Zobrazeno 1 - 10
of 14
pro vyhledávání: '"Cleac'h, Simon Le"'
Autor:
Brüdigam, Jan, Abbas, Ali-Adeeb, Sorokin, Maks, Fang, Kuan, Hung, Brandon, Guru, Maya, Sosnowski, Stefan, Wang, Jiuguang, Hirche, Sandra, Cleac'h, Simon Le
Robotic manipulation is challenging due to discontinuous dynamics, as well as high-dimensional state and action spaces. Data-driven approaches that succeed in manipulation tasks require large amounts of data and expert demonstrations, typically from
Externí odkaz:
http://arxiv.org/abs/2408.01258
Autor:
Cleac'h, Simon Le, Schwager, Mac, Manchester, Zachary, Sindhwani, Vikas, Florence, Pete, Singh, Sumeet
We present a differentiable formulation of rigid-body contact dynamics for objects and robots represented as compositions of convex primitives. Existing optimization-based approaches simulating contact between convex primitives rely on a bilevel form
Externí odkaz:
http://arxiv.org/abs/2212.06764
Autor:
Cleac'h, Simon Le, Yu, Hong-Xing, Guo, Michelle, Howell, Taylor A., Gao, Ruohan, Wu, Jiajun, Manchester, Zachary, Schwager, Mac
We present a differentiable pipeline for simulating the motion of objects that represent their geometry as a continuous density field parameterized as a deep network. This includes Neural Radiance Fields (NeRFs), and other related models. From the de
Externí odkaz:
http://arxiv.org/abs/2210.09420
We present a new solver for non-convex trajectory optimization problems that is specialized for robotics applications. CALIPSO, or the Conic Augmented Lagrangian Interior-Point SOlver, combines several strategies for constrained numerical optimizatio
Externí odkaz:
http://arxiv.org/abs/2205.09255
Autor:
Howell, Taylor A., Cleac'h, Simon Le, Brüdigam, Jan, Kolter, J. Zico, Schwager, Mac, Manchester, Zachary
We present Dojo, a differentiable physics engine for robotics that prioritizes stable simulation, accurate contact physics, and differentiability with respect to states, actions, and system parameters. Dojo achieves stable simulation at low sample ra
Externí odkaz:
http://arxiv.org/abs/2203.00806
Autor:
Howell, Taylor A., Cleac'h, Simon Le, Singh, Sumeet, Florence, Pete, Manchester, Zachary, Sindhwani, Vikas
We present a framework for bi-level trajectory optimization in which a system's dynamics are encoded as the solution to a constrained optimization problem and smooth gradients of this lower-level problem are passed to an upper-level trajectory optimi
Externí odkaz:
http://arxiv.org/abs/2109.04928
Autor:
Cleac'h, Simon Le, Howell, Taylor, Yang, Shuo, Lee, Chi-Yen, Zhang, John, Bishop, Arun, Schwager, Mac, Manchester, Zachary
We present a general approach for controlling robotic systems that make and break contact with their environments. Contact-implicit model predictive control (CI-MPC) generalizes linear MPC to contact-rich settings by utilizing a bi-level planning for
Externí odkaz:
http://arxiv.org/abs/2107.05616
Dynamic games are an effective paradigm for dealing with the control of multiple interacting actors. This paper introduces ALGAMES (Augmented Lagrangian GAME-theoretic Solver), a solver that handles trajectory-optimization problems with multiple acto
Externí odkaz:
http://arxiv.org/abs/2104.08452
Existing game-theoretic planning methods assume that the robot knows the objective functions of the other agents a priori while, in practical scenarios, this is rarely the case. This paper introduces LUCIDGames, an inverse optimal control algorithm t
Externí odkaz:
http://arxiv.org/abs/2011.08152
Managing uncertainty is a fundamental and critical issue in spacecraft entry guidance. This paper presents a novel approach for uncertainty propagation during entry, descent and landing that relies on a new sum-of-squares robust verification techniqu
Externí odkaz:
http://arxiv.org/abs/2011.02441