Zobrazeno 1 - 10
of 239
pro vyhledávání: '"Manchester, Ian"'
We propose a novel layer-wise parameterization for convolutional neural networks (CNNs) that includes built-in robustness guarantees by enforcing a prescribed Lipschitz bound. Each layer in our parameterization is designed to satisfy a linear matrix
Externí odkaz:
http://arxiv.org/abs/2410.22258
Autor:
Bartlett, Tara, Manchester, Ian R.
This paper presents an algorithm that finds a centroidal motion and footstep plan for a Spring-Loaded Inverted Pendulum (SLIP)-like bipedal robot model substantially faster than real-time. This is achieved with a novel representation of the dynamic f
Externí odkaz:
http://arxiv.org/abs/2409.09939
Autor:
Abood, Damian, Manchester, Ian R.
We present a sample-based motion planning algorithm specialised to a class of underactuated systems using path parameterisation. The structure this class presents under a path parameterisation enables the trivial computation of dynamic feasibility al
Externí odkaz:
http://arxiv.org/abs/2409.05278
This paper presents a study of robust policy networks in deep reinforcement learning. We investigate the benefits of policy parameterizations that naturally satisfy constraints on their Lipschitz bound, analyzing their empirical performance and robus
Externí odkaz:
http://arxiv.org/abs/2405.11432
In this paper, we introduce a novel class of neural differential equation, which are intrinsically Lyapunov stable, exponentially stable or passive. We take a recently proposed Polyak Lojasiewicz network (PLNet) as an Lyapunov function and then param
Externí odkaz:
http://arxiv.org/abs/2404.12554
In this paper, we extend the control contraction metrics (CCM) approach, which was originally proposed for the universal tracking control of nonlinear systems, to those that evolves on Lie groups. Our idea is to view the manifold as a constrained set
Externí odkaz:
http://arxiv.org/abs/2403.15264
This paper presents a new bi-Lipschitz invertible neural network, the BiLipNet, which has the ability to smoothly control both its Lipschitzness (output sensitivity to input perturbations) and inverse Lipschitzness (input distinguishability from diff
Externí odkaz:
http://arxiv.org/abs/2402.01344
Autor:
Yi, Bowen, Manchester, Ian R.
The inertial measurement unit (IMU) preintegration approach nowadays is widely used in various robotic applications. In this article, we revisit the preintegration theory and propose a novel interpretation to understand it from a nonlinear observer p
Externí odkaz:
http://arxiv.org/abs/2307.04165
This paper introduces a new linear parameterization to the problem of visual inertial simultaneous localization and mapping (VI-SLAM) -- without any approximation -- for the case only using information from a single monocular camera and an inertial m
Externí odkaz:
http://arxiv.org/abs/2306.12723
Neural networks are typically sensitive to small input perturbations, leading to unexpected or brittle behaviour. We present RobustNeuralNetworks.jl: a Julia package for neural network models that are constructed to naturally satisfy a set of user-de
Externí odkaz:
http://arxiv.org/abs/2306.12612