Modular robot design optimization with generative adversarial networks

J Hu, J Whitman, M Travers… - … Conference on Robotics …, 2022 - ieeexplore.ieee.org
simulations in Pybullet [21]. We evaluate our method by querying them with randomly sampled
terrains and simulating … of the generated designs in simulation. We conducted all training …

Evolution and morphogenesis of simulated modular robots: a comparison between a direct and generative encoding

F Veenstra, A Faina, S Risi, K Stoy - … , The Netherlands, April 19-21, 2017 …, 2017 - Springer
… use of powerful generative encodings, here we investigate how a generative encoding and
… in modular robots when the number of robotic modules changes. Simulating less modules …

Learning to simulate dynamic environments with gamegan

SW Kim, Y Zhou, J Philion… - Proceedings of the …, 2020 - openaccess.thecvf.com
Simulation is a crucial component of any robotic system. In … In this paper, we aim to learn
a simulator by simply watching … We introduce GameGAN, a generative model that learns to …

Appgan: Generative adversarial networks for generating robot approach behaviors into small groups of people

F Yang, C Peters - … IEEE International Conference on Robot …, 2019 - ieeexplore.ieee.org
… to navigate a robot for engaging a group of people. Claudio et al. [17] simulate approaching
… that may impact robot behaviors, such as human orientations and robot approach distances. …

Lifelike agility and play in quadrupedal robots using reinforcement learning and generative pre-trained models

L Han, Q Zhu, J Sheng, C Zhang, T Li… - Nature Machine …, 2024 - nature.com
… At the imitation learning stage in simulation, we have compared the proposed VQ-PMC
method with β-VAE based motor controllers. At the current stage, we continue to investigate the …

Enhancing construction robot learning for collaborative and long-horizon tasks using generative adversarial imitation learning

R Li, Z Zou - Advanced Engineering Informatics, 2023 - Elsevier
… Imitation Learning (GAIL), have been proposed to learn … (VR) integrated robot control
approach to control robots for long-… Our study was implemented purely in simulation, assuming …

Generative modeling of autonomous robots and their environments using reservoir computing

EA Antonelo, B Schrauwen… - Neural Processing …, 2007 - Springer
… The data (from distance and color sensors, and actuator) collected from the robot simulator
are used to train and test reservoir networks in a Matlab environment using the RCToolbox1 […

Bridging the gap between simulation and reality using generative neural networks

NR Cruz Brunet - 2021 - repositorio.uchile.cl
… the simulation-toreality gap in the robotic soccer environment using generative neural networks
to transform simulated … When training and testing machine learning models with images …

Generalization through simulation: Integrating simulated and real data into deep reinforcement learning for vision-based autonomous flight

K Kang, S Belkhale, G Kahn, P Abbeel… - … conference on robotics …, 2019 - ieeexplore.ieee.org
… world robot learning using generalization through simulation. … and simulation can serve
complementary functions for robot … [9] generative model is trained on the simulated image data. …

[HTML][HTML] Model-driven processes and tools to design robot-based generative learning objects for computer science education

V Štuikys, R Burbaitė, K Bespalova… - Science of Computer …, 2016 - Elsevier
… In this paper, we introduce a methodology to design robot-oriented generative learning
objects (GLOs) that are, in fact, heterogeneous meta-programs to teach computer science (CS) …