Gustavo Batista
Papers
2
Total Citations
23
H-Index
2
About
Gustavo Batista is a researcher at the forefront of autonomous systems and robotics, with a focused expertise in pedestrian trajectory prediction. His work addresses a critical challenge in autonomous driving: anticipating human movement with both accuracy and interpretability. Batista’s major contributions lie in developing deep learning frameworks that integrate explicit, dynamics-based constraints and goal-driven reasoning into motion prediction models. Unlike conventional black-box approaches, his methods incorporate physical priors about human locomotion, resulting in predictions that are not only more reliable but also explainable—a vital feature for safety-critical applications. His most-cited paper, "Pedestrian trajectory prediction using goal-driven and dynamics-based deep learning framework" (2025), has already garnered 17 citations, signaling its immediate impact on the field. A subsequent work from 2024 further refines this approach, earning 6 citations. By bridging the gap between data-driven learning and classical physics-based modeling, Batista is helping to shape the next generation of autonomous navigation systems, where machines must understand and anticipate human intent in complex, dynamic environments.
Research Focus
Key Achievements
Top Papers
- 1
- 2Pedestrian Trajectory Prediction Using Dynamics-based Deep Learning6 citations · 2024