Insect-inspired AI for autonomous robots

GCHE de Croon, JJG Dupeyroux, SB Fuller… - Science robotics, 2022 - science.org
Autonomous robots are expected to perform a wide range of sophisticated tasks in complex,
unknown environments. However, available onboard computing capabilities and algorithms …

Control of human gait stability through foot placement

SM Bruijn, JH Van Dieën - Journal of The Royal Society …, 2018 - royalsocietypublishing.org
During human walking, the centre of mass (CoM) is outside the base of support for most of
the time, which poses a challenge to stabilizing the gait pattern. Nevertheless, most of us are …

Caterpillar-inspired soft crawling robot with distributed programmable thermal actuation

S Wu, Y Hong, Y Zhao, J Yin, Y Zhu - Science Advances, 2023 - science.org
Many inspirations for soft robotics are from the natural world, such as octopuses, snakes,
and caterpillars. Here, we report a caterpillar-inspired, energy-efficient crawling robot with …

Real-world humanoid locomotion with reinforcement learning

I Radosavovic, T ** and perching in arboreal environments
WRT Roderick, MR Cutkosky, D Lentink - Science Robotics, 2021 - science.org
Birds take off and land on a wide range of complex surfaces. In contrast, current robots are
limited in their ability to dynamically grasp irregular objects. Leveraging recent findings on …

Human-in-the-loop optimization of exoskeleton assistance during walking

J Zhang, P Fiers, KA Witte, RW Jackson… - Science, 2017 - science.org
Exoskeletons and active prostheses promise to enhance human mobility, but few have
succeeded. Optimizing device characteristics on the basis of measured human performance …

Multi-receptor skin with highly sensitive tele-perception somatosensory

Y Du, P Shen, H Liu, Y Zhang, L Jia, X Pu, F Yang… - Science …, 2024 - science.org
The limitations and complexity of traditional noncontact sensors in terms of sensitivity and
threshold settings pose great challenges to extend the traditional five human senses. Here …

Verifiable reinforcement learning via policy extraction

O Bastani, Y Pu… - Advances in neural …, 2018 - proceedings.neurips.cc
While deep reinforcement learning has successfully solved many challenging control tasks,
its real-world applicability has been limited by the inability to ensure the safety of learned …