Abstract
Integration of reinforcement learning with unmanned aerial vehicles (UAVs) to achieve autonomous flight has been an active research area in recent years. An important part focuses on obstacle detection and avoidance for UAVs navigating through an environment. Exploration in an unseen environment can be tackled with Deep Q-Network (DQN). However, value exploration with uniform sampling of actions may lead to redundant states, where often the environments inherently bear sparse rewards. To resolve this, we present two techniques for improving exploration for UAV obstacle avoidance. The first is a convergence-based approach that uses convergence error to iterate through unexplored actions and temporal threshold to balance exploration and exploitation. The second is a guidance-based approach using a Domain Network which uses a Gaussian mixture distribution to compare previously seen states to a predicted next state in order to select the next action. Performance and evaluation of these approaches were implemented in multiple 3-D simulation environments, with variation in complexity. The proposed approach demonstrates a two-fold improvement in average rewards compared to state of the art.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Chavan, R., Gengaje, S.R.: Multiple object detection using GMM technique and tracking using Kalman filter (2017)
Dadi, H., Venkatesh, P., Poornesh, P., Narayana Rao, L., Kumar, N.: Tracking multiple moving objects using gaussian mixture model. Int. J. Soft Comput. Eng. (IJSCE) 3, 114–119 (2013)
Gou, S.Z., Liu, Y.: DQN with model-based exploration: efficient learning on environments with sparse rewards. ArXiv, abs/1903.09295 (2019)
Habibian, S., et al.: Design and implementation of a maxi-sized mobile robot (Karo) for rescue missions. ROBOMECH J. 8(1), 1–33 (2021)
van Hasselt, H., Guez, A., Silver, D.: Deep reinforcement learning with double q-learning. In: Proceedings of the Thirtieth AAAI Conference on Artificial Intelligence, AAAI 2016, pp. 2094–2100. AAAI Press (2016)
Kahn, G., Villaflor, A., Pong, V., Abbeel, P., Levine, S.: Uncertainty-aware reinforcement learning for collision avoidance. ArXiv, abs/1702.01182 (2017)
Lee, H., Jung, S., Shim, D.: Vision-based UAV landing on the moving vehicle, pp. 1–7, 06 2016
Long, P., Fan, T., Liao, X., Liu, W., Zhang, H., Pan, J.: Towards optimally decentralized multi-robot collision avoidance via deep reinforcement learning. 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 6252–6259 (2017)
Ma, Z., Wang, C., Niu, Y., Wang, X., Shen, L.: A saliency-based reinforcement learning approach for a UAV to avoid flying obstacles. Robot. Auton. Syst. 100, 108–118 (2018)
Maimaitijiang, M., Sagan, V., Sidike, P., Hartling, S., Esposito, F., Fritschi, F.B.: Soybean yield prediction from UAV using multimodal data fusion and deep learning. Remote Sens. Environ. 237, 111599 (2020)
Mammadli, R., Wolf, F., Jannesari, A.: The art of getting deep neural networks in shape. ACM Trans. Archit. Code Optim. (TACO) 15(4), 62:1–62:21 (2019)
Masadeh, A.E., Wang, Z., Kamal, A.E.: Convergence-based exploration algorithm for reinforcement learning. Electrical and Computer Engineering Technical Reports and White Papers 1, Iowa State University, Ames, IA (2018)
Michels, J., Saxena, A., Ng, A.Y.: High speed obstacle avoidance using monocular vision and reinforcement learning. In: Proceedings of the 22nd International Conference on Machine Learning, ICML 2005, pp. 593–600. Association for Computing Machinery, New York (2005)
Mnih, V., et al.: Playing Atari with deep reinforcement learning. ArXiv, abs/1312.5602 (2013)
Niaraki, A., Roghair, J., Jannesari, A.: Visual exploration and energy-aware path planning via reinforcement learning (2021)
Oh, J., Guo, X., Lee, H., Lewis, R.L., Singh, S.P.: Action-conditional video prediction using deep networks in Atari games. In: NIPS (2015)
Pathak, D., Agrawal, P., Efros, A.A., Darrell, T.: Curiosity-driven exploration by self-supervised prediction. In: ICML (2017)
Preiss, J.A., Hönig, W., Sukhatme, G.S., Ayanian, N.: Crazyswarm: a large nano-quadcopter swarm. In: 2017 IEEE International Conference on Robotics and Automation (ICRA), pp. 3299–3304 (2017)
Schaul, T., Quan, J., Antonoglou, I., Silver, D.: Prioritized experience replay. CoRR, abs/1511.05952 (2015)
Shah, S., Dey, D., Lovett, C., Kapoor, A.: AirSim: high-fidelity visual and physical simulation for autonomous vehicles. ArXiv, abs/1705.05065 (2017)
Smolyanskiy, N., Kamenev, A., Smith, J., Birchfield, S.T.: Toward low-flying autonomous MAV trail navigation using deep neural networks for environmental awareness. In: 2017 IEEE/RSJ International Conference on Intelligent Robots and Systems (IROS), pp. 4241–4247 (2017)
Subrahmanyam, V., Kim, D., Kumar, C., Shad, S., Jannesari, A.: Efficient object detection model for real-time UAV applications. Comput. Inf. Sci. 14(1) (2021)
Sutton, R.S., Barto, A.G.: Reinforcement Learning: An Introduction, 2nd edn., The MIT Press (2018)
Wang, C., Wang, J., Zhang, X., Zhang, X.: Autonomous navigation of UAV in large-scale unknown complex environment with deep reinforcement learning. In: 2017 IEEE Global Conference on Signal and Information Processing (GlobalSIP), pp. 858–862 (2017)
Wang, Z., Schaul, T., Hessel, M., Hasselt, H., Lanctot, M., Freitas, N.: Dueling network architectures for deep reinforcement learning. arXiv preprint arXiv:1511.06581 (2015)
Xie, L., Wang, S., Markham, A., Trigoni, N.:Towards monocular vision based obstacle avoidance through deep reinforcement learning. In: RSS 2017 workshop on New Frontiers for Deep Learning in Robotics (2017)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2022 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Roghair, J., Niaraki, A., Ko, K., Jannesari, A. (2022). A Vision Based Deep Reinforcement Learning Algorithm for UAV Obstacle Avoidance. In: Arai, K. (eds) Intelligent Systems and Applications. IntelliSys 2021. Lecture Notes in Networks and Systems, vol 294. Springer, Cham. https://doi.org/10.1007/978-3-030-82193-7_8
Download citation
DOI: https://doi.org/10.1007/978-3-030-82193-7_8
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-82192-0
Online ISBN: 978-3-030-82193-7
eBook Packages: Intelligent Technologies and RoboticsIntelligent Technologies and Robotics (R0)