Zobrazeno 1 - 8
of 8
pro vyhledávání: '"Rodriguez, Ivan Dario Jimenez"'
Autor:
Csomay-Shanklin, Noel, Compton, William D., Rodriguez, Ivan Dario Jimenez, Ambrose, Eric R., Yue, Yisong, Ames, Aaron D.
We study the design of robust and agile controllers for hybrid underactuated systems. Our approach breaks down the task of creating a stabilizing controller into: 1) learning a mapping that is invariant under optimal control, and 2) driving the actua
Externí odkaz:
http://arxiv.org/abs/2409.06125
Autor:
Compton, William, Rodriguez, Ivan Dario Jimenez, Csomay-Shanklin, Noel, Yue, Yisong, Ames, Aaron D.
Stabilizing underactuated systems is an inherently challenging control task due to fundamental limitations on how the control input affects the unactuated dynamics. Decomposing the system into actuated (output) and unactuated (zero) coordinates provi
Externí odkaz:
http://arxiv.org/abs/2408.14749
Forward invariance is a long-studied property in control theory that is used to certify that a dynamical system stays within some pre-specified set of states for all time, and also admits robustness guarantees (e.g., the certificate holds under pertu
Externí odkaz:
http://arxiv.org/abs/2210.16940
The weight, space, and power limitations of small aerial vehicles often prevent the application of modern control techniques without significant model simplifications. Moreover, high-speed agile behavior, such as that exhibited in drone racing, make
Externí odkaz:
http://arxiv.org/abs/2207.05220
This work presents Neural Gaits, a method for learning dynamic walking gaits through the enforcement of set invariance that can be refined episodically using experimental data from the robot. We frame walking as a set invariance problem enforceable v
Externí odkaz:
http://arxiv.org/abs/2204.08120
We propose a method for training ordinary differential equations by using a control-theoretic Lyapunov condition for stability. Our approach, called LyaNet, is based on a novel Lyapunov loss formulation that encourages the inference dynamics to conve
Externí odkaz:
http://arxiv.org/abs/2202.02526
Autor:
Silva, Andrew, Killian, Taylor, Rodriguez, Ivan Dario Jimenez, Son, Sung-Hyun, Gombolay, Matthew
Publikováno v:
Proceedings of the Twenty Third International Conference on Artificial Intelligence and Statistics 2020, 1855-1865
Decision trees are ubiquitous in machine learning for their ease of use and interpretability. Yet, these models are not typically employed in reinforcement learning as they cannot be updated online via stochastic gradient descent. We overcome this li
Externí odkaz:
http://arxiv.org/abs/1903.09338
We present foundations for using Model Predictive Control (MPC) as a differentiable policy class for reinforcement learning in continuous state and action spaces. This provides one way of leveraging and combining the advantages of model-free and mode
Externí odkaz:
http://arxiv.org/abs/1810.13400