Occupancy-SLAM: An Efficient and Robust Algorithm for Simultaneously Optimizing Robot Poses and Occupancy Map

2025-02-10

AI Summary

To address error accumulation arising from the decoupled estimation of robot poses and occupancy maps in featureless SLAM, this paper proposes the first end-to-end joint optimization framework. It parameterizes the voxel-based occupancy map as differentiable vertex variables, unifies them with robot pose variables in a single optimization model, and solves both simultaneously using a nonlinear optimizer (e.g., Ceres Solver). The method supports both 2D and 3D LiDAR data and employs bilinear or trilinear interpolation to model continuous occupancy values. Evaluated on multiple 2D LiDAR benchmarks, it achieves superior trajectory and map accuracy compared to state-of-the-art methods including Cartographer and Hector SLAM, while maintaining comparable computational efficiency. 3D experiments further demonstrate scalability. The core contribution is the paradigm shift from conventional two-stage pipelines to the first differentiable, joint optimization of occupancy map vertices and robot poses.

Technology Category

• Intelligent Robots: State Estimation
• Search and Optimization: Learning to Search
• Computer Vision: Learning & Optimization for CV

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs
• Search and Retrieval-Augmented AI: Web learning to rank, online learning, and counterfactual learning for ranking

Abstract

Joint optimization of poses and features has been extensively studied and demonstrated to yield more accurate results in feature-based SLAM problems. However, research on jointly optimizing poses and non-feature-based maps remains limited. Occupancy maps are widely used non-feature-based environment representations because they effectively classify spaces into obstacles, free areas, and unknown regions, providing robots with spatial information for various tasks. In this paper, we propose Occupancy-SLAM, a novel optimization-based SLAM method that enables the joint optimization of robot trajectory and the occupancy map through a parameterized map representation. The key novelty lies in optimizing both robot poses and occupancy values at different cell vertices simultaneously, a significant departure from existing methods where the robot poses need to be optimized first before the map can be estimated. Evaluations using simulations and practical 2D laser datasets demonstrate that the proposed approach can robustly obtain more accurate robot trajectories and occupancy maps than state-of-the-art techniques with comparable computational time. Preliminary results in the 3D case further confirm the potential of the proposed method in practical 3D applications, achieving more accurate results than existing methods.

Problem

• Optimizes robot poses and occupancy maps jointly
• Introduces parameterized map representation for SLAM
• Enhances accuracy in 2D and 3D applications

Innovation

• Joint optimization of poses and occupancy
• Parameterized map representation for SLAM
• Simultaneous cell vertex and pose optimization