World Modeling for Autonomous Wheel Loaders
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2023
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911891441319936 |
|---|---|
| author | Aoshima, Koji Fälldin, Arvid Wadbro, Eddie Servin, Martin |
| author_facet | Aoshima, Koji Fälldin, Arvid Wadbro, Eddie Servin, Martin |
| contents | This paper presents a method for learning world models for wheel loaders performing automatic loading actions on a pile of soil. Data-driven models were learned to output the resulting pile state, loaded mass, time, and work for a single loading cycle given inputs that include a heightmap of the initial pile shape and action parameters for an automatic bucket-filling controller. Long-horizon planning of sequential loading in a dynamically changing environment is thus enabled as repeated model inference. The models, consisting of deep neural networks, were trained on data from 3D multibody dynamics simulation of over 10,000 random loading actions in gravel piles of different shapes. The accuracy and inference time for predicting the loading performance and the resulting pile state were, on average, 95% in 1.2 ms and 97% in 4.5 ms, respectively. Long-horizon predictions were found feasible over 40 sequential loading actions. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2309_12016 |
| institution | arXiv |
| publishDate | 2023 |
| record_format | arxiv |
| spellingShingle | World Modeling for Autonomous Wheel Loaders Aoshima, Koji Fälldin, Arvid Wadbro, Eddie Servin, Martin Robotics This paper presents a method for learning world models for wheel loaders performing automatic loading actions on a pile of soil. Data-driven models were learned to output the resulting pile state, loaded mass, time, and work for a single loading cycle given inputs that include a heightmap of the initial pile shape and action parameters for an automatic bucket-filling controller. Long-horizon planning of sequential loading in a dynamically changing environment is thus enabled as repeated model inference. The models, consisting of deep neural networks, were trained on data from 3D multibody dynamics simulation of over 10,000 random loading actions in gravel piles of different shapes. The accuracy and inference time for predicting the loading performance and the resulting pile state were, on average, 95% in 1.2 ms and 97% in 4.5 ms, respectively. Long-horizon predictions were found feasible over 40 sequential loading actions. |
| title | World Modeling for Autonomous Wheel Loaders |
| topic | Robotics |
| url | https://arxiv.org/abs/2309.12016 |