Compliant Grasping Control for a Tactile Self-Sensing Soft Gripper

Area of Science:

• Robotics
• Mechatronics
• Sensing Technology

Background:

• Soft grippers offer passive compliance for adaptive grasping but struggle with fragile objects.
• Precise force sensing and control are essential for nondestructive grasping with soft grippers.
• Existing soft gripper technologies require enhanced force control for delicate tasks.

Purpose of the Study:

• To develop an online learning, self-tuning nonlinearity impedance controller for a tactile self-sensing soft gripper.
• To achieve accurate and precise grasping force control for soft robotic grippers.
• To enhance the safety and effectiveness of soft grippers in handling delicate or fragile objects.

Main Methods:

• A liquid lens-based optical tactile sensing unit was integrated into a two-finger soft gripper for force sensing.
• An impedance controller based on the Hammerstein nonlinear model was designed for force control.
• Adaptive laws utilizing adaptive theory and online sequential extreme learning machine were employed for parameter tuning.

Main Results:

• The tactile sensing unit demonstrated rapid response time, high sensitivity, good resolution, and linearity.
• The proposed force controller exhibited accurate grasping force control and robustness in nonlinear environments.
• The controller's online learning capability allowed for real-time parameter adjustment.

Conclusions:

• The developed controller enables precise force control in soft grippers, overcoming limitations of passive compliance.
• The system's real-time, adaptive nature and simple structure show significant potential for various grasping applications.
• This technology is well-suited for delicate tasks such as biological sample collection and industrial product sorting.