Carnegie Mellon University
pmannam_phd_ri_2024.pdf (23.67 MB)

Design Iteration of Dexterous Compliant Robotic Manipulators

Download (23.67 MB)
posted on 2024-01-19, 22:08 authored by Pragna MannamPragna Mannam

 The goal of personal robotics is to have robots in homes performing everyday tasks efficiently to improve our quality of life. Towards this end, manipulators are needed which are low cost, safe around humans, and approach human-level dexterity. However, existing off-the-shelf manipulators are expensive both in cost and manufacturing time, difficult to repair, and unsafe to operate with delicate objects due to rigid components. Soft robotic manipulators, on the other hand, show great promise as their compliance allows them to conform to objects, exhibit physical robustness, and execute safe object interactions, while being low cost through the use of rapid prototyping. However, designing soft robot manipulators is challenging due to their high degrees of freedom and the inherent complexity of modeling soft materials in simulation. This makes it difficult to iterate on the soft manipulator design prior to manufacturing. To this end, this thesis explores a spectrum of approaches to quickly iterate on the design and evaluation of soft hands, in a matter of days, to allow rapid turnaround of real robot hand prototypes. This allows the designer to swiftly assess the performance of the design for tasks in the real world, and inform future design improvements using real-world measurable metrics. We explore various design iter?ation approaches by designing and evaluating two different types of manipulators: a parallel delta manipulator and a tendon-driven anthropomorphic (human-like) hand. 

Delta manipulators have high precision and low inertia, which lend themselves perfectly to performing fine-grained manipulations. However, 3D-printing these manipulators with soft materials leads to non-ideal kinematic behavior. First, we explore iterating on the design of 3D-printed parallelogram links, which are a key component of the delta manipulator, using a human-in-the-loop approach towards achieving close to ideal kinematic behavior. Then, we evaluate a two-fingered 6-DoF delta manipulator, consisting of the designed parallelogram links, using teleoperation in real-world tasks. We demonstrate the compliance and dexterity of our gripper through six dexterous manipulation tasks involving small and delicate objects, such as twisting a grape off a stem.

 Subsequently, this thesis explores design iteration for anthropomorphic soft hands to achieve contact-rich manipulation that enables a wider variety of tasks. Contrary to first designing the manipulator and then evaluating it in the real world, we create a unified design iteration and evaluation framework for a 3D-printed 16-DoF dexterous anthropomorphic soft hand (DASH). We rapidly design and test five iterations of DASH, in a matter of days, by leveraging 3D-printing for fabrication and utilizing teleoperation for evaluation across 30 real-world manipulation tasks. The changes to each successive iteration of DASH is informed by a human designer after observing previous evaluation results. Our final iteration of DASH solves 19 of the 30 tasks compared to Allegro, a popular rigid manipulator on the market, which can only solve 7 tasks. 

Finally, we automate the design iteration process, thereby taking the human outof the loop, in order to explore a larger design space.  To achieve this, we simulatethe soft hand as a rigid body and use hand evolution methods to transfer control policies across a large set of generated hand designs. Subsequently, we evaluate theoptimized design as a soft tendon-driven hand and show that it solves 23 of the 30 tasks, outperforming our previously iterated hands designs.

This thesis explores techniques for iterative design including rapid prototyping,teleoperation, and simulation to enable designers to tune kinematics and compliancefor dexterous tasks through real robot evaluation. We show that substantial improvements  can  be  made  between  design  iterations  and  over  state  of  the  art  dexterousrobotic hands on dexterity benchmarks.  The key takeaway from our work is thatachieving robot hand dexterity requires detailed attention to hand kinematics andcompliance.   We also observe that a rich suite of tasks involving a variety of objects and using non-binary evaluation metrics can better inform the design iteration process.  The thesis concludes by presenting several avenues for future work in thedesign iteration space.




Degree Type

  • Dissertation


  • Robotics Institute

Degree Name

  • Doctor of Philosophy (PhD)


Jean Oh Nancy Pollard

Usage metrics



    Ref. manager