Bridging the Sim-to-Real Gap with Bayesian Inference
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2024
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866909301883273216 |
|---|---|
| author | Rothfuss, Jonas Sukhija, Bhavya Treven, Lenart Dörfler, Florian Coros, Stelian Krause, Andreas |
| author_facet | Rothfuss, Jonas Sukhija, Bhavya Treven, Lenart Dörfler, Florian Coros, Stelian Krause, Andreas |
| contents | We present SIM-FSVGD for learning robot dynamics from data. As opposed to traditional methods, SIM-FSVGD leverages low-fidelity physical priors, e.g., in the form of simulators, to regularize the training of neural network models. While learning accurate dynamics already in the low data regime, SIM-FSVGD scales and excels also when more data is available. We empirically show that learning with implicit physical priors results in accurate mean model estimation as well as precise uncertainty quantification. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system. Using model-based RL, we demonstrate a highly dynamic parking maneuver with drifting, using less than half the data compared to the state of the art. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2403_16644 |
| institution | arXiv |
| publishDate | 2024 |
| record_format | arxiv |
| spellingShingle | Bridging the Sim-to-Real Gap with Bayesian Inference Rothfuss, Jonas Sukhija, Bhavya Treven, Lenart Dörfler, Florian Coros, Stelian Krause, Andreas Robotics Machine Learning We present SIM-FSVGD for learning robot dynamics from data. As opposed to traditional methods, SIM-FSVGD leverages low-fidelity physical priors, e.g., in the form of simulators, to regularize the training of neural network models. While learning accurate dynamics already in the low data regime, SIM-FSVGD scales and excels also when more data is available. We empirically show that learning with implicit physical priors results in accurate mean model estimation as well as precise uncertainty quantification. We demonstrate the effectiveness of SIM-FSVGD in bridging the sim-to-real gap on a high-performance RC racecar system. Using model-based RL, we demonstrate a highly dynamic parking maneuver with drifting, using less than half the data compared to the state of the art. |
| title | Bridging the Sim-to-Real Gap with Bayesian Inference |
| topic | Robotics Machine Learning |
| url | https://arxiv.org/abs/2403.16644 |