What does this research mean for the field?

An integrated air-ground collaborative exploration method combining 3D Gaussian field-enhanced ORB-SLAM2, G-ICP, and an improved JPS path planning algorithm achieves an 87.5% success rate in complex environments by resolving cross-view registration and optimizing trajectory smoothness. Novelty: ClaimNovelty.METHODOLOGICAL. Consensus alignment: ConsensusAlignment.NEUTRAL.

What question did this study set out to answer?

To resolve relative pose estimation drift and trajectory roughness during air-ground robotic exploration by developing an integrated collaborative localization, dense mapping, and path planning framework.

September 2, 2026Unmanned Systems

Collaborative Exploration of VSLAM Based Autonomous Vehicles and Drones

View Full Paper

Ask AI

Bookmark

Authors

CJChenliu Jiao XZXun Zhao YLYunping Liu

Discussion

Member takes

Overview

Robotic evaluation demonstrates an 87.5% collaborative exploration success rate in air-ground autonomous systems, highlighting improved multi-robot mapping and trajectory optimization.

Key Points

To resolve relative pose estimation drift and trajectory roughness during air-ground robotic exploration by developing an integrated collaborative localization, dense mapping, and path planning framework.
Enhanced ORB-SLAM2 by incorporating a 3D Gaussian field map representation paired with Generalized Iterative Closest Point (G-ICP) registration for cross-view point cloud alignment.
Formulated an improved Jump Point Search (JPS) path planner using dynamic heuristic weights, direction factors, and line-of-sight checks to satisfy vehicle kinematic constraints.
Validated the complete framework using a real heterogeneous robotic platform comprising an autonomous vehicle and an unmanned aerial drone in complex physical scenarios.
The heterogeneous vehicle-drone platform achieved an 87.5% collaborative exploration success rate in complex test environments.
The 3D Gaussian field and G-ICP registration generated globally consistent dense maps, eliminating ground vehicle perceptual blind spots caused by sparse features.
The constrained JPS algorithm effectively avoided local optima while improving trajectory smoothness and kinematic feasibility.

Cite This Study

Jiao et al. (2026) studied this question.

synapsesocial.com/papers/6a97e28dc562ede874ec6c07 https://doi.org/10.1142/s2301385028500665

View Full Paper

Ask AI

Bookmark

September 2, 2026Unmanned Systems

Collaborative Exploration of VSLAM Based Autonomous Vehicles and Drones

View Full Paper

Ask AI

Bookmark

Authors

CJChenliu Jiao XZXun Zhao YLYunping Liu

Discussion

Member takes

Overview

Robotic evaluation demonstrates an 87.5% collaborative exploration success rate in air-ground autonomous systems, highlighting improved multi-robot mapping and trajectory optimization.

Key Points

To resolve relative pose estimation drift and trajectory roughness during air-ground robotic exploration by developing an integrated collaborative localization, dense mapping, and path planning framework.
Enhanced ORB-SLAM2 by incorporating a 3D Gaussian field map representation paired with Generalized Iterative Closest Point (G-ICP) registration for cross-view point cloud alignment.
Formulated an improved Jump Point Search (JPS) path planner using dynamic heuristic weights, direction factors, and line-of-sight checks to satisfy vehicle kinematic constraints.
Validated the complete framework using a real heterogeneous robotic platform comprising an autonomous vehicle and an unmanned aerial drone in complex physical scenarios.
The heterogeneous vehicle-drone platform achieved an 87.5% collaborative exploration success rate in complex test environments.
The 3D Gaussian field and G-ICP registration generated globally consistent dense maps, eliminating ground vehicle perceptual blind spots caused by sparse features.
The constrained JPS algorithm effectively avoided local optima while improving trajectory smoothness and kinematic feasibility.

Cite This Study

Jiao et al. (2026) studied this question.

synapsesocial.com/papers/6a97e28dc562ede874ec6c07 https://doi.org/10.1142/s2301385028500665

Also Consider

Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context:

View Full Paper

Ask AI

Bookmark