Deep Learning Enabled Perception and Decision Making for Autonomous Robots
Download PDFAbstract
This chapter explores the transformative impact of deep learning on the fields of perception and decision-making in autonomous robots. We provide a comprehensive overview of the foundational concepts, recent advancements, and practical applications of deep learning models that enable robots to perceive their environment and make intelligent decisions. The chapter delves into the core methodologies, including Convolutional Neural Networks (CNNs) for visual perception and Reinforcement Learning (RL) for autonomous control. We discuss the challenges in developing robust and reliable autonomous systems, such as the need for large-scale annotated datasets, the complexity of real-world environments, and the importance of safe and ethical decision-making. Furthermore, we present a proposed methodology that integrates advanced deep learning architectures for enhanced perception and decision-making capabilities. The results and discussion section showcases the performance of our proposed model on a selected dataset, highlighting its effectiveness in complex scenarios. Finally, we conclude with a summary of the key findings and a discussion of future research directions in this rapidly evolving field.
References
- ZhaoYang Dong and Tianjing Wang. “Artificial intelligence driving perception, cognition, decision-making and deduction in energy systems: State-of-the-art and potential directions”. In: Energy Internet 1.1 (2024), pp. 27–33.
- Jingyuan Zhao et al. “A survey of autonomous driving from a deep learning perspective”. In: ACM Computing Surveys 57.10 (2025), pp. 1–60.
- Stanislav Hristov Ivanov. “Automated decision-making”. In: foresight 25.1 (2023), pp. 4–19.
- Afia Maham and Dur E Nayab Tashfa. “Deep Learning Perspective of Scene Understanding in Autonomous Robots”. In: arXiv preprint arXiv:2512.14020 (2025).
- Jianjun Ni et al. “Deep learning-based scene understanding for autonomous robots: A survey”. In: Intelligence & Robotics 3.3 (2023), pp. 374–401.
- Jia Guo et al. “Convolutional neural network-based robot control for an eye-in-hand camera”. In: IEEE Transactions on Systems, Man, and Cybernetics: Systems 53.8 (2023), pp. 4764–4775.
- Sergey Kulik and Alexander Shtanko. “Using convolutional neural networks for recognition of objects varied in appearance in computer vision for intellectual robots”. In: Procedia Computer Science 169 (2020), pp. 164–167.
- Ravi Raj and Andrzej Kos. “An extensive study of convolutional neural networks: Applications in computer vision for improved robotics perceptions”. In: Sensors 25.4 (2025), p. 1033.
- Badri Raj Lamichhane, Gun Srijuntongsiri, and Teerayut Horanont. “CNN based 2D object detection techniques: A review”. In: Frontiers in Computer Science 7 (2025), p. 1437664.
- Joan Alvarado et al. “Cocoa Monilia Data Set: A cocoa pod dataset to detect and classify Monilia roreri in real conditions”. In: Data in Brief (2026), p. 112447.
- Andreas Geiger, Philip Lenz, and Raquel Urtasun. “Are we ready for autonomous driving? the kitti vision benchmark suite”. In: 2012 IEEE conference on computer vision and pattern recognition. IEEE. 2012, pp. 3354–3361.
- Hamid Taheri, Seyed Rasoul Hosseini, and Mohammad Ali Nekoui. “Deep reinforcement learning with enhanced ppo for safe mobile robot navigation”. In: arXiv preprint arXiv:2405.16266 (2024).
Deep Learning: Foundations, Advances, and Intelligent Applications
