Event
Extended LASMP: Language Instruction-Guided UAV Sampling Planning
1 reports · 1 sources
Saswati Bhattacharjee and other authors propose Extended LASMP, a sampling-based motion planning method for 3D navigation of quadrotors: it incorporates navigation instructions directly into the sampling distribution, concentrating samples in regions aligned with the instructions, and uses a prompt-based large language model to parse natural language instructions into yaw conditions and altitude-aware geometric constraints. The authors state that extensive simulations in complex environments show that the method can generate collision-free and consistent trajectories, substantially reducing the number of samples compared with uniform RRT-type planners. These conclusions currently come from simulation; real flight validation has not yet been reported.
Report timeline
- Extended LASMP: A Language-Aided Subset Sampling Motion Planner for Drone Navigation
The paper proposes Extended LASMP, which incorporates navigation commands directly into the sampling distribution to improve the exploration efficiency of sampling-based motion planning for quadcopters in three-dimensional environments. The method generalizes subset sampling to command-aligned regions and uses a prompt-based large language model to parse natural-language instructions into yaw-conditioned and altitude-aware geometric constraints. Simulations in complex environments show that the method generates collision-free, consistent trajectories while significantly reducing sampling effort compared with uniform RRT-based planners.
arXiv cs.RO ·