Tensegrity robots navigate complex terrain with learned contact-aware control
Model Predictive Control of Tensegrity Robots via Contact-Aware Graph Neural Dynamics Model
Robotics
Summary
Tensegrity robots can move over rough ground but are hard to control because their movements depend on tricky contacts with the environment. The authors developed a new control method that uses a special AI model called a graph neural network to better understand these contacts, including bumps and obstacles. This model helps the robot predict how it will move and plan its path more accurately. They tested their method in simulations with many obstacles and found it worked better than older methods, helping the robot move more smoothly and reliably.
What this means in practice
- •For robotics engineers: Enable robots with flexible structures to better navigate uneven, obstacle-filled environments using learned contact-aware control models.
- •For robotics software developers: Develop predictive control software that integrates learned dynamics models with motion primitives to improve robot maneuverability in complex terrain.
Authors
Nelson Chen, Patrick Meng, Charles Tang, Angelina Degay, Zachary Brei, Rebecca Kramer-Bottiglio, Kostas E. Bekris, Mridul Aanjaneya
Abstract
Tensegrity robots offer lightweight, compliant mobility over challenging terrain but remain difficult to model and control due to complex contact-rich dynamics and partial observability. This work presents a model predictive path integral (MPPI) controller for a three-bar tensegrity robot driven by a learned graph neural network (GNN) dynamics model. This work first extends prior GNN-based models with a differentiable contact detection module. The extension allows the dynamics model to reason over non-horizontal planar terrains, obstacles, as well as self-collisions. Then, the learned dynamics model and the MPPI controller operate in a closed data-collection loop, iteratively improving model accuracy and control performance. This work further introduces a hybrid MPPI strategy that combines MPPI with turning motion primitives to improve maneuverability. Experiments are performed in MuJoCo across five navigation tasks, which include, wall obstacles, inclines, narrow corridors, low-clearance structures, and a composite 3D obstacle course. The experiments demonstrate that the hybrid MPPI controller operating over the learned GNN dynamics model improves predictive accuracy over a flat-ground baseline model and achieves superior navigation performance compared to $A^*$-based re-planning and MPPI-only variants. Results show that the contact-aware learned dynamics combined with the sampling-based model predictive control enable robust tensegrity navigation in complex, contact-rich environments.