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

TL;DR

TetraGrip addresses the challenge of reliable suction-based grasping in cluttered warehouse scenes by introducing a four-suction gripper with independent linear actuators and ToF proximity sensing for real-time, reactive control. The system combines low-latency onboard computation on a Jetson platform, a multi-sensor fusion strategy, and a PPO-based reinforcement learning policy to handle stacked and obstructed objects, outperforming single-suction baselines by $22.86\%$ in stacked scenarios. Key contributions include the hardware design, sensing-enabled suction cups, and an RL policy capable of adapting to occlusions and complex layouts, demonstrated through real-world experiments and simulations. The work shows the practicality of sensor-driven, multi-actuated grasping in unstructured warehouses, with implications for more reliable bin-picking and order-fulfillment tasks in industry.

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 \tetra, 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 \tetra 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/}.

Figures (12)

• Figure 1: (Left) TetraGrip picking an item from an industrial warehouse shelf. (Right) TetraGrip Picking an item from a stacked object scene in simulation.
• Figure 2:
• Figure 3:
• Figure 5: Objects used in experiments
• Figure 6: TetraGrip success rate for complex geometries.