Quadcopter Guidance Law Design using Deep Reinforcement Learning

Aydinli S. U., KUTAY A. T.

10th International Conference on Recent Advances in Air and Space Technologies, RAST 2023, İstanbul, Türkiye, 7 - 09 Haziran 2023 identifier identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Doi Numarası: 10.1109/rast57548.2023.10197848
  • Basıldığı Şehir: İstanbul
  • Basıldığı Ülke: Türkiye
  • Anahtar Kelimeler: deep reinforcement learning, guidance law, model predictive control, pro-portional navigation
  • Orta Doğu Teknik Üniversitesi Adresli: Evet

Özet

This paper examines the quadcopter-target inter-ception problem and proposes a deep reinforcement learning-based approach to solve this problem. The quadcopter-target interception problem is formulated by constructing an Markov Decision Process (MDP) which consist of states, possible actions, transition probabilities and real-valued reward function. The relative position, velocity and angle information between the quadcopter and the target is used when the agent selects the appropriate actions to intercept the target. Permissible acceleration commands are defined as the action space and closing velocity is used in the definition of real-valued reward function. The proposed algorithm is compared with the True Proportional Navigation (TPN) and Model Predictive Control (MPC) algorithms. Numerical simulation results confirm that proposed approach is a suitable solution for the quadcopter guidance problem.