Embodied Executable Policy Learning with Language-based Scene Summarization

J Qiu, M Xu, W Han, S Moon, D Zhao - arXiv preprint arXiv:2306.05696, 2023 - arxiv.org
Large Language models (LLMs) have shown remarkable success in assisting robot learning
tasks, ie, complex household planning. However, the performance of pretrained LLMs …

Automatic Loading of Unknown Material with a Wheel Loader Using Reinforcement Learning

D Eriksson, R Ghabcheloo… - 2024 IEEE International …, 2024 - ieeexplore.ieee.org
Loading multiple different materials with wheel loaders is a challenging task because
various materials require different loading techniques. It's, therefore, difficult to find a single …

[PDF][PDF] Towards Multiple Material Loading for Wheel Loaders Using Transfer Learning

D Eriksson, R Ghabcheloo, M Geimer - 2023 - trepo.tuni.fi
Automatic bucket filling is an important puzzle piece in reducing the impact of labor shortage
in the construction industry by lowering the learning curve for new operators and reducing …

Optimizing a Bucket Filling Strategy for Wheel Loaders Inside a Dream Environment

D Eriksson, M Geimer - Marcus, Optimizing a Bucket Filling Strategy for … - papers.ssrn.com
Reinforcement Learning (RL) requires many interactions with the environment to converge
to an optimal strategy, which makes it unfeasible to apply to wheel loaders and the bucket …