Comprehensive Performance Evaluation between Visual SLAM and LiDAR SLAM for Mobile Robots: Theories and Experiments

Zhao, Yu-Lin; Hong, Yi-Tian; Huang, Han-Pang

doi:10.3390/app14093945

Cited by 3 publications

References 25 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

A semantic SLAM system for dynamic environments

Hu,

Zong,

Mou

et al. 2024

International Conference on Automation and Intelligent Technology (ICAIT 2024)

View full text Add to dashboard Cite

With the development of robotics and self-driving vehicles, simultaneous localization and mapping technology has become critical. Visual SLAM utilizes the camera as the primary sensor and shows significant advantages in texture-rich static environments. However, conventional vision SLAM systems do not perform well in dynamic environments, such as changes in lighting, loss of camera positioning, or movement of feature points due to object motion. This study proposes a new SLAM system for dynamic environments, YOEC-DSLAM. YOEC-DSLAM combines a lightweight semantic segmentation network and a multi-view geometry approach to effectively identify and filter dynamic feature points, thereby significantly improving the accuracy and robustness of map construction. These improvements improve the real-time and accuracy of the system across the board. Experiments show that YOEC-DSLAM exhibits unique advantages in processing highly dynamic scenes.

show abstract

A semantic SLAM system for dynamic environments

Hu,

Zong,

Mou

et al. 2024

International Conference on Automation and Intelligent Technology (ICAIT 2024)

View full text Add to dashboard Cite

show abstract

FGRL: Federated Growing Reinforcement Learning for Resilient Mapless Navigation in Unfamiliar Environments

Tian,

Wei,

et al. 2024

Applied Sciences

View full text Add to dashboard Cite

In this paper, we propose a federated growing reinforcement learning (FGRL) approach for solving the mapless navigation problem of unmanned ground vehicles (UGVs) facing cluttered unfamiliar obstacles. Deep reinforcement learning (DRL) has the potential to provide adaptive behaviors for autonomous agents through interactive learning, but standard episodic DRL algorithms often struggle with out-of-distribution observations. For navigation tasks, UGVs often encounter unfamiliar situations where novel obstacles differ from prior experience. To address this problem, the proposed FGRL approach enables multiple agents to obtain their individual navigation models in diverse scenarios, and achieves online knowledge aggregation to obtain an adaptive and resilient model that copes with unfamiliar uncertain obstacles. Specifically, during the learning process of navigation tasks, we introduce the growth rate of each agent’s local model based on the performance of consecutive learning rounds. Then, we weight the local model of each agent based on the growth rate to achieve knowledge aggregation in a shared model. We also consider a growth threshold to eliminate the interference of low-quality local models. We carry out extensive simulations to validate the proposed solution, and the results show that our approach can learn resilient behaviors of collision avoidance for UGVs to cope with never encountered and cluttered unfamiliar obstacles.

show abstract

Visual-Inertial RGB-D SLAM with Encoder Integration of ORB Triangulation and Depth Measurement Uncertainties

Ma,

Cheng

2024

Sensors

View full text Add to dashboard Cite

In recent years, the accuracy of visual SLAM (Simultaneous Localization and Mapping) technology has seen significant improvements, making it a prominent area of research. However, within the current RGB-D SLAM systems, the estimation of 3D positions of feature points primarily relies on direct measurements from RGB-D depth cameras, which inherently contain measurement errors. Moreover, the potential of triangulation-based estimation for ORB (Oriented FAST and Rotated BRIEF) feature points remains underutilized. To address the singularity of measurement data, this paper proposes the integration of the ORB features, triangulation uncertainty estimation and depth measurements uncertainty estimation, for 3D positions of feature points. This integration is achieved using a CI (Covariance Intersection) filter, referred to as the CI-TEDM (Triangulation Estimates and Depth Measurements) method. Vision-based SLAM systems face significant challenges, particularly in environments, such as long straight corridors, weakly textured scenes, or during rapid motion, where tracking failures are common. To enhance the stability of visual SLAM, this paper introduces an improved CI-TEDM method by incorporating wheel encoder data. The mathematical model of the encoder is proposed, and detailed derivations of the encoder pre-integration model and error model are provided. Building on these improvements, we propose a novel tightly coupled visual-inertial RGB-D SLAM with encoder integration of ORB triangulation and depth measurement uncertainties. Validation on open-source datasets and real-world environments demonstrates that the proposed improvements significantly enhance the robustness of real-time state estimation and localization accuracy for intelligent vehicles in challenging environments.

show abstract

Comprehensive Performance Evaluation between Visual SLAM and LiDAR SLAM for Mobile Robots: Theories and Experiments

Cited by 3 publications

References 25 publications

A semantic SLAM system for dynamic environments

A semantic SLAM system for dynamic environments

FGRL: Federated Growing Reinforcement Learning for Resilient Mapless Navigation in Unfamiliar Environments

Visual-Inertial RGB-D SLAM with Encoder Integration of ORB Triangulation and Depth Measurement Uncertainties

Contact Info

Product

Resources

About