Abstract
We present MIDGARD, a simulation platform based on Unreal Engine for training autonomous robots in complex outdoor unstructured environments. It offers photorealistic 3D scenes, procedural scene generation, and integration with ROS and OpenAI Gym. The focus of MIDGARD is on navigation, where an autonomous agent travels from random initial positions to designated target locations avoiding obstacles, enabling researchers to develop and evaluate novel algorithms and navigation methods. We evaluate MIDGARD’s suitability as a research tool by training navigation algorithms based on reinforcement learning; we also assess sim-to-real transfer capabilities in a traversable horizon prediction task, using deep learning models on RGB images only.
MIDGARD builds and docs are available at www.midgardsim.org.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
“Kingdom of mankind”, i.e., Earth, in Norse mythology.
- 2.
The agent has been trained for 2,500 steps with an update of 80 epochs at each step. The initial learning rate for the actor was 0.0003 and 0.001 for the critic.
References
Dosovitskiy, A., Ros, G., Codevilla, F., Lopez, A., Koltun, V.: Carla: an open urban driving simulator. arXiv:1711.03938 (2017)
BeamNG GmbH. BeamNG.tech. https://www.beamng.tech/
Thomas, D., Woodall, W., Fernandez, E.: Next-generation ROS: building on DDS. In: ROSCon Chicago 2014. Open Robotics, Mountain View (2014)
Brockman, G., et al.: OpenAI gym. arXiv:1606.01540 (2016)
Raffin, A., Hill, A., Gleave, A., Kanervisto, A., Ernestus, M., Dormann, N.: Stable-baselines3: reliable reinforcement learning implementations. J. Mach. Learn. Res. 22(268), 1–8 (2021)
Schulman, J., Wolski, F., Dhariwal, P., Radford, A., Klimov, O.: Proximal policy optimization algorithms. arXiv:1707.06347 (2017)
Haarnoja, T., Zhou, A., Abbeel, P., Levine, S.: Soft actor-critic: off-policy maximum entropy deep reinforcement learning with a stochastic actor. In: ICML (2018)
Palazzo, S., et al.: Domain adaptation for outdoor robot traversability estimation from RGB data with safety-preserving loss. In: IEEE IROS (2020)
Acknowledgement
G. Muscato, C. Spampinato and F. Cancelliere acknowledge financial support from PNRR MUR project PE0000013-FAIR.
D. C. Guastella acknowledges support by the project PON R&I REACT-EU.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Vecchio, G. et al. (2024). MIDGARD: A Robot Navigation Simulator for Outdoor Unstructured Environments. In: Secchi, C., Marconi, L. (eds) European Robotics Forum 2024. ERF 2024. Springer Proceedings in Advanced Robotics, vol 32. Springer, Cham. https://doi.org/10.1007/978-3-031-76424-0_22
Download citation
DOI: https://doi.org/10.1007/978-3-031-76424-0_22
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-76423-3
Online ISBN: 978-3-031-76424-0
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)