More Like this

1. Learning Differentiable Tensegrity Dynamics using Graph Neural Networks

   Chen, N; Wang, K; Johnson_III, W; Kramer-Bottiglio, R; Bekris, Kostas E; Aanjaneya, M (November 2024, Conference on Robot Learning (CoRL))

   Tensegrity robots are composed of rigid struts and flexible cables. They constitute an emerging class of hybrid rigid-soft robotic systems and are promising systems for a wide array of applications, ranging from locomotion to assembly. They are difficult to control and model accurately, however, due to their compliance and high number of degrees of freedom. To address this issue, prior work has introduced a differentiable physics engine designed for tensegrity robots based on first principles. In contrast, this work proposes the use of graph neural networks to model contact dynamics over a graph representation of tensegrity robots, which leverages their natural graph-like cable connectivity between end caps of rigid rods. This learned simulator can accurately model 3-bar and 6-bar tensegrity robot dynamics in simulation-to-simulation experiments where MuJoCo is used as the ground truth. It can also achieve higher accuracy than the previous differentiable engine for a real 3-bar tensegrity robot, for which the robot state is only partially observable. When compared against direct applications of recent mesh-based graph neural network simulators, the proposed approach is computationally more efficient, both for training and inference, while achieving higher accuracy. Code and data are available at https://github.com/nchen9191/tensegrity_gnn_simulator_public 

   more » « less
2. Learning Differentiable Tensegrity Dynamics using Graph Neural Networks

   Chen, N; Wang, K; Johnson_III, W; Kramer-Bottiglio, R; Bekris, Kostas E; Aanjaneya, M (November 2024, Conference on Robot Learning (CoRL))

   Tensegrity robots are composed of rigid struts and flexible cables. They constitute an emerging class of hybrid rigid-soft robotic systems and are promising systems for a wide array of applications, ranging from locomotion to assembly. They are difficult to control and model accurately, however, due to their compliance and high number of degrees of freedom. To address this issue, prior work has introduced a differentiable physics engine designed for tensegrity robots based on first principles. In contrast, this work proposes the use of graph neural networks to model contact dynamics over a graph representation of tensegrity robots, which leverages their natural graph-like cable connectivity between end caps of rigid rods. This learned simulator can accurately model 3-bar and 6-bar tensegrity robot dynamics in simulation-to-simulation experiments where MuJoCo is used as the ground truth. It can also achieve higher accuracy than the previous differentiable engine for a real 3-bar tensegrity robot, for which the robot state is only partially observable. When compared against direct applications of recent mesh-based graph neural network simulators, the proposed approach is computationally more efficient, both for training and inference, while achieving higher accuracy. Code and data are available at https://github.com/nchen9191/tensegrity_gnn_simulator_public 

   more » « less
3. Learning Differentiable Tensegrity Dynamics using Graph Neural Networks

   Chen, N; Wang, K; Johnson_III, W; Kramer-Bottiglio, R; Bekris, Kostas E; Aanjaneya, M (November 2024, Conference on Robot Learning (CoRL))

   Tensegrity robots are composed of rigid struts and flexible cables. They constitute an emerging class of hybrid rigid-soft robotic systems and are promising systems for a wide array of applications, ranging from locomotion to assembly. They are difficult to control and model accurately, however, due to their compliance and high number of degrees of freedom. To address this issue, prior work has introduced a differentiable physics engine designed for tensegrity robots based on first principles. In contrast, this work proposes the use of graph neural networks to model contact dynamics over a graph representation of tensegrity robots, which leverages their natural graph-like cable connectivity between end caps of rigid rods. This learned simulator can accurately model 3-bar and 6-bar tensegrity robot dynamics in simulation-to-simulation experiments where MuJoCo is used as the ground truth. It can also achieve higher accuracy than the previous differentiable engine for a real 3-bar tensegrity robot, for which the robot state is only partially observable. When compared against direct applications of recent mesh-based graph neural network simulators, the proposed approach is computationally more efficient, both for training and inference, while achieving higher accuracy. Code and data are available at https://github.com/nchen9191/tensegrity_gnn_simulator_public 

   more » « less
4. 6N-DoF Pose Tracking for Tensegrity Robots

   https://doi.org/10.1007/978-3-031-25555-7_10  

   Lu, S.; Johnson, W.; Wang, K.; Huang, X.; Booth, J.; Kramer-Bottiglio, R.; Bekris, K. E. (January 2022, International Symposium on Robotics Research (ISRR))

   Tensegrity robots, which are composed of compressive elements (rods) and flexible tensile elements (e.g., cables), have a variety of advantages, including flexibility, low weight, and resistance to mechanical impact. Nevertheless, the hybrid soft-rigid nature of these robots also complicates the ability to localize and track their state. This work aims to address what has been recognized as a grand challenge in this domain, i.e., the state estimation of tensegrity robots through a markerless, vision-based method, as well as novel, onboard sensors that can measure the length of the robot's cables. In particular, an iterative optimization process is proposed to track the 6-DoF pose of each rigid element of a tensegrity robot from an RGB-D video as well as endcap distance measurements from the cable sensors. To ensure that the pose estimates of rigid elements are physically feasible, i.e., they are not resulting in collisions between rods or with the environment, physical constraints are introduced during the optimization. Real-world experiments are performed with a 3-bar tensegrity robot, which performs locomotion gaits. Given ground truth data from a motion capture system, the proposed method achieves less than 1~cm translation error and 3 degrees rotation error, which significantly outperforms alternatives. At the same time, the approach can provide accurate pose estimation throughout the robot's motion, while motion capture often fails due to occlusions. 

   more » « less
5. Robots that Can Survive the Egg Drop

   https://doi.org/10.3389/frym.2024.1452937  

   Johnson, William R; Kramer-Bottiglio, Rebecca (November 2024, Frontiers for Young Minds)

   If you ever did the egg drop challenge, you know it is hard to build something that can protect a fragile egg from crashing into the ground and breaking. Engineers are building soft robots called tensegrity robots, which are designed to survive harsh crashes. The word tensegrity comes from “tension” and “integrity”. It means the robot is made of stiff bars held together with stretchy cables. This flexible structure helps a tensegrity robot absorb the impact from crashes. Someday, these robots might be used to explore dangerous places like deep caves or other planets. These robots could fall off cliffs or into craters. Right now, engineers are making tensegrity robots better and easier to control. In this article, we will explain how tensegrity robots work. We will discuss their advantages, their disadvantages, and what they can be used for. 

   more » « less