Miguel Antunes

Papers

Total Citations

H-Index

About

Miguel Antunes is a researcher focused on advancing the perception and prediction capabilities of autonomous driving systems. His work centers on sensor fusion, multi-object tracking, and motion forecasting, addressing critical challenges in real-world autonomous vehicle safety. Antunes has made notable contributions to integrating LiDAR and RADAR data for robust object detection and tracking, as demonstrated in his 2022 paper on LiDAR-RADAR fusion in the CARLA simulator (4 citations). He also developed a real-time, power-efficient 3D DAMOT system for autonomous driving, which tackles the growing issue of perception-related accidents in vehicles with Automated Driving Systems (3 citations). In 2023, Antunes introduced an Efficient Context-Aware Graph Transformer for vehicle motion prediction (2 citations), an innovative approach that leverages Bird Eye View HD maps and past trajectories to accurately forecast the movements of multiple surrounding agents—a crucial task for self-driving vehicles and robots. His work bridges simulation and real-time deployment, offering practical solutions for safer autonomous navigation. Antunes’ research is particularly relevant for students and engineers working on sensor integration, deep learning for robotics, and end-to-end autonomous driving pipelines.