TetraGrip: Sensor-Driven Multi-Suction Reactive Object Manipulation in Cluttered Scenes

2025-03-12

AI Summary

Unreliable grasping in dense warehouse environments arises from object occlusion, stacking, and non-adhesive surfaces. Method: This paper proposes a four-degree-of-freedom adjustable linear-driven mechanism with four suction cups, integrated with Time-of-Flight (ToF) proximity sensors and real-time feedback control to enable coordinated multi-suction-cup grasping. It introduces, for the first time, a reinforcement learning–based dynamic suction-cup configuration strategy that overcomes physical constraints of single-cup systems, enabling reactive, adaptive grasping under severe occlusion and stacking. Contribution/Results: Experiments show a 22.86% improvement in pick-up success rate over baseline methods. The system reliably localizes and grasps fully occluded objects, retrieves objects in complex poses, and maintains robust operation even when one suction cup fails entirely. This work establishes a novel, reliable, and adaptive end-effector paradigm for high-density warehouse robotics.

Technology Category

• Intelligent Robots: Manipulation
• Search and Optimization: Learning to Search
• Planning, Routing, and Scheduling: Learning for Planning and Scheduling

Application Category

• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking
• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Systems and Infrastructure for Web, Mobile and WoT: Energy management for devices in mobile Web and WoT environments

Abstract

Warehouse robotic systems equipped with vacuum grippers must reliably grasp a diverse range of objects from densely packed shelves. However, these environments present significant challenges, including occlusions, diverse object orientations, stacked and obstructed items, and surfaces that are difficult to suction. We introduce etra, a novel vacuum-based grasping strategy featuring four suction cups mounted on linear actuators. Each actuator is equipped with an optical time-of-flight (ToF) proximity sensor, enabling reactive grasping. We evaluate etra in a warehouse-style setting, demonstrating its ability to manipulate objects in stacked and obstructed configurations. Our results show that our RL-based policy improves picking success in stacked-object scenarios by 22.86% compared to a single-suction gripper. Additionally, we demonstrate that TetraGrip can successfully grasp objects in scenarios where a single-suction gripper fails due to physical limitations, specifically in two cases: (1) picking an object occluded by another object and (2) retrieving an object in a complex scenario. These findings highlight the advantages of multi-actuated, suction-based grasping in unstructured warehouse environments. The project website is available at: href{https://tetragrip.github.io/}{https://tetragrip.github.io/}.

Problem

• Reliable grasping of diverse objects in cluttered warehouse environments.
• Overcoming occlusions and difficult surfaces with multi-suction grippers.
• Improving picking success in stacked and obstructed object scenarios.

Innovation

• Four suction cups on linear actuators
• Optical ToF sensors for reactive grasping
• RL-based policy improves picking success