Robotic Hand Mechatronics

Dexterity Through Mechanical Intelligence

Robotic hands typically achieve dexterity by increasing actuation inputs, which in turn demands additional sensing and control complexity. This talk presents an alternative path: embedding task-relevant intelligence directly into the mechanical structure. I will introduce the PhaseHand, a sequentially underactuated robotic hand that passively transitions among power, tripod, and pinch grasps through its transmission architecture and joint design. I will discuss the underlying design principles and show how phase-based mechanisms can expand the versatility of low-cost manipulators while minimizing control requirements. 

Generation of DLR Robotic Hands

Designing Robust Soft Hands: From Synergies and Compliance to Real-World Applications

Soft and underactuated robotic hands offer a promising approach to robust manipulation in real-world environments, where objects, tasks, and interaction conditions are often uncertain. By exploiting mechanical compliance, adaptive morphology, and synergistic actuation, these systems can simplify control while improving safety, versatility, and resilience.

In this talk, I will discuss the mechatronic design principles behind robust soft hands, drawing from the development of synergy-based robotic and prosthetic platforms such as the Pisa/IIT SoftHand and related systems. The talk will focus on how design choices involving compliance, underactuation, sensing, and control affect the trade-off between simplicity, dexterity, robustness, and usability.

I will also discuss how these principles translate into real-world applications, including robotic manipulation, prosthetic hands, assistive technologies, and soft end-effectors for uncertain environments. The aim is to highlight soft hand mechatronics as an integrated design problem, where morphology, actuation, sensing, and control must be co-designed to move from laboratory prototypes toward reliable and deployable robotic systems. 

Design of Variable Stiffness Grippers for Handling Delicate Products

Towards Dexterous Manipulation with Soft Prosthetic Hands

Embodied Mechanical Intelligence in Gripper Design

Robotic manipulation in cluttered and constrained environments is often addressed by increasing the complexity of perception, planning, and learning algorithms. 

The talk presents a complementary perspective: designing grippers whose morphology embeds part of the intelligence required for manipulation.

The talk will first introduce how passive compliance and mechanical design can turn environmental constraints into useful resources for robust grasping. This principle will then be demonstrated in a learning-based decluttering scenario, used as an application case to show how gripper design can simplify the manipulation problem. 

Within this scenario, a soft–rigid gripper is compared with conventional rigid and soft grippers to investigate how morphology influences learning.

The results show that an appropriate gripper design can physically embed useful interaction strategies into the grasping action itself, enabling effective decluttering strategies to be learned with a simpler action space.

Inventing Robotic Hand Mechanisms

Conventional omnidirectional wheel mechanisms are limited in their ability to climb steps and cross gaps. The Omni-Ball, consisting of two connected hemispherical wheels, overcomes these limitations by enabling the crossing of higher obstacles and larger gaps than previously. By elongating the Omni-Ball longitudinally into a cylinder shape, we obtained the Omni-Crawler, which enables omnidirectional mobility on rough terrain. In addition, transforming the cylinder shape into a torus with inner-outer membrane motion not only enables robotic mobility in murky water, but makes it possible to further transition from Omni-Crawler to Omni-Gripper. Conventional soft grippers are not suitable for objects with sharp sections such as broken valves and glass shards, but the torus shape solves this problem by using a three-layered variable stiffness skin-bag made of cut-resistant cloth. A similar function could also be achieved using a string of beads made of titanium which can grip objects of almost any shape, even when they are on fire.