Zobrazeno 1 - 10
of 20
pro vyhledávání: '"Gangapurwala, Siddhant"'
Autor:
Campanaro, Luigi, De Martini, Daniele, Gangapurwala, Siddhant, Merkt, Wolfgang, Havoutis, Ioannis
This paper proposes a simple strategy for sim-to-real in Deep-Reinforcement Learning (DRL) -- called Roll-Drop -- that uses dropout during simulation to account for observation noise during deployment without explicitly modelling its distribution for
Externí odkaz:
http://arxiv.org/abs/2304.13150
Publikováno v:
IEEE International Conference on Robotics and Automation (ICRA) 2023
Robotic locomotion is often approached with the goal of maximizing robustness and reactivity by increasing motion control frequency. We challenge this intuitive notion by demonstrating robust and dynamic locomotion with a learned motion controller ex
Externí odkaz:
http://arxiv.org/abs/2209.14887
Training deep reinforcement learning (DRL) locomotion policies often require massive amounts of data to converge to the desired behaviour. In this regard, simulators provide a cheap and abundant source. For successful sim-to-real transfer, exhaustive
Externí odkaz:
http://arxiv.org/abs/2209.12878
Autor:
Mitchell, Alexander L., Merkt, Wolfgang, Geisert, Mathieu, Gangapurwala, Siddhant, Engelcke, Martin, Jones, Oiwi Parker, Havoutis, Ioannis, Posner, Ingmar
Quadruped locomotion is rapidly maturing to a degree where robots are able to realise highly dynamic manoeuvres. However, current planners are unable to vary key gait parameters of the in-swing feet midair. In this work we address this limitation and
Externí odkaz:
http://arxiv.org/abs/2205.01179
Autor:
Mitchell, Alexander L., Merkt, Wolfgang, Geisert, Mathieu, Gangapurwala, Siddhant, Engelcke, Martin, Jones, Oiwi Parker, Havoutis, Ioannis, Posner, Ingmar
Quadruped locomotion is rapidly maturing to a degree where robots now routinely traverse a variety of unstructured terrains. However, while gaits can be varied typically by selecting from a range of pre-computed styles, current planners are unable to
Externí odkaz:
http://arxiv.org/abs/2112.04809
Autor:
Campanaro, Luigi, Gangapurwala, Siddhant, De Martini, Daniele, Merkt, Wolfgang, Havoutis, Ioannis
Central Pattern Generators (CPGs) have several properties desirable for locomotion: they generate smooth trajectories, are robust to perturbations and are simple to implement. Although conceptually promising, we argue that the full potential of CPGs
Externí odkaz:
http://arxiv.org/abs/2102.12891
Autor:
Gangapurwala, Siddhant, Geisert, Mathieu, Orsolino, Romeo, Fallon, Maurice, Havoutis, Ioannis
We present a unified model-based and data-driven approach for quadrupedal planning and control to achieve dynamic locomotion over uneven terrain. We utilize on-board proprioceptive and exteroceptive feedback to map sensory information and desired bas
Externí odkaz:
http://arxiv.org/abs/2012.03094
Autor:
Mitchell, Alexander L., Engelcke, Martin, Jones, Oiwi Parker, Surovik, David, Gangapurwala, Siddhant, Melon, Oliwier, Havoutis, Ioannis, Posner, Ingmar
Traditional approaches to quadruped control frequently employ simplified, hand-derived models. This significantly reduces the capability of the robot since its effective kinematic range is curtailed. In addition, kinodynamic constraints are often non
Externí odkaz:
http://arxiv.org/abs/2007.01520
Deep reinforcement learning (RL) uses model-free techniques to optimize task-specific control policies. Despite having emerged as a promising approach for complex problems, RL is still hard to use reliably for real-world applications. Apart from chal
Externí odkaz:
http://arxiv.org/abs/2002.09676
Akademický článek
Tento výsledek nelze pro nepřihlášené uživatele zobrazit.
K zobrazení výsledku je třeba se přihlásit.
K zobrazení výsledku je třeba se přihlásit.