Papers
2
Total Citations
23
H-Index
2
About
Francisco Souza is a researcher at the intersection of mobile robotics and probabilistic machine learning, with a primary focus on semantic place classification and time-dependent inference systems. His most influential work, "Applying Probabilistic Mixture Models to Semantic Place Classification in Mobile Robotics" (2015, 20 citations), addresses the challenge of enabling robots to understand their indoor environments by classifying sensor data into meaningful semantic categories. Souza’s approach transforms raw sensor readings into feature spaces and applies supervised probabilistic classification, significantly advancing how robots perceive and interact with their surroundings. He further extends this work in "Dynamic Bayesian Network for Time-Dependent Classification Problems in Robotics" (2017, 3 citations), where he introduces dynamic Bayesian networks (DBNs) to model temporal dependencies in classification tasks. By leveraging Bayesian inference to incorporate prior knowledge and sequential observations, Souza’s DBN framework enhances robotic decision-making in dynamic environments. His contributions are particularly valuable for autonomous systems that must operate reliably over time, and his work continues to influence research in probabilistic robotics and intelligent perception.
Research Focus
Key Achievements
Top Papers
- 1
- 2