I am a third year PhD student, co-advised by Professor Mridul Aanjaneya (primary) and Professor Kostas Bekris (secondary). My research is on developing differentiable simulation methods for robotics by combining physics first-principles and machine learning models.
Website: https://nchen9191.github.io/
Publications:
2026 |
Chen, N; Johnson, W; Kramer-Bottiglio, R; Bekris, K; Aanjaneya, M CableRobotGraphSim: A Graph Neural Network for Modeling Partially Observable Cable-Driven Robot Dynamics Inproceedings Learning for Dynamics and Control (L4DC) - Oral Presentation, USC, Los Angeles, CA, 2026. @inproceedings{CableRobotGraphSim_l4dc, title = {CableRobotGraphSim: A Graph Neural Network for Modeling Partially Observable Cable-Driven Robot Dynamics}, author = {N Chen and W Johnson and R Kramer-Bottiglio and K Bekris and M Aanjaneya }, year = {2026}, date = {2026-06-18}, booktitle = {Learning for Dynamics and Control (L4DC) - Oral Presentation}, address = {USC, Los Angeles, CA}, abstract = {General-purpose simulators have accelerated the development of robots. Traditional simulators based on first-principles, however, typically require full-state observability or depend on parameter search for system identification. This work presents CableRobotGraphSim, a novel Graph Neural Network (GNN) model for cable-driven robots that aims to address shortcomings of prior simulation solutions. By representing cable-driven robots as graphs, with the rigid-bodies as nodes and the cables and contacts as edges, this model can quickly and accurately match the properties of other simulation models and real robots, while ingesting only partially observable inputs. Accompanying the GNN model is a sim-and-real co-training procedure that promotes generalization and robustness to noisy real data. This model is further integrated with a Model Predictive Path Integral (MPPI) controller for closed-loop navigation, which showcases the model's speed and accuracy. The code and data can be found at https://github.com/nchen9191/cable-robot-graph-sim.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } General-purpose simulators have accelerated the development of robots. Traditional simulators based on first-principles, however, typically require full-state observability or depend on parameter search for system identification. This work presents CableRobotGraphSim, a novel Graph Neural Network (GNN) model for cable-driven robots that aims to address shortcomings of prior simulation solutions. By representing cable-driven robots as graphs, with the rigid-bodies as nodes and the cables and contacts as edges, this model can quickly and accurately match the properties of other simulation models and real robots, while ingesting only partially observable inputs. Accompanying the GNN model is a sim-and-real co-training procedure that promotes generalization and robustness to noisy real data. This model is further integrated with a Model Predictive Path Integral (MPPI) controller for closed-loop navigation, which showcases the model's speed and accuracy. The code and data can be found at https://github.com/nchen9191/cable-robot-graph-sim. |
Johnson, W; Meng, P; Chen, N; Cimatti, L; Vercoutere, A; Aanjaneya, M; Kramer-Bottiglio, R; Bekris, K An Open-Source, Reproducible Tensegrity Robot that can Navigate Among Obstacles Journal Article IEEE Robotics and Automation Letters (RA-L), 2026. @article{open_source_tensegrity, title = {An Open-Source, Reproducible Tensegrity Robot that can Navigate Among Obstacles}, author = {W Johnson and P Meng and N Chen and L Cimatti and A Vercoutere and M Aanjaneya and R Kramer-Bottiglio and K Bekris }, url = {https://ieeexplore.ieee.org/document/11474858}, year = {2026}, date = {2026-02-05}, journal = {IEEE Robotics and Automation Letters (RA-L)}, abstract = {Tensegrity robots, composed of rigid struts and elastic tendons, provide impact resistance, low mass, and adaptability to unstructured terrain. Their compliance and complex, coupled dynamics, however, present modeling and control challenges, hindering planning and obstacle avoidance. This paper presents a complete, open-source, and reproducible system that enables navigation for a 3-bar tensegrity robot. The system comprises: (i) an inexpensive, open-source hardware design, and (ii) an integrated, open-source software stack for physics-based modeling, system identification, state estimation, path planning, and control. All hardware and software are publicly available at https://sites.google.com/view/tensegrity-navigation/. The proposed system tracks the robot using a static overhead camera and executes collision-free paths to a goal among known obstacle locations. System robustness is demonstrated through experiments involving unmodeled environmental challenges, including a vertical drop, an incline, and granular media, culminating in an outdoor field demonstration. To validate reproducibility, experiments were conducted using robot instances at two different laboratories. This work provides the robotics community with a complete navigation system for a compliant, impact-resistant, and shape-morphing robot. This system is intended to serve as a springboard for advancing the navigation capabilities of other unconventional robotic platforms.}, keywords = {}, pubstate = {published}, tppubtype = {article} } Tensegrity robots, composed of rigid struts and elastic tendons, provide impact resistance, low mass, and adaptability to unstructured terrain. Their compliance and complex, coupled dynamics, however, present modeling and control challenges, hindering planning and obstacle avoidance. This paper presents a complete, open-source, and reproducible system that enables navigation for a 3-bar tensegrity robot. The system comprises: (i) an inexpensive, open-source hardware design, and (ii) an integrated, open-source software stack for physics-based modeling, system identification, state estimation, path planning, and control. All hardware and software are publicly available at https://sites.google.com/view/tensegrity-navigation/. The proposed system tracks the robot using a static overhead camera and executes collision-free paths to a goal among known obstacle locations. System robustness is demonstrated through experiments involving unmodeled environmental challenges, including a vertical drop, an incline, and granular media, culminating in an outdoor field demonstration. To validate reproducibility, experiments were conducted using robot instances at two different laboratories. This work provides the robotics community with a complete navigation system for a compliant, impact-resistant, and shape-morphing robot. This system is intended to serve as a springboard for advancing the navigation capabilities of other unconventional robotic platforms. |
2024 |
Chen, N; Wang, K; Johnson, W; Kramer-Bottiglio, R; Bekris, K; Aanjaneya, M Learning Differentiable Tensegrity Dynamics Using Graph Neural Networks Inproceedings Conference on Robot Learning (CoRL), Munich, Germany, 2024. @inproceedings{Chen:2024aa, title = {Learning Differentiable Tensegrity Dynamics Using Graph Neural Networks}, author = {N Chen and K Wang and W Johnson and R Kramer-Bottiglio and K Bekris and M Aanjaneya}, url = {https://openreview.net/pdf?id=5Awumz1VKU}, year = {2024}, date = {2024-11-01}, booktitle = {Conference on Robot Learning (CoRL)}, address = {Munich, Germany}, abstract = {Tensegrity robots are composed of rigid struts and flexible cables and constitute an emerging class of hybrid rigid-soft robotic systems. They 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 high number of degrees of freedom and compliance. To address this issue, prior works have 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 the natural graph-like cable connectivity between the rod end caps. 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, where the robot state is only being partially observable. When compared against direct applications of recent graph neural network simulators, the proposed approach is computationally more efficient both for training and inference, while achieving higher accuracy.}, keywords = {}, pubstate = {published}, tppubtype = {inproceedings} } Tensegrity robots are composed of rigid struts and flexible cables and constitute an emerging class of hybrid rigid-soft robotic systems. They 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 high number of degrees of freedom and compliance. To address this issue, prior works have 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 the natural graph-like cable connectivity between the rod end caps. 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, where the robot state is only being partially observable. When compared against direct applications of recent graph neural network simulators, the proposed approach is computationally more efficient both for training and inference, while achieving higher accuracy. |