Tumbling Robot Control Using Reinforcement Learning: An Adaptive Control Policy That Transfers Well to the Real World

A Schwartzwald, M Tlachac, L Guzman… - IEEE Robotics & …, 2022 - ieeexplore.ieee.org
Tumbling robots are simple platforms that are able to traverse large obstacles relative to
their size, at the cost of being difficult to control. Existing control methods apply only a subset …

Optimizing gait libraries via a coverage metric

B Bittner, S Revzen - arXiv preprint arXiv:2107.08775, 2021 - arxiv.org
Many robots move through the world by composing locomotion primitives like steps and
turns. To do so well, robots need not have primitives that make intuitive sense to humans …

Robots made from ice: an analysis of manufacturing techniques

D Carroll, M Yim - 2020 IEEE/RSJ International Conference on …, 2020 - ieeexplore.ieee.org
Modular robotic systems with self-repair or self-replication capabilities have been presented
as a robust, low cost solution to extraterrestrial or Arctic exploration. This paper explores …

Sim-to-real with domain randomization for tumbling robot control

A Schwartzwald… - 2020 IEEE/RSJ …, 2020 - ieeexplore.ieee.org
Tumbling locomotion allows for small robots to traverse comparatively rough terrain,
however, their motion is complex and difficult to control. Existing tumbling robot control …

GREEMA: Proposal and Experimental Verification of Growing Robot by Eating Environmental Material for Landslide Disaster

Y Tsunoda, Y Sato, K Osuka - Journal of Robotics and Mechatronics, 2024 - jstage.jst.go.jp
In areas inaccessible to humans, such as the lunar surface and landslide sites, there is a
need for multiple autonomous mobile robot systems that can replace human workers …

Behaviour Aesthetics of Reinforcement Learning in a Robotic Art Installation

S Audry, R Dumont-Gagné, H Scurto - 4th NeurIPS Workshop on …, 2020 - hal.science
This paper presents our practice with reinforcement learning (RL) in the context of a robotic
art project. We adopted a design-oriented approach to RL, privileging embodied robot …