Project Description

Contact, manipulation, and touch are core capabilities that define how biological systems experience the world: friction, pressure, and force all inform behavior, and we exploit these features to understand the world and achieve complicated tasks. However, these capabilities are often out of reach for many robot systems, particularly manipulators, which are typically rigid. In contrast, soft robots are made out of intrinsically malleable and flexible materials, allowing them to safely contact and comply with the environment intrinsically. However, this compliance also means that planning high-level behaviors for soft robots remains a complicated tasks: feasible models struggle to accurately account for the continuous deformation and complex physical interaction, and unmodeled environmental factors can further influence the behavior. Moreover, many high- level planning methods make assumptions native to rigid systems: contact is avoided, control is precise, and environments are well-modeled. Algorithms that alleviate these assumptions do not exploit the core capability of soft systems: their intrinsic mechanical intelligence.
This proposal seeks to co-design mechanisms and methods. By designing algorithms with assumptions of mechanically intelligent interaction from the start, systems can be designed with their output in mind, guiding design mechanically to have beneficial properties to exploit and an algorithm to exploit them. 

Start Date

Jan-March 2025 

Postdoc Qualifications

1) Strong background in planning, modeling, control, or design
2) Ph.D. in relevant field, e.g., Mechanical Engineering, Computer Science, or Robotics
3) Collaborative spirit, interdisciplinary mindset, and passion for communi- cation and mentoring 

Co-advisors

Laura Blumenschein, School of Mechanical Engineering
lhblumen@purdue.edu
https://engineering.purdue.edu/raad

Zachary Kingston, Department of Computer Science
zkingston@purdue.edu

Bibliography