6 papers · 1 filter
Mamba-based Selective State Space Modeling Improves the Accuracy-Complexity Tradeoff of SmolVLA Vision-Language-Action Experts
Farida Mohsen, Thowayba Elkaffash, Mohammad Reza Chalak Qazani +3
Vision-language-action (VLA) models face a crucial tradeoff between their task success rate and the policy-call frequency. Executing a single action per inference () enables a…
Real-Time Human-Robot Interaction Intent Detection Using RGB-based Pose and Emotion Cues with Cross-Camera Model Generalization
Farida Mohsen, Ali Safa
Service robots in public spaces require real-time understanding of human behavioral intentions for natural interaction. We present a practical multimodal framework for frame-accura…
MINT-RVAE: Multi-Cues Intention Prediction of Human-Robot Interaction using Human Pose and Emotion Information from RGB-only Camera Data
Farida Mohsen, Ali Safa
Efficiently detecting human intent to interact with ubiquitous robots is crucial for effective human-robot interaction (HRI) and collaboration. Over the past decade, deep learning…
Deep Fusion of Ultra-Low-Resolution Thermal Camera and Gyroscope Data for Lighting-Robust and Compute-Efficient Rotational Odometry
Farida Mohsen, Ali Safa
Accurate rotational odometry is crucial for autonomous robotic systems, particularly for small, power-constrained platforms such as drones and mobile robots. This study introduces…
Benchmarking Online Object Trackers for Underwater Robot Position Locking Applications
Ali Safa, Waqas Aman, Ali Al-Zawqari +1
Autonomously controlling the position of Remotely Operated underwater Vehicles (ROVs) is of crucial importance for a wide range of underwater engineering applications, such as in t…
Co-Design of a Robot Controller Board and Indoor Positioning System for IoT-Enabled Applications
Ali Safa, Ali Al-Zawqari
This paper describes the development of a cost-effective yet precise indoor robot navigation system composed of a custom robot controller board and an indoor positioning system. Fi…