Kirk Hovell

About

Kirk Hovell is a leading researcher at the intersection of aerospace engineering and artificial intelligence, specializing in autonomous spacecraft operations, robotic capture, and deep reinforcement learning (DRL). His work addresses the critical unsolved challenge of enabling manipulator-equipped chaser spacecraft to autonomously capture uncooperative or spinning target space debris—a prerequisite for on-orbit servicing and debris removal. Hovell’s major contributions include pioneering the use of DRL-based guidance systems for real-time, computationally lightweight spacecraft capture. His most-cited paper, “Laboratory Experimentation of Spacecraft Robotic Capture Using Deep-Reinforcement-Learning–Based Guidance” (2022, 15 citations), provides the first experimental validation of DRL for this task. His 2025 work, “Optimal Capture of Spinning Spacecraft via Deep Learning Vision and Guidance” (4 citations), further advances the field by integrating pseudospectral optimization with deep learning for robust, real-time control of spinning targets. Hovell’s doctoral thesis (2022, 3 citations) laid the foundational framework for these innovations. With a growing citation impact, his research is shaping the future of autonomous space robotics, offering scalable solutions for debris mitigation and satellite servicing.

Research Focus

Key Achievements

Top Papers

1. 1
   Laboratory Experimentation of Spacecraft Robotic Capture Using Deep-Reinforcement-Learning–Based Guidance

   15 citations · 2022
2. 2
   Optimal Capture of Spinning Spacecraft via Deep Learning Vision and Guidance

   4 citations · 2025
3. 3
   Deep Reinforcement Learning as Guidance for Aerospace Robotics

   3 citations · 2022

Key Collaborators

Contact & Links