Nikola Jovičić
Union University, School of Computing
Knez Mihailova 6/VI, 11000 Belgrade, Serbia
E-mail: jovicicnikola@outlook.com
Robotica & Management, Vol. 26, No. 2, pp. 16-21
DOI: https://doi.org/10.24193/rm.2021.2.3
Abstract: In this paper, a system for autonomous navigation of unmapped forest paths in a simulation, along with a new simulator for testing and training it is presented. For navigation, it uses a combination of path planning and deep neural networks trained with imitation learning.
Keywords: imitation learning, forest, deep learning, simulation, path planning.
References
[1] Giusti A. et al.: “A Machine Learning Approach to Visual Perception of Forest Trails for Mobile Robots,” in IEEE Robotics and Automation Letters, vol. 1, no. 2, pp. 661-667, July 2016.
[2] Smolyanskiy N. et al.: “Toward Low-Flying Autonomous MAV Trail Navigation using Deep Neural Networks for Environmental Awareness”, IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4241-4247, 2017.
[3] Ghamry, et al.: “Cooperative Forest Monitoring and Fire Detection Using a Team of UAVs-UGVs”, in ICUAS, 2016.
[4] Pierzchała M. et al.: “Mapping forests using an unmanned ground vehicle with 3D LiDAR and graph-SLAM”, in Computers and Electronics in Agriculture, Volume 145, 2018.
[5] Chisholm R. et al.: “UAV LiDAR for below-canopy forest surveys”, in Journal of Unmanned Vehicle Systems 01(01):61-68, December 2013.
[6] Mohan M. et al.: “UAV-Supported Forest Regeneration: Current Trends, Challenges and Implications”, in Remote Sensing, 2021.
[7] Bojarski M. et al “End to End Learning for Self-Driving Cars”, in arXiv preprint arXiv:1604.07316, 2016.
[8] Grigorescu S. “Embedded Vision for Self-Driving on Forest Roads”. on CVPR, Workshop on Embedded Vision, 2021.
[9] Osa T. et al “An algorithmic perspective on imitation learning”, in Foundations and Trends in Robotics, 2018.
[10] He K et al “Deep residual learning for image recognition”, 2015.
[11] Agarap, A. F. “Deep Learning using Rectified Linear Units (ReLU)”, 2018.
[12] Paszk A. et al “PyTorch: An Imperative Style, High-Performance Deep Learning Library”, 2019.
[13] Diederik P. K., Ba J. “Adam: A Method for Stochastic Optimization”, in 3rd International Conference for Learning Representations, 2015.
[14] Wang K. et al “Approaches, Challenges, and Applications for Deep Visual Odometry: Toward to Complicated and Emerging Areas”, in IEEE Transactions on Cognitive and Developmental Systems, 2020.
[15] Jovičić N.: “Automated unmapped forest path navigation of mobile rover using neural networks”, video file, November 2021, retrieved from https://youtu.be/nr6jNAzg1TQ