Realizing Safe and Robust Autonomy through Exploitable Compliance
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 robot systems, where rigid components forgo mechanical responses that are used by biological systems to increase robustness under contact. In contrast, soft robots add back in that compliance through flexible materials and structures, allowing them to safely contact and comply with the environment. These new mechanical responses from compliance demand new approaches to planning high-level behaviors, especially for long time horizon tasks. Current feasible models struggle to accurately account for the continuous deformation and complex physical interaction, and many high-level planning methods make assumptions which compound this struggle, avoiding contact and assuming precision control.
To create systems which can safely and robustly interact with the complexities of the world, we need designs that can actively leverage compliance to improve task performance and algorithms that can create plans which exploit that intrinsic mechanical intelligence. This proposal seeks new co-design approaches which center contact and compliance and mix computational and mechanical responses to revolutionize robot design and control.
Start Date
January 2026
Postdoc Qualifications
Experience with hardware experimentation and simulation-to-real transfer
Expertise in simulation and modeling, preferably soft body simulation and contact modeling
PhD in relevant field, e.g., Mechanical Engineering, Computer Science, or Robotics
Collaborative spirit, interdisciplinary mindset, and passion for communication and mentoring
Co-Advisors
Laura H. Blumenschein, lhblumen@purdue.edu, Mechanical Engineering, https://engineering.purdue.edu/ME/People/ptProfile?resource_id=241064
Zachary Kingston, zkingston@purdue, Computer Science, https://www.cs.purdue.edu/people/faculty/zkingsto.html
Bibliography
L. Chen, Y. Gao, S. Wang, F. Fuentes, L. H. Blumenschein, and Z. Kingston. “Physics-grounded differentiable simulation for soft growing robots”. In: 2025 IEEE 8th International Conference on Soft Robotics(RoboSoft). IEEE. 2025, pp. 1–8
F. Fuentes, S. Diagne, Z. Kingston, and L. H. Blumenschein. “Exteroception through Proprioception Sensing through Improved Contact Modeling for Soft Growing Robots”. In: arXiv preprint arXiv:2507.10694 (2025)
S. Wang and L. H. Blumenschein. “Refined Modeling for Serial Pneumatic Artificial Muscles Enables Model-Based Actuation Design”. In: 2024 IEEE 7th International Conference on Soft Robotics (RoboSoft). IEEE 2024, pp. 800–807
J. D. Greer, L. H. Blumenschein, R. Alterovitz, E. W. Hawkes, and A. M. Okamura. “Robust navigation of a soft growing robot by exploiting contact with the environment”. In: The International Journal of Robotics Research 39.14 (2020), pp. 1724–1738
C. Quintero-Pena, W. Thomason, Z. Kingston, A. Kyrillidis, and L. E. Kavraki. “Stochastic Implicit Neural Signed Distance Functions for Safe Motion Planning under Sensing Uncertainty”. In: 2024 IEEE Inter- national Conference on Robotics and Automation (ICRA). IEEE. 2024, pp. 2360–2367