Krishna Dev Kumar

Toronto Metropolitan University

Papers

3

Total Citations

6

H-Index

2

About

Krishna Dev Kumar is at the forefront of autonomous space operations, specializing in reinforcement learning and optimization-based motion planning for on-orbit assembly. His research tackles one of the most challenging problems in modern space exploration: enabling spacecraft to autonomously construct large structures in orbit without human intervention. Kumar’s major contributions include developing a reinforcement-learning-based continuation strategy that overcomes the extreme sensitivity of optimal control solvers to initial guesses—a critical bottleneck in autonomous assembly. He also introduced a novel convex optimization approach for collision avoidance that transforms traditionally non-convex, non-differentiable constraints into tractable problems, avoiding the conservatism of prior methods. Though his most-cited works are recent (2024–2025), they have already garnered attention, with his flagship paper on reinforcement learning for on-orbit assembly accumulating 3 citations in its first year. This work represents a significant step toward enabling long-term space colonization and large-scale orbital infrastructure. Kumar’s innovative fusion of machine learning and optimal control positions him as an emerging leader in autonomous space robotics, with his methods poised to underpin future missions requiring in-space manufacturing and assembly.

Research Focus

Key Achievements

2
H-Index
3
Papers
6
Total Citations
2
Avg Citations/Paper
🏆 Most Cited Paper
A Reinforcement Learning-Based Continuation Strategy for Autonomous On-Orbit Assembly
3 citations · 2024
📈 Most Prolific Year: 2024 (2 Papers)
🤝 Key Collaborators: 3
🏛 Institutions: Toronto Metropolitan University

Top Papers

  1. 1
  2. 2
  3. 3

Key Collaborators

Contact & Links

Available for collaboration
Content generated · 13 days ago