DOA: A Degeneracy Optimization Agent with Adaptive Pose Compensation Capability based on Deep Reinforcement Learning
Preprint
Abstract
Particle filter-based 2D-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 paper, we use Proximal Policy Optimization (PPO) 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 protocol design. We design a specialized reward function to guide the agent in developing perception capabilities for degenerate environments. Using the output degeneracy factor as a reference weight, the agent can dynamically adjust the contribution of different sensors to pose optimization. Specifically, the observation distribution is shifted towards the motion model 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 SOTA methods to prove its superior degeneracy detection and optimization capabilities across various environments.Keywords
All Related Versions
This publication has 17 references indexed in Scilit:
- Anti-Degeneracy Scheme for Lidar SLAM Based on Particle Filter in Geometry Feature-Less EnvironmentsIEEE Robotics and Automation Letters, 2025
- P2d-DO: Degeneracy Optimization for LiDAR SLAM With Point-to-Distribution Detection FactorsIEEE Robotics and Automation Letters, 2024
- Intermittent VIO-Assisted LiDAR SLAM Against Degeneracy: Recognition and MitigationIEEE Transactions on Instrumentation and Measurement, 2024
- A Fast and Accurate Visual Inertial Odometry Using Hybrid Point-Line FeaturesIEEE Robotics and Automation Letters, 2024
- IMU Augment Tightly Coupled Lidar-Visual-Inertial Odometry for Agricultural EnvironmentsIEEE Robotics and Automation Letters, 2024
- Switch-SLAM: Switching-Based LiDAR-Inertial-Visual SLAM for Degenerate EnvironmentsIEEE Robotics and Automation Letters, 2024
- LIVER: A Tightly Coupled LiDAR-Inertial-Visual State Estimator With High Robustness for Underground EnvironmentsIEEE Robotics and Automation Letters, 2024
- High-Speed Stereo Visual SLAM for Low-Powered Computing DevicesIEEE Robotics and Automation Letters, 2023
- PointNetKL: Deep Inference for GICP Covariance Estimation in Bathymetric SLAMIEEE Robotics and Automation Letters, 2020
- Real-time loop closure in 2D LIDAR SLAM2016