Zobrazeno 1 - 10
of 6 945
pro vyhledávání: '"Posner P"'
We present a diffusion-based approach to quadrupedal locomotion that simultaneously addresses the limitations of learning and interpolating between multiple skills and of (modes) offline adapting to new locomotion behaviours after training. This is t
Externí odkaz:
http://arxiv.org/abs/2411.08832
Causal structures play a central role in world models that flexibly adapt to changes in the environment. While recent works motivate the benefits of discovering local causal graphs for dynamics modelling, in this work we demonstrate that accurately c
Externí odkaz:
http://arxiv.org/abs/2411.06890
Beyond the Sun-Earth line, spacecraft equipped with various solar telescopes are intended to be deployed at several different vantage points in the heliosphere to carry out coordinated, multi-view observations of the Sun and its dynamic activities. I
Externí odkaz:
http://arxiv.org/abs/2408.04208
Autor:
Newbury, Rhys, Collins, Jack, He, Kerry, Pan, Jiahe, Posner, Ingmar, Howard, David, Cosgun, Akansel
Differentiable simulators continue to push the state of the art across a range of domains including computational physics, robotics, and machine learning. Their main value is the ability to compute gradients of physical processes, which allows differ
Externí odkaz:
http://arxiv.org/abs/2407.05560
Autor:
Han, Chaeyeon, Seshadri, Pavan, Ding, Yiwei, Posner, Noah, Koo, Bon Woo, Agrawal, Animesh, Lerch, Alexander, Guhathakurta, Subhrajit
While various sensors have been deployed to monitor vehicular flows, sensing pedestrian movement is still nascent. Yet walking is a significant mode of travel in many cities, especially those in Europe, Africa, and Asia. Understanding pedestrian volu
Externí odkaz:
http://arxiv.org/abs/2406.09998
Autor:
Mitchell, Alexander L., Merkt, Wolfgang, Papatheodorou, Aristotelis, Havoutis, Ioannis, Posner, Ingmar
The current state-of-the-art in quadruped locomotion is able to produce a variety of complex motions. These methods either rely on switching between a discrete set of skills or learn a distribution across gaits using complex black-box models. Alterna
Externí odkaz:
http://arxiv.org/abs/2405.19452
We present COmpetitive Mechanisms for Efficient Transfer (COMET), a modular world model which leverages reusable, independent mechanisms across different environments. COMET is trained on multiple environments with varying dynamics via a two-step pro
Externí odkaz:
http://arxiv.org/abs/2404.15109
Mastering dexterous robotic manipulation of deformable objects is vital for overcoming the limitations of parallel grippers in real-world applications. Current trajectory optimisation approaches often struggle to solve such tasks due to the large sea
Externí odkaz:
http://arxiv.org/abs/2403.12861
3D scene understanding for robotic applications exhibits a unique set of requirements including real-time inference, object-centric latent representation learning, accurate 6D pose estimation and 3D reconstruction of objects. Current methods for scen
Externí odkaz:
http://arxiv.org/abs/2402.16308
World models are a powerful tool for developing intelligent agents. By predicting the outcome of a sequence of actions, world models enable policies to be optimised via on-policy reinforcement learning (RL) using synthetic data, i.e. in "in imaginati
Externí odkaz:
http://arxiv.org/abs/2312.08533