Active Robotic Mapping through Deep Reinforcement Learning
This work addresses efficient mapping for robotics, but it is incremental as it builds on prior exploration methods with slight improvements.
The paper tackles the problem of active robotic mapping by training an agent with deep reinforcement learning to map environments quickly, achieving performance slightly better than a near-optimal myopic exploration scheme in a simulated Disaster Mapping scenario.
We propose an approach to learning agents for active robotic mapping, where the goal is to map the environment as quickly as possible. The agent learns to map efficiently in simulated environments by receiving rewards corresponding to how fast it constructs an accurate map. In contrast to prior work, this approach learns an exploration policy based on a user-specified prior over environment configurations and sensor model, allowing it to specialize to the specifications. We evaluate the approach through a simulated Disaster Mapping scenario and find that it achieves performance slightly better than a near-optimal myopic exploration scheme, suggesting that it could be useful in more complicated problem scenarios.