Zobrazeno 1 - 10
of 49
pro vyhledávání: '"Chou, Glen"'
We propose a method for improving the prediction accuracy of learned robot dynamics models on out-of-distribution (OOD) states. We achieve this by leveraging two key sources of structure often present in robot dynamics: 1) sparsity, i.e., some compon
Externí odkaz:
http://arxiv.org/abs/2403.12245
Gradient-based methods enable efficient search capabilities in high dimensions. However, in order to apply them effectively in offline optimization paradigms such as offline Reinforcement Learning (RL) or Imitation Learning (IL), we require a more ca
Externí odkaz:
http://arxiv.org/abs/2306.14079
Autor:
Chou, Glen, Tedrake, Russ
We present a method for synthesizing dynamic, reduced-order output-feedback polynomial control policies for control-affine nonlinear systems which guarantees runtime stability to a goal state, when using visual observations and a learned perception m
Externí odkaz:
http://arxiv.org/abs/2304.12405
To make robots accessible to a broad audience, it is critical to endow them with the ability to take universal modes of communication, like commands given in natural language, and extract a concrete desired task specification, defined using a formal
Externí odkaz:
http://arxiv.org/abs/2303.08006
We present a method for providing statistical guarantees on runtime safety and goal reachability for integrated planning and control of a class of systems with unknown nonlinear stochastic underactuated dynamics. Specifically, given a dynamics datase
Externí odkaz:
http://arxiv.org/abs/2212.06874
We present a motion planning algorithm for a class of uncertain control-affine nonlinear systems which guarantees runtime safety and goal reachability when using high-dimensional sensor measurements (e.g., RGB-D images) and a learned perception modul
Externí odkaz:
http://arxiv.org/abs/2206.06553
We propose a method for learning constraints represented as Gaussian processes (GPs) from locally-optimal demonstrations. Our approach uses the Karush-Kuhn-Tucker (KKT) optimality conditions to determine where on the demonstrations the constraint is
Externí odkaz:
http://arxiv.org/abs/2112.04612
We present a method for contraction-based feedback motion planning of locally incrementally exponentially stabilizable systems with unknown dynamics that provides probabilistic safety and reachability guarantees. Given a dynamics dataset, our method
Externí odkaz:
http://arxiv.org/abs/2104.08695
We present a method for learning to satisfy uncertain constraints from demonstrations. Our method uses robust optimization to obtain a belief over the potentially infinite set of possible constraints consistent with the demonstrations, and then uses
Externí odkaz:
http://arxiv.org/abs/2011.04141
We present a method for feedback motion planning of systems with unknown dynamics which provides probabilistic guarantees on safety, reachability, and goal stability. To find a domain in which a learned control-affine approximation of the true dynami
Externí odkaz:
http://arxiv.org/abs/2010.08993