Coordinated crawling via reinforcement learning
Coordinated crawling via reinforcement learning
复制标题
通过强化学习协调爬行
DOI:
10.1098/rsif.2020.0198
复制
发表时间:
2020
影响因子:
3.9
通讯作者:
Mahadevan, L.
中科院分区:
文献类型:
--
作者:
Mishra, Shruti;van Rees, Wim M.;Mahadevan, L.
Rectilinear crawling locomotion is a primitive and common mode of locomotion in slender soft-bodied animals. It requires coordinated contractions that propagate along a body that interacts frictionally with its environment. We propose a simple approach to understand how this coordination arises in a neuromechanical model of a segmented, soft-bodied crawler via an iterative process that might have both biological antecedents and technological relevance. Using a simple reinforcement learning algorithm, we show that an initial all-to-all neural coupling converges to a simple nearest-neighbour neural wiring that allows the crawler to move forward using a localized wave of contraction that is qualitatively similar to what is observed inDrosophila melanogasterlarvae and used in many biomimetic solutions. The resulting solution is a function of how we weight gait regularization in the reward, with a trade-off between speed and robustness to proprioceptive noise. Overall, our results, which embed the brain–body–environment triad in a learning scheme, have relevance for soft robotics while shedding light on the evolution and development of locomotion.
登录
查看更多内容
DOI:
--
发表时间:
--
期刊:
影响因子:
--
作者:
W. Garrey;A. Moore
通讯作者:
A. Moore
影响因子:
9.2
作者:
Darshana Narayanan;A. Ghazanfar
通讯作者:
A. Ghazanfar
影响因子:
4.3
作者:
Loveless, Jane;Lagogiannis, Konstantinos;Webb, Barbara
通讯作者:
Webb, Barbara
DOI:
10.1098/rspb.2014.1092
发表时间:
2014-09-07
影响因子:
4.7
作者:
Paoletti, P.;Mahadevan, L.
通讯作者:
Mahadevan, L.
影响因子:
3.1
作者:
Kohsaka H;Guertin PA;Nose A
通讯作者:
Nose A