Zobrazeno 1 - 10
of 23
pro vyhledávání: '"Gandhi, Manan"'
This paper introduces a new C++/CUDA library for GPU-accelerated stochastic optimization called MPPI-Generic. It provides implementations of Model Predictive Path Integral control, Tube-Model Predictive Path Integral Control, and Robust Model Predict
Externí odkaz:
http://arxiv.org/abs/2409.07563
We introduce the notion of importance sampling under embedded barrier state control, titled Safety Controlled Model Predictive Path Integral Control (SC-MPPI). For robotic systems operating in an environment with multiple constraints, hard constraint
Externí odkaz:
http://arxiv.org/abs/2303.03441
This paper proposes embedded Gaussian Process Barrier States (GP-BaS), a methodology to safely control unmodeled dynamics of nonlinear system using Bayesian learning. Gaussian Processes (GPs) are used to model the dynamics of the safety-critical syst
Externí odkaz:
http://arxiv.org/abs/2212.00268
This work explores the nature of augmented importance sampling in safety-constrained model predictive control problems. When operating in a constrained environment, sampling based model predictive control and motion planning typically utilizes penalt
Externí odkaz:
http://arxiv.org/abs/2204.05963
A reinforcement learning (RL) policy trained in a nominal environment could fail in a new/perturbed environment due to the existence of dynamic variations. Existing robust methods try to obtain a fixed policy for all envisioned dynamic variation scen
Externí odkaz:
http://arxiv.org/abs/2106.02249
Autor:
Wang, Ziyi, So, Oswin, Gibson, Jason, Vlahov, Bogdan, Gandhi, Manan S., Liu, Guan-Horng, Theodorou, Evangelos A.
In this paper, we provide a generalized framework for Variational Inference-Stochastic Optimal Control by using thenon-extensive Tsallis divergence. By incorporating the deformed exponential function into the optimality likelihood function, a novel T
Externí odkaz:
http://arxiv.org/abs/2104.00241
In this paper we propose a novel decision making architecture for Robust Model Predictive Path Integral control (RMPPI) and investigate its performance guarantees and applicability to off-road navigation. Key building blocks of the proposed architect
Externí odkaz:
http://arxiv.org/abs/2102.09027
Many neural networks use the tanh activation function, however when given a probability distribution as input, the problem of computing the output distribution in neural networks with tanh activation has not yet been addressed. One important example
Externí odkaz:
http://arxiv.org/abs/1806.09431
Trajectory optimization of a controlled dynamical system is an essential part of autonomy, however many trajectory optimization techniques are limited by the fidelity of the underlying parametric model. In the field of robotics, a lack of model knowl
Externí odkaz:
http://arxiv.org/abs/1702.04800
Autor:
Gandhi, Manan
In complex engineered systems, completing an objective is sometimes not enough. The system must be able to reach a set performance characteristic, such as an unmanned aerial vehicle flying from point A to point B, \textit{under 10 seconds}. This intr
Externí odkaz:
http://arxiv.org/abs/1506.00731