An Underactuated Robotic Gripper with Flowability and Variable Stiffness for Food Bin-Picking
YITONG XUE, Zhongkui Wang
AI summary
Problem
Automating food bin-picking is challenging due to soft, easily damaged items and cluttered piles that cause sensitivity to positioning errors and unintended contact damage. Existing soft grippers often still rely on precise sensing and control to avoid damaging surrounding objects.
Approach
The gripper uses highly compliant, beaded fingers that passively slip into gaps to avoid disturbing nearby items, then a single motor increases tendon tension to stiffen the fingers for secure, low-damage lifting.
Key results
- 97.1% grasping success rate across seven diverse food items
- Monotonic stiffness tuning achieved through single-thread tension control
- Vibration settling time reduced from 1.7 s to 0.4 s during high-speed motion
- Single-motor mechanism successfully integrates grasp closure and stiffness modulation
Why it matters
Provides a low-cost, sensor-light solution for reliable automation of delicate food handling in unstructured agricultural and processing environments.
Abstract
This paper presents a single-motor underactuated gripper with variable stiffness, designed for food bin-picking tasks. The gripper employs highly compliant fingers that can passively adapt to cluttered environments and enclose target objects. Upon grasping, tendon-driven actuation increases struc- tural stiffness, enabling low-damage, error-tolerant manipulation. Experiments on a variety of food items demonstrate robust grasping performance and stable object handling.