Arvi Jonnarth
Papers
1
Total Citations
3
H-Index
1
About
Arvi Jonnarth is a researcher advancing the frontier of autonomous robotics through deep reinforcement learning and coverage path planning (CPP). His work addresses the critical challenge of enabling robots to efficiently navigate and cover unknown, confined spaces—a problem with applications spanning robotic lawn mowing, precision agriculture, and search-and-rescue operations. Jonnarth’s most cited paper, "Sim-to-Real Transfer of Deep Reinforcement Learning Agents for Online Coverage Path Planning" (2025, 3 citations), tackles the notorious gap between simulated training environments and real-world deployment. By developing agents that can generalize from simulation to physical robots, he provides a practical pathway for deploying adaptive, online CPP solutions where offline methods fall short. This contribution is particularly impactful because it moves beyond provably complete but rigid offline planning, offering flexibility in dynamic or partially known environments. Jonnarth’s work is a key step toward robust, real-time robotic autonomy, bridging theory and application for next-generation autonomous systems.
Research Focus
Key Achievements
Top Papers
- 1