CLChenxi Lu

Chenxi Lu

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Chenxi Lu has a total of 8 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Autonomous Multi-Site Sampling on Asteroids via Landmark Rehearsal-Aware Hopping Trajectory Planning

    by Meng Yu, Ya Wu, Chenxi Lu

    Thoroughly exploring small celestial body surfaces offers significant potentials for scientific rewards, yet it also carries substantial risks. These risks arise primarily from complex surface terrain, micro-gravity environments and weak solar illumination conditions. To address the challenges of conducting continuous and safe sampling across multiple scientifically interesting regions on the asteroid surface, this paper proposes a comprehensive trajectory planning scheme that integrates fine-reconstruction of target landmarks with intelligent hopping trajectory planning. The main idea of this study is to extract metrics related to safety and navigation attributes from candidate landmarks and incorporate them with hopping trajectory planning between adjacent waypoints. The 3D Gaussian Splatting (3DGS) method is first applied to remote sensing images to generate a 3D model of the target area. Then, the generated 3DGS model is employed to render images in trajectory planning module, wherein the ZEM/ZEV path planner is incorporated with reinforcement learning (RL) framework to rehearse visual perception opportunities of landmarks (e.g. rocks or rugged terrains) based upon the rendered images. The RL-enhanced ZEM/ZEV planner allows the rover to flexibly deviate toward targets of interests, which improves the landmark observation opportunities while ensuring safety and navigational performance. Numerical simulations and an experimental trial are carried out to validate the performance of the proposed method, results from which demonstrates that the proposed algorithm can generate safe multi-site hopping trajectories on asteroid surfaces with plausible visual coverage of regions of interest, while maintaining precise localization throughout the process.

  • Open Access

    Autonomous Multi-Site Sampling on Asteroids via Landmark Rehearsal-Aware Hopping Trajectory Planning

    by Meng Yu, Ya Wu, Chenxi Lu

    Thoroughly exploring small celestial body surfaces offers significant potentials for scientific rewards, yet it also carries substantial risks. These risks arise primarily from complex surface terrain, micro-gravity environments and weak solar illumination conditions. To address the challenges of conducting continuous and safe sampling across multiple scientifically interesting regions on the asteroid surface, this paper proposes a comprehensive trajectory planning scheme that integrates fine-reconstruction of target landmarks with intelligent hopping trajectory planning. The main idea of this study is to extract metrics related to safety and navigation attributes from candidate landmarks and incorporate them with hopping trajectory planning between adjacent waypoints. The 3D Gaussian Splatting (3DGS) method is first applied to remote sensing images to generate a 3D model of the target area. Then, the generated 3DGS model is employed to render images in trajectory planning module, wherein the ZEM/ZEV path planner is incorporated with reinforcement learning (RL) framework to rehearse visual perception opportunities of landmarks (e.g. rocks or rugged terrains) based upon the rendered images. The RL-enhanced ZEM/ZEV planner allows the rover to flexibly deviate toward targets of interests, which improves the landmark observation opportunities while ensuring safety and navigational performance. Numerical simulations and an experimental trial are carried out to validate the performance of the proposed method, results from which demonstrates that the proposed algorithm can generate safe multi-site hopping trajectories on asteroid surfaces with plausible visual coverage of regions of interest, while maintaining precise localization throughout the process.

  • Open Access

    AGCNeRF: Air–Ground Collaborative Visual Mapping and Navigation via Landmark-Enhanced Neural Radiance Fields

    by Chenxi Lu, Meng Yu, Yin Wang, Hua Li

    Unmanned vehicles are becoming increasingly essential in executing high-risk missions in unknown environments such as search and rescue. As the complexity of operational environments escalates, carrying out unmanned tasks becomes cumbersome or even infeasible for a single vehicle, hampered by limited perception and operational constraints. Aiming at enhancing the flexibility of unmanned operations under complicated scenarios, this study introduces AGC-NeRF, an innovative air–ground collaborative exploration framework that harnesses the functional complementarity of UAVs and UGVs—enabling a UGV to navigate through a complex scenario with the assistance of a UAV via referencing a neural radiance map. First, a UAV is employed to collect aerial images for reconstructing the environment to be explored by a UGV, leveraging its aerial perspective to achieve wide-area coverage and global environmental perception that is unattainable for a single UGV. Concurrently, an innovative image saliency evaluation approach is introduced to meticulously select landmarks that are contributive to the UGV’s navigation system, yielding a pre-trained NeRF model of the operation scene. Then, a landmark-aware 6-DOF ego-motion estimator and collision-free trajectory optimizer are designed for the UGV based on the NeRF map. Finally, an online replanning architecture is established which relies on a ground station for NeRF training and state optimization by synergizing the trajectory planner and the state estimator, which forms a dual-agent vision-only navigation pipeline. Simulations and experiments validate that AGC-NeRF enables reliable UGV trajectory planning and state estimation in unknown environments, demonstrating superior efficacy and robustness of the air–ground collaborative paradigm.