Massive Parallel Deep Reinforcement Learning for Active SLAM

Abstract

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.

Figures (6)

• Figure 1: Parallel DRL training with 750 robots (cyan). The proposed pipeline leverages NVIDIA Isaac Sim/Lab for Active SLAM training in a GPU-accelerated environment.
• Figure 2: Overview of the proposed uncertainty-aware Active SLAM framework.
• Figure 3: Isaac Sim/Lab testing environments. Env. 2 and Env. 3 were recreated following placed2020deep. Env. 4 was taken from nvidia_isaacsim_env_assets_4_5_0.
• Figure 4: Training curves of our pipeline using $750$ parallel agents in environment \ref{['framework']}. This figure shows that tens of millions of ASLAM training timesteps can be achieved in a few hours with our pipeline.
• Figure 5: Correlation between RMSE (estimated pose - GT) and $U_t$. This graph was computed in Environment $1$.