates a contact-implicit model predictive control approach for versatile, real-time multi-object pushing in robotics, capable of handling diverse geometries and complex contact interactions with high success rates.

Contribution

The authors introduce C3+, an improved CI-MPC algorithm that enables real-time multi-object pushing with broader object diversity and complex contact reasoning, surpassing prior methods.

Findings

Achieves 98% success rate across 33 objects

Real-time performance in multi-object pushing tasks

Average time-to-goal increases with number of objects

Abstract

Non-prehensile manipulation of diverse objects remains a core challenge in robotics, driven by unknown physical properties and the complexity of contact-rich interactions. Recent advances in contact-implicit model predictive control (CI-MPC), with contact reasoning embedded directly in the trajectory optimization, have shown promise in tackling the task efficiently and robustly. However, demonstrations have been limited to narrowly curated examples. In this work, we showcase the broader capabilities of CI-MPC through precise planar pushing tasks over a wide range of object geometries, including multi-object domains. These scenarios demand reasoning over numerous inter-object and object-environment contacts to strategically manipulate and de-clutter the environment, challenges that were intractable for prior CI-MPC methods. To achieve this, we introduce Consensus Complementarity Control Plus (C3+), an enhanced CI-MPC algorithm integrated into a complete pipeline spanning object scanning, mesh reconstruction, and hardware execution. Compared to its predecessor C3, C3+ achieves substantially faster solve times, enabling real-time performance even in multi-object pushing tasks. On hardware, our system achieves overall 98% success rate across 33 objects, reaching pose goals within tight tolerances. The average time-to-goal is approximately 0.5, 1.6, 3.2, and 5.3 minutes for 1-, 2-, 3-, and 4-object tasks, respectively. Project page: https://dairlab.github.io/push-anything.