Gino Brunner

About

Gino Brunner’s research lies at the intersection of deep reinforcement learning, robotics, and spatial navigation. His most influential work focuses on teaching machines to read 2D maps and navigate complex 3D environments—a task that challenges even humans. In his 2018 paper, "Teaching a Machine to Read Maps With Deep Reinforcement Learning" (38 citations), Brunner demonstrated how an agent could learn to localize itself and plan paths using only a map and visual input, a breakthrough for autonomous systems in robotics and AI. His earlier 2017 paper (16 citations) laid the groundwork for this approach, showing that deep reinforcement learning could bridge the gap between abstract map representations and real-world navigation. These contributions have advanced the field of embodied AI, with implications for autonomous vehicles, drones, and assistive robots. Brunner’s work is notable for its practical focus on solving a core challenge in robotics—reliable navigation without GPS—and has been cited by researchers exploring map-based reasoning and reinforcement learning in complex environments. His research continues to inspire efforts to make machines more spatially aware and autonomous.

Research Focus

Key Achievements

Top Papers

1. 1
   Teaching a Machine to Read Maps With Deep Reinforcement Learning

   38 citations · 2018
2. 2
   Teaching a Machine to Read Maps with Deep Reinforcement Learning

   16 citations · 2017

Key Collaborators

Contact & Links