DroneVLA: VLA-based Aerial Manipulation
F. Mehboob*, M. James*, A. Habeel*, J. Sam, M. A. Cabrera, and D. Tsetserukou
ACM/IEEE International Conference on Human-Robot Interaction (HRI) Late-Breaking Report, 2026
Research
Research & Publications
My work sits on one question: how to get the semantic reasoning of foundation models without giving up the reliability classical robotics already provides. Classical methods are not obsolete. The interesting problem is knowing where a learned model earns its place and where a particle filter still wins.
Research Interests
01Multi-agent embodied navigation
02Vision-language models for robotics
03Semantic mapping and spatial perception
04Open-vocabulary object-goal navigation
05Language-goal and image-goal navigation
06Multi-robot task allocation
07SLAM and probabilistic localization
08Control, planning, and field robotics
Publications
Peer-reviewed
2 papers· Accepted and published at a reviewed venue.Hybrid F' and ROS 2 Architecture for Vision-Based Autonomous Flight: Design and Experimental Validation
A. Metwally, M. James, A. Fedoseev, M. Altamirano Cabrera, D. Tsetserukou, A. Somov
IEEE International Conference on Industrial Technology (ICIT), 2026
Preprints
3 papers· Available on arXiv, not peer-reviewed.AnyGoal: Vision-Language Guided Multi-Agent Exploration for Training-Free Lifelong Navigation
M. James et al.
arXiv preprint, 2026
GoalSwarm: Multi-UAV Semantic Coordination for Open-Vocabulary Object Navigation
M. James, A. A. Habel, A. Fedoseev, and D. Tsetserukou
arXiv preprint, 2026
GoalVLM: VLM-driven Object Goal Navigation for Multi-Agent System
M. James, A. Habel, A. Fedoseev, and D. Tsetserukou
arXiv preprint, 2026