DOA: A Degeneracy Optimization Agent With Adaptive Pose Compensation Capability Based on Deep Reinforcement Learning
Yanbin Li, Canran Xiao, Hongyang He, Shenghai Yuan, Zong Ke, Jiajie Yu, Zixiong Qin, Zhiguo Zhang, Wenzheng Chi, Wei Zhang · IEEE Transactions on Industrial Electronics · 2026
Particle filter-based simultaneous localization and mapping (2-D-SLAM) is widely used in indoor localization tasks due to its efficiency. However, indoor environments such as long straight corridors can cause severe degeneracy problems in SLAM. In this article, we propose a new paradigm of degeneracy optimization and demonstrate its effectiveness through mathematical analysis and extensive experiments. We use proximal policy optimization (PPO) Schulman to train an adaptive degeneracy optimization agent (DOA) to address degeneracy problem. We propose a systematic methodology to address three critical challenges in traditional supervised learning frameworks: 1) data acquisition bottlenecks in degenerate dataset; 2) inherent quality deterioration of training samples; and 3) ambiguity in annotation rules design. And we design a specialized reward function to guide the agent in developing perception capabilities for degenerate environments. Using the output degeneracy factor as reference, the agent can dynamically adjust the process of sensor fusion in pose optimization. Specifically, the observation distribution is shifted towards the motion distribution, with the step size determined by a linear interpolation formula related to the degeneracy factor. In addition, we employ a transfer learning module to endow the agent with generalization capabilities across different environments and address the inefficiency of training in degenerate environments. Finally, we conduct ablation studies to demonstrate the rationality of our model design and the role of transfer learning. We also compare the proposed DOA with state-of-the-art (SOTA) methods to prove its superior degeneracy detection and optimization capabilities across various environments.