Massive Parallel Deep Reinforcement Learning for Active SLAM
For researchers in robotics and SLAM, this work addresses the scalability bottleneck of DRL-based Active SLAM, enabling faster experimentation and more realistic scenarios.
The paper proposes a scalable end-to-end deep reinforcement learning framework for Active SLAM that enables massively parallel training, reducing training time and supporting continuous action spaces. Compared to state-of-the-art methods, it achieves significant speedups in training while maintaining competitive performance.
Recent advances in parallel computing and GPU acceleration have created new opportunities for computation-intensive learning problems such as Active SLAM -- where actions are selected to reduce uncertainty and improve joint mapping and localization. However, existing DRL-based approaches remain constrained by the lack of scalable parallel training. In this work, we address this challenge by proposing a scalable end-to-end DRL framework for Active SLAM that enables massively parallel training. Compared with the state of the art, our method significantly reduces training time, supports continuous action spaces and facilitates the exploration of more realistic scenarios. It is released as an open-source framework to promote reproducibility and community adoption.